xdl/stable-diffusion-webui
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

first commit
Some checks failed
Linter / ruff (push) Has been cancelled
Details
Linter / eslint (push) Has been cancelled
Details
Tests / tests on CPU with empty model (push) Has been cancelled
Details

Browse Source
This commit is contained in:
xdl 2024-12-18 15:48:02 +08:00
commit e354d5af27
305 changed files with 54496 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
.eslintignore Normal file
View File

@ -0,0 +1,4 @@
extensions
extensions-disabled
repositories
venv

98
.eslintrc.js Normal file
View File

@ -0,0 +1,98 @@
/* global module */
module.exports = {
env: {
browser: true,
es2021: true,
},
extends: "eslint:recommended",
parserOptions: {
ecmaVersion: "latest",
},
rules: {
"arrow-spacing": "error",
"block-spacing": "error",
"brace-style": "error",
"comma-dangle": ["error", "only-multiline"],
"comma-spacing": "error",
"comma-style": ["error", "last"],
"curly": ["error", "multi-line", "consistent"],
"eol-last": "error",
"func-call-spacing": "error",
"function-call-argument-newline": ["error", "consistent"],
"function-paren-newline": ["error", "consistent"],
"indent": ["error", 4],
"key-spacing": "error",
"keyword-spacing": "error",
"linebreak-style": ["error", "unix"],
"no-extra-semi": "error",
"no-mixed-spaces-and-tabs": "error",
"no-multi-spaces": "error",
"no-redeclare": ["error", {builtinGlobals: false}],
"no-trailing-spaces": "error",
"no-unused-vars": "off",
"no-whitespace-before-property": "error",
"object-curly-newline": ["error", {consistent: true, multiline: true}],
"object-curly-spacing": ["error", "never"],
"operator-linebreak": ["error", "after"],
"quote-props": ["error", "consistent-as-needed"],
"semi": ["error", "always"],
"semi-spacing": "error",
"semi-style": ["error", "last"],
"space-before-blocks": "error",
"space-before-function-paren": ["error", "never"],
"space-in-parens": ["error", "never"],
"space-infix-ops": "error",
"space-unary-ops": "error",
"switch-colon-spacing": "error",
"template-curly-spacing": ["error", "never"],
"unicode-bom": "error",
},
globals: {
//script.js
gradioApp: "readonly",
executeCallbacks: "readonly",
onAfterUiUpdate: "readonly",
onOptionsChanged: "readonly",
onUiLoaded: "readonly",
onUiUpdate: "readonly",
uiCurrentTab: "writable",
uiElementInSight: "readonly",
uiElementIsVisible: "readonly",
//ui.js
opts: "writable",
all_gallery_buttons: "readonly",
selected_gallery_button: "readonly",
selected_gallery_index: "readonly",
switch_to_txt2img: "readonly",
switch_to_img2img_tab: "readonly",
switch_to_img2img: "readonly",
switch_to_sketch: "readonly",
switch_to_inpaint: "readonly",
switch_to_inpaint_sketch: "readonly",
switch_to_extras: "readonly",
get_tab_index: "readonly",
create_submit_args: "readonly",
restart_reload: "readonly",
updateInput: "readonly",
onEdit: "readonly",
//extraNetworks.js
requestGet: "readonly",
popup: "readonly",
// profilerVisualization.js
createVisualizationTable: "readonly",
// from python
localization: "readonly",
// progrssbar.js
randomId: "readonly",
requestProgress: "readonly",
// imageviewer.js
modalPrevImage: "readonly",
modalNextImage: "readonly",
// localStorage.js
localSet: "readonly",
localGet: "readonly",
localRemove: "readonly",
// resizeHandle.js
setupResizeHandle: "writable"
}
};

2
.git-blame-ignore-revs Normal file
View File

@ -0,0 +1,2 @@
# Apply ESlint
9c54b78d9dde5601e916f308d9a9d6953ec39430

105
.github/ISSUE_TEMPLATE/bug_report.yml vendored Normal file
View File

@ -0,0 +1,105 @@
name: Bug Report
description: You think something is broken in the UI
title: "[Bug]: "
labels: ["bug-report"]
body:
- type: markdown
attributes:
value: |
> The title of the bug report should be short and descriptive.
> Use relevant keywords for searchability.
> Do not leave it blank, but also do not put an entire error log in it.
- type: checkboxes
attributes:
label: Checklist
description: |
Please perform basic debugging to see if extensions or configuration is the cause of the issue.
Basic debug procedure
　1. Disable all third-party extensions - check if extension is the cause
　2. Update extensions and webui - sometimes things just need to be updated
　3. Backup and remove your config.json and ui-config.json - check if the issue is caused by bad configuration
　4. Delete venv with third-party extensions disabled - sometimes extensions might cause wrong libraries to be installed
　5. Try a fresh installation webui in a different directory - see if a clean installation solves the issue
Before making a issue report please, check that the issue hasn't been reported recently.
options:
- label: The issue exists after disabling all extensions
- label: The issue exists on a clean installation of webui
- label: The issue is caused by an extension, but I believe it is caused by a bug in the webui
- label: The issue exists in the current version of the webui
- label: The issue has not been reported before recently
- label: The issue has been reported before but has not been fixed yet
- type: markdown
attributes:
value: |
> Please fill this form with as much information as possible. Don't forget to "Upload Sysinfo" and "What browsers" and provide screenshots if possible
- type: textarea
id: what-did
attributes:
label: What happened?
description: Tell us what happened in a very clear and simple way
placeholder: |
txt2img is not working as intended.
validations:
required: true
- type: textarea
id: steps
attributes:
label: Steps to reproduce the problem
description: Please provide us with precise step by step instructions on how to reproduce the bug
placeholder: |
1. Go to ...
2. Press ...
3. ...
validations:
required: true
- type: textarea
id: what-should
attributes:
label: What should have happened?
description: Tell us what you think the normal behavior should be
placeholder: |
WebUI should ...
validations:
required: true
- type: dropdown
id: browsers
attributes:
label: What browsers do you use to access the UI ?
multiple: true
options:
- Mozilla Firefox
- Google Chrome
- Brave
- Apple Safari
- Microsoft Edge
- Android
- iOS
- Other
- type: textarea
id: sysinfo
attributes:
label: Sysinfo
description: System info file, generated by WebUI. You can generate it in settings, on the Sysinfo page. Drag the file into the field to upload it. If you submit your report without including the sysinfo file, the report will be closed. If needed, review the report to make sure it includes no personal information you don't want to share. If you can't start WebUI, you can use --dump-sysinfo commandline argument to generate the file.
placeholder: |
1. Go to WebUI Settings -> Sysinfo -> Download system info.
If WebUI fails to launch, use --dump-sysinfo commandline argument to generate the file
2. Upload the Sysinfo as a attached file, Do NOT paste it in as plain text.
validations:
required: true
- type: textarea
id: logs
attributes:
label: Console logs
description: Please provide **full** cmd/terminal logs from the moment you started UI to the end of it, after the bug occurred. If it's very long, provide a link to pastebin or similar service.
render: Shell
validations:
required: true
- type: textarea
id: misc
attributes:
label: Additional information
description: |
Please provide us with any relevant additional info or context.
Examples:
　I have updated my GPU driver recently.

5
.github/ISSUE_TEMPLATE/config.yml vendored Normal file
View File

@ -0,0 +1,5 @@
blank_issues_enabled: false
contact_links:
- name: WebUI Community Support
url: https://github.com/AUTOMATIC1111/stable-diffusion-webui/discussions
about: Please ask and answer questions here.

40
.github/ISSUE_TEMPLATE/feature_request.yml vendored Normal file
View File

@ -0,0 +1,40 @@
name: Feature request
description: Suggest an idea for this project
title: "[Feature Request]: "
labels: ["enhancement"]
body:
- type: checkboxes
attributes:
label: Is there an existing issue for this?
description: Please search to see if an issue already exists for the feature you want, and that it's not implemented in a recent build/commit.
options:
- label: I have searched the existing issues and checked the recent builds/commits
required: true
- type: markdown
attributes:
value: |
*Please fill this form with as much information as possible, provide screenshots and/or illustrations of the feature if possible*
- type: textarea
id: feature
attributes:
label: What would your feature do ?
description: Tell us about your feature in a very clear and simple way, and what problem it would solve
validations:
required: true
- type: textarea
id: workflow
attributes:
label: Proposed workflow
description: Please provide us with step by step information on how you'd like the feature to be accessed and used
value: |
1. Go to ....
2. Press ....
3. ...
validations:
required: true
- type: textarea
id: misc
attributes:
label: Additional information
description: Add any other context or screenshots about the feature request here.

15
.github/pull_request_template.md vendored Normal file
View File

@ -0,0 +1,15 @@
## Description
* a simple description of what you're trying to accomplish
* a summary of changes in code
* which issues it fixes, if any
## Screenshots/videos:
## Checklist:
- [ ] I have read [contributing wiki page](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Contributing)
- [ ] I have performed a self-review of my own code
- [ ] My code follows the [style guidelines](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Contributing#code-style)
- [ ] My code passes [tests](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Tests)

38
.github/workflows/on_pull_request.yaml vendored Normal file
View File

@ -0,0 +1,38 @@
name: Linter
on:
- push
- pull_request
jobs:
lint-python:
name: ruff
runs-on: ubuntu-latest
if: github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name != github.event.pull_request.base.repo.full_name
steps:
- name: Checkout Code
uses: actions/checkout@v4
- uses: actions/setup-python@v5
with:
python-version: 3.11
# NB: there's no cache: pip here since we're not installing anything
# from the requirements.txt file(s) in the repository; it's faster
# not to have GHA download an (at the time of writing) 4 GB cache
# of PyTorch and other dependencies.
- name: Install Ruff
run: pip install ruff==0.3.3
- name: Run Ruff
run: ruff .
lint-js:
name: eslint
runs-on: ubuntu-latest
if: github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name != github.event.pull_request.base.repo.full_name
steps:
- name: Checkout Code
uses: actions/checkout@v4
- name: Install Node.js
uses: actions/setup-node@v4
with:
node-version: 18
- run: npm i --ci
- run: npm run lint

81
.github/workflows/run_tests.yaml vendored Normal file
View File

@ -0,0 +1,81 @@
name: Tests
on:
- push
- pull_request
jobs:
test:
name: tests on CPU with empty model
runs-on: ubuntu-latest
if: github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name != github.event.pull_request.base.repo.full_name
steps:
- name: Checkout Code
uses: actions/checkout@v4
- name: Set up Python 3.10
uses: actions/setup-python@v5
with:
python-version: 3.10.6
cache: pip
cache-dependency-path: |
**/requirements*txt
launch.py
- name: Cache models
id: cache-models
uses: actions/cache@v4
with:
path: models
key: "2023-12-30"
- name: Install test dependencies
run: pip install wait-for-it -r requirements-test.txt
env:
PIP_DISABLE_PIP_VERSION_CHECK: "1"
PIP_PROGRESS_BAR: "off"
- name: Setup environment
run: python launch.py --skip-torch-cuda-test --exit
env:
PIP_DISABLE_PIP_VERSION_CHECK: "1"
PIP_PROGRESS_BAR: "off"
TORCH_INDEX_URL: https://download.pytorch.org/whl/cpu
WEBUI_LAUNCH_LIVE_OUTPUT: "1"
PYTHONUNBUFFERED: "1"
- name: Print installed packages
run: pip freeze
- name: Start test server
run: >
python -m coverage run
--data-file=.coverage.server
launch.py
--skip-prepare-environment
--skip-torch-cuda-test
--test-server
--do-not-download-clip
--no-half
--disable-opt-split-attention
--use-cpu all
--api-server-stop
2>&1 | tee output.txt &
- name: Run tests
run: |
wait-for-it --service 127.0.0.1:7860 -t 20
python -m pytest -vv --junitxml=test/results.xml --cov . --cov-report=xml --verify-base-url test
- name: Kill test server
if: always()
run: curl -vv -XPOST http://127.0.0.1:7860/sdapi/v1/server-stop && sleep 10
- name: Show coverage
run: |
python -m coverage combine .coverage*
python -m coverage report -i
python -m coverage html -i
- name: Upload main app output
uses: actions/upload-artifact@v4
if: always()
with:
name: output
path: output.txt
- name: Upload coverage HTML
uses: actions/upload-artifact@v4
if: always()
with:
name: htmlcov
path: htmlcov

19
.github/workflows/warns_merge_master.yml vendored Normal file
View File

@ -0,0 +1,19 @@
name: Pull requests can't target master branch
"on":
pull_request:
types:
- opened
- synchronize
- reopened
branches:
- master
jobs:
check:
runs-on: ubuntu-latest
steps:
- name: Warning marge into master
run: |
echo -e "::warning::This pull request directly merge into \"master\" branch, normally development happens on \"dev\" branch."
exit 1

44
.gitignore vendored Normal file
View File

@ -0,0 +1,44 @@
__pycache__
*.ckpt
*.safetensors
*.pth
.DS_Store
/ESRGAN/*
/SwinIR/*
/repositories
/venv
/tmp
/model.ckpt
/models/**/*
/GFPGANv1.3.pth
/gfpgan/weights/*.pth
/ui-config.json
/outputs
/config.json
/log
/webui.settings.bat
/embeddings
/styles.csv
/params.txt
/styles.csv.bak
/webui-user.bat
/webui-user.sh
/interrogate
/user.css
/.idea
notification.mp3
/SwinIR
/textual_inversion
.vscode
/extensions
/test/stdout.txt
/test/stderr.txt
/cache.json*
/config_states/
/node_modules
/package-lock.json
/.coverage*
/test/test_outputs
/cache
trace.json
/sysinfo-????-??-??-??-??.json

3
.pylintrc Normal file
View File

@ -0,0 +1,3 @@
# See https://pylint.pycqa.org/en/latest/user_guide/messages/message_control.html
[MESSAGES CONTROL]
disable=C,R,W,E,I

1085
CHANGELOG.md Normal file
View File

File diff suppressed because it is too large Load Diff

7
CITATION.cff Normal file
View File

@ -0,0 +1,7 @@
cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
- given-names: AUTOMATIC1111
title: "Stable Diffusion Web UI"
date-released: 2022-08-22
url: "https://github.com/AUTOMATIC1111/stable-diffusion-webui"

12
CODEOWNERS Normal file
View File

@ -0,0 +1,12 @@
* @AUTOMATIC1111
# if you were managing a localization and were removed from this file, this is because
# the intended way to do localizations now is via extensions. See:
# https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Developing-extensions
# Make a repo with your localization and since you are still listed as a collaborator
# you can add it to the wiki page yourself. This change is because some people complained
# the git commit log is cluttered with things unrelated to almost everyone and
# because I believe this is the best overall for the project to handle localizations almost
# entirely without my oversight.

663
LICENSE.txt Normal file
View File

@ -0,0 +1,663 @@
GNU AFFERO GENERAL PUBLIC LICENSE
Version 3, 19 November 2007
Copyright (c) 2023 AUTOMATIC1111
Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
Preamble
The GNU Affero General Public License is a free, copyleft license for
software and other kinds of works, specifically designed to ensure
cooperation with the community in the case of network server software.
The licenses for most software and other practical works are designed
to take away your freedom to share and change the works. By contrast,
our General Public Licenses are intended to guarantee your freedom to
share and change all versions of a program--to make sure it remains free
software for all its users.
When we speak of free software, we are referring to freedom, not
price. Our General Public Licenses are designed to make sure that you
have the freedom to distribute copies of free software (and charge for
them if you wish), that you receive source code or can get it if you
want it, that you can change the software or use pieces of it in new
free programs, and that you know you can do these things.
Developers that use our General Public Licenses protect your rights
with two steps: (1) assert copyright on the software, and (2) offer
you this License which gives you legal permission to copy, distribute
and/or modify the software.
A secondary benefit of defending all users' freedom is that
improvements made in alternate versions of the program, if they
receive widespread use, become available for other developers to
incorporate. Many developers of free software are heartened and
encouraged by the resulting cooperation. However, in the case of
software used on network servers, this result may fail to come about.
The GNU General Public License permits making a modified version and
letting the public access it on a server without ever releasing its
source code to the public.
The GNU Affero General Public License is designed specifically to
ensure that, in such cases, the modified source code becomes available
to the community. It requires the operator of a network server to
provide the source code of the modified version running there to the
users of that server. Therefore, public use of a modified version, on
a publicly accessible server, gives the public access to the source
code of the modified version.
An older license, called the Affero General Public License and
published by Affero, was designed to accomplish similar goals. This is
a different license, not a version of the Affero GPL, but Affero has
released a new version of the Affero GPL which permits relicensing under
this license.
The precise terms and conditions for copying, distribution and
modification follow.
TERMS AND CONDITIONS
0. Definitions.
"This License" refers to version 3 of the GNU Affero General Public License.
"Copyright" also means copyright-like laws that apply to other kinds of
works, such as semiconductor masks.
"The Program" refers to any copyrightable work licensed under this
License. Each licensee is addressed as "you". "Licensees" and
"recipients" may be individuals or organizations.
To "modify" a work means to copy from or adapt all or part of the work
in a fashion requiring copyright permission, other than the making of an
exact copy. The resulting work is called a "modified version" of the
earlier work or a work "based on" the earlier work.
A "covered work" means either the unmodified Program or a work based
on the Program.
To "propagate" a work means to do anything with it that, without
permission, would make you directly or secondarily liable for
infringement under applicable copyright law, except executing it on a
computer or modifying a private copy. Propagation includes copying,
distribution (with or without modification), making available to the
public, and in some countries other activities as well.
To "convey" a work means any kind of propagation that enables other
parties to make or receive copies. Mere interaction with a user through
a computer network, with no transfer of a copy, is not conveying.
An interactive user interface displays "Appropriate Legal Notices"
to the extent that it includes a convenient and prominently visible
feature that (1) displays an appropriate copyright notice, and (2)
tells the user that there is no warranty for the work (except to the
extent that warranties are provided), that licensees may convey the
work under this License, and how to view a copy of this License. If
the interface presents a list of user commands or options, such as a
menu, a prominent item in the list meets this criterion.
1. Source Code.
The "source code" for a work means the preferred form of the work
for making modifications to it. "Object code" means any non-source
form of a work.
A "Standard Interface" means an interface that either is an official
standard defined by a recognized standards body, or, in the case of
interfaces specified for a particular programming language, one that
is widely used among developers working in that language.
The "System Libraries" of an executable work include anything, other
than the work as a whole, that (a) is included in the normal form of
packaging a Major Component, but which is not part of that Major
Component, and (b) serves only to enable use of the work with that
Major Component, or to implement a Standard Interface for which an
implementation is available to the public in source code form. A
"Major Component", in this context, means a major essential component
(kernel, window system, and so on) of the specific operating system
(if any) on which the executable work runs, or a compiler used to
produce the work, or an object code interpreter used to run it.
The "Corresponding Source" for a work in object code form means all
the source code needed to generate, install, and (for an executable
work) run the object code and to modify the work, including scripts to
control those activities. However, it does not include the work's
System Libraries, or general-purpose tools or generally available free
programs which are used unmodified in performing those activities but
which are not part of the work. For example, Corresponding Source
includes interface definition files associated with source files for
the work, and the source code for shared libraries and dynamically
linked subprograms that the work is specifically designed to require,
such as by intimate data communication or control flow between those
subprograms and other parts of the work.
The Corresponding Source need not include anything that users
can regenerate automatically from other parts of the Corresponding
Source.
The Corresponding Source for a work in source code form is that
same work.
2. Basic Permissions.
All rights granted under this License are granted for the term of
copyright on the Program, and are irrevocable provided the stated
conditions are met. This License explicitly affirms your unlimited
permission to run the unmodified Program. The output from running a
covered work is covered by this License only if the output, given its
content, constitutes a covered work. This License acknowledges your
rights of fair use or other equivalent, as provided by copyright law.
You may make, run and propagate covered works that you do not
convey, without conditions so long as your license otherwise remains
in force. You may convey covered works to others for the sole purpose
of having them make modifications exclusively for you, or provide you
with facilities for running those works, provided that you comply with
the terms of this License in conveying all material for which you do
not control copyright. Those thus making or running the covered works
for you must do so exclusively on your behalf, under your direction
and control, on terms that prohibit them from making any copies of
your copyrighted material outside their relationship with you.
Conveying under any other circumstances is permitted solely under
the conditions stated below. Sublicensing is not allowed; section 10
makes it unnecessary.
3. Protecting Users' Legal Rights From Anti-Circumvention Law.
No covered work shall be deemed part of an effective technological
measure under any applicable law fulfilling obligations under article
11 of the WIPO copyright treaty adopted on 20 December 1996, or
similar laws prohibiting or restricting circumvention of such
measures.
When you convey a covered work, you waive any legal power to forbid
circumvention of technological measures to the extent such circumvention
is effected by exercising rights under this License with respect to
the covered work, and you disclaim any intention to limit operation or
modification of the work as a means of enforcing, against the work's
users, your or third parties' legal rights to forbid circumvention of
technological measures.
4. Conveying Verbatim Copies.
You may convey verbatim copies of the Program's source code as you
receive it, in any medium, provided that you conspicuously and
appropriately publish on each copy an appropriate copyright notice;
keep intact all notices stating that this License and any
non-permissive terms added in accord with section 7 apply to the code;
keep intact all notices of the absence of any warranty; and give all
recipients a copy of this License along with the Program.
You may charge any price or no price for each copy that you convey,
and you may offer support or warranty protection for a fee.
5. Conveying Modified Source Versions.
You may convey a work based on the Program, or the modifications to
produce it from the Program, in the form of source code under the
terms of section 4, provided that you also meet all of these conditions:
a) The work must carry prominent notices stating that you modified
it, and giving a relevant date.
b) The work must carry prominent notices stating that it is
released under this License and any conditions added under section
7. This requirement modifies the requirement in section 4 to
"keep intact all notices".
c) You must license the entire work, as a whole, under this
License to anyone who comes into possession of a copy. This
License will therefore apply, along with any applicable section 7
additional terms, to the whole of the work, and all its parts,
regardless of how they are packaged. This License gives no
permission to license the work in any other way, but it does not
invalidate such permission if you have separately received it.
d) If the work has interactive user interfaces, each must display
Appropriate Legal Notices; however, if the Program has interactive
interfaces that do not display Appropriate Legal Notices, your
work need not make them do so.
A compilation of a covered work with other separate and independent
works, which are not by their nature extensions of the covered work,
and which are not combined with it such as to form a larger program,
in or on a volume of a storage or distribution medium, is called an
"aggregate" if the compilation and its resulting copyright are not
used to limit the access or legal rights of the compilation's users
beyond what the individual works permit. Inclusion of a covered work
in an aggregate does not cause this License to apply to the other
parts of the aggregate.
6. Conveying Non-Source Forms.
You may convey a covered work in object code form under the terms
of sections 4 and 5, provided that you also convey the
machine-readable Corresponding Source under the terms of this License,
in one of these ways:
a) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by the
Corresponding Source fixed on a durable physical medium
customarily used for software interchange.
b) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by a
written offer, valid for at least three years and valid for as
long as you offer spare parts or customer support for that product
model, to give anyone who possesses the object code either (1) a
copy of the Corresponding Source for all the software in the
product that is covered by this License, on a durable physical
medium customarily used for software interchange, for a price no
more than your reasonable cost of physically performing this
conveying of source, or (2) access to copy the
Corresponding Source from a network server at no charge.
c) Convey individual copies of the object code with a copy of the
written offer to provide the Corresponding Source. This
alternative is allowed only occasionally and noncommercially, and
only if you received the object code with such an offer, in accord
with subsection 6b.
d) Convey the object code by offering access from a designated
place (gratis or for a charge), and offer equivalent access to the
Corresponding Source in the same way through the same place at no
further charge. You need not require recipients to copy the
Corresponding Source along with the object code. If the place to
copy the object code is a network server, the Corresponding Source
may be on a different server (operated by you or a third party)
that supports equivalent copying facilities, provided you maintain
clear directions next to the object code saying where to find the
Corresponding Source. Regardless of what server hosts the
Corresponding Source, you remain obligated to ensure that it is
available for as long as needed to satisfy these requirements.
e) Convey the object code using peer-to-peer transmission, provided
you inform other peers where the object code and Corresponding
Source of the work are being offered to the general public at no
charge under subsection 6d.
A separable portion of the object code, whose source code is excluded
from the Corresponding Source as a System Library, need not be
included in conveying the object code work.
A "User Product" is either (1) a "consumer product", which means any
tangible personal property which is normally used for personal, family,
or household purposes, or (2) anything designed or sold for incorporation
into a dwelling. In determining whether a product is a consumer product,
doubtful cases shall be resolved in favor of coverage. For a particular
product received by a particular user, "normally used" refers to a
typical or common use of that class of product, regardless of the status
of the particular user or of the way in which the particular user
actually uses, or expects or is expected to use, the product. A product
is a consumer product regardless of whether the product has substantial
commercial, industrial or non-consumer uses, unless such uses represent
the only significant mode of use of the product.
"Installation Information" for a User Product means any methods,
procedures, authorization keys, or other information required to install
and execute modified versions of a covered work in that User Product from
a modified version of its Corresponding Source. The information must
suffice to ensure that the continued functioning of the modified object
code is in no case prevented or interfered with solely because
modification has been made.
If you convey an object code work under this section in, or with, or
specifically for use in, a User Product, and the conveying occurs as
part of a transaction in which the right of possession and use of the
User Product is transferred to the recipient in perpetuity or for a
fixed term (regardless of how the transaction is characterized), the
Corresponding Source conveyed under this section must be accompanied
by the Installation Information. But this requirement does not apply
if neither you nor any third party retains the ability to install
modified object code on the User Product (for example, the work has
been installed in ROM).
The requirement to provide Installation Information does not include a
requirement to continue to provide support service, warranty, or updates
for a work that has been modified or installed by the recipient, or for
the User Product in which it has been modified or installed. Access to a
network may be denied when the modification itself materially and
adversely affects the operation of the network or violates the rules and
protocols for communication across the network.
Corresponding Source conveyed, and Installation Information provided,
in accord with this section must be in a format that is publicly
documented (and with an implementation available to the public in
source code form), and must require no special password or key for
unpacking, reading or copying.
7. Additional Terms.
"Additional permissions" are terms that supplement the terms of this
License by making exceptions from one or more of its conditions.
Additional permissions that are applicable to the entire Program shall
be treated as though they were included in this License, to the extent
that they are valid under applicable law. If additional permissions
apply only to part of the Program, that part may be used separately
under those permissions, but the entire Program remains governed by
this License without regard to the additional permissions.
When you convey a copy of a covered work, you may at your option
remove any additional permissions from that copy, or from any part of
it. (Additional permissions may be written to require their own
removal in certain cases when you modify the work.) You may place
additional permissions on material, added by you to a covered work,
for which you have or can give appropriate copyright permission.
Notwithstanding any other provision of this License, for material you
add to a covered work, you may (if authorized by the copyright holders of
that material) supplement the terms of this License with terms:
a) Disclaiming warranty or limiting liability differently from the
terms of sections 15 and 16 of this License; or
b) Requiring preservation of specified reasonable legal notices or
author attributions in that material or in the Appropriate Legal
Notices displayed by works containing it; or
c) Prohibiting misrepresentation of the origin of that material, or
requiring that modified versions of such material be marked in
reasonable ways as different from the original version; or
d) Limiting the use for publicity purposes of names of licensors or
authors of the material; or
e) Declining to grant rights under trademark law for use of some
trade names, trademarks, or service marks; or
f) Requiring indemnification of licensors and authors of that
material by anyone who conveys the material (or modified versions of
it) with contractual assumptions of liability to the recipient, for
any liability that these contractual assumptions directly impose on
those licensors and authors.
All other non-permissive additional terms are considered "further
restrictions" within the meaning of section 10. If the Program as you
received it, or any part of it, contains a notice stating that it is
governed by this License along with a term that is a further
restriction, you may remove that term. If a license document contains
a further restriction but permits relicensing or conveying under this
License, you may add to a covered work material governed by the terms
of that license document, provided that the further restriction does
not survive such relicensing or conveying.
If you add terms to a covered work in accord with this section, you
must place, in the relevant source files, a statement of the
additional terms that apply to those files, or a notice indicating
where to find the applicable terms.
Additional terms, permissive or non-permissive, may be stated in the
form of a separately written license, or stated as exceptions;
the above requirements apply either way.
8. Termination.
You may not propagate or modify a covered work except as expressly
provided under this License. Any attempt otherwise to propagate or
modify it is void, and will automatically terminate your rights under
this License (including any patent licenses granted under the third
paragraph of section 11).
However, if you cease all violation of this License, then your
license from a particular copyright holder is reinstated (a)
provisionally, unless and until the copyright holder explicitly and
finally terminates your license, and (b) permanently, if the copyright
holder fails to notify you of the violation by some reasonable means
prior to 60 days after the cessation.
Moreover, your license from a particular copyright holder is
reinstated permanently if the copyright holder notifies you of the
violation by some reasonable means, this is the first time you have
received notice of violation of this License (for any work) from that
copyright holder, and you cure the violation prior to 30 days after
your receipt of the notice.
Termination of your rights under this section does not terminate the
licenses of parties who have received copies or rights from you under
this License. If your rights have been terminated and not permanently
reinstated, you do not qualify to receive new licenses for the same
material under section 10.
9. Acceptance Not Required for Having Copies.
You are not required to accept this License in order to receive or
run a copy of the Program. Ancillary propagation of a covered work
occurring solely as a consequence of using peer-to-peer transmission
to receive a copy likewise does not require acceptance. However,
nothing other than this License grants you permission to propagate or
modify any covered work. These actions infringe copyright if you do
not accept this License. Therefore, by modifying or propagating a
covered work, you indicate your acceptance of this License to do so.
10. Automatic Licensing of Downstream Recipients.
Each time you convey a covered work, the recipient automatically
receives a license from the original licensors, to run, modify and
propagate that work, subject to this License. You are not responsible
for enforcing compliance by third parties with this License.
An "entity transaction" is a transaction transferring control of an
organization, or substantially all assets of one, or subdividing an
organization, or merging organizations. If propagation of a covered
work results from an entity transaction, each party to that
transaction who receives a copy of the work also receives whatever
licenses to the work the party's predecessor in interest had or could
give under the previous paragraph, plus a right to possession of the
Corresponding Source of the work from the predecessor in interest, if
the predecessor has it or can get it with reasonable efforts.
You may not impose any further restrictions on the exercise of the
rights granted or affirmed under this License. For example, you may
not impose a license fee, royalty, or other charge for exercise of
rights granted under this License, and you may not initiate litigation
(including a cross-claim or counterclaim in a lawsuit) alleging that
any patent claim is infringed by making, using, selling, offering for
sale, or importing the Program or any portion of it.
11. Patents.
A "contributor" is a copyright holder who authorizes use under this
License of the Program or a work on which the Program is based. The
work thus licensed is called the contributor's "contributor version".
A contributor's "essential patent claims" are all patent claims
owned or controlled by the contributor, whether already acquired or
hereafter acquired, that would be infringed by some manner, permitted
by this License, of making, using, or selling its contributor version,
but do not include claims that would be infringed only as a
consequence of further modification of the contributor version. For
purposes of this definition, "control" includes the right to grant
patent sublicenses in a manner consistent with the requirements of
this License.
Each contributor grants you a non-exclusive, worldwide, royalty-free
patent license under the contributor's essential patent claims, to
make, use, sell, offer for sale, import and otherwise run, modify and
propagate the contents of its contributor version.
In the following three paragraphs, a "patent license" is any express
agreement or commitment, however denominated, not to enforce a patent
(such as an express permission to practice a patent or covenant not to
sue for patent infringement). To "grant" such a patent license to a
party means to make such an agreement or commitment not to enforce a
patent against the party.
If you convey a covered work, knowingly relying on a patent license,
and the Corresponding Source of the work is not available for anyone
to copy, free of charge and under the terms of this License, through a
publicly available network server or other readily accessible means,
then you must either (1) cause the Corresponding Source to be so
available, or (2) arrange to deprive yourself of the benefit of the
patent license for this particular work, or (3) arrange, in a manner
consistent with the requirements of this License, to extend the patent
license to downstream recipients. "Knowingly relying" means you have
actual knowledge that, but for the patent license, your conveying the
covered work in a country, or your recipient's use of the covered work
in a country, would infringe one or more identifiable patents in that
country that you have reason to believe are valid.
If, pursuant to or in connection with a single transaction or
arrangement, you convey, or propagate by procuring conveyance of, a
covered work, and grant a patent license to some of the parties
receiving the covered work authorizing them to use, propagate, modify
or convey a specific copy of the covered work, then the patent license
you grant is automatically extended to all recipients of the covered
work and works based on it.
A patent license is "discriminatory" if it does not include within
the scope of its coverage, prohibits the exercise of, or is
conditioned on the non-exercise of one or more of the rights that are
specifically granted under this License. You may not convey a covered
work if you are a party to an arrangement with a third party that is
in the business of distributing software, under which you make payment
to the third party based on the extent of your activity of conveying
the work, and under which the third party grants, to any of the
parties who would receive the covered work from you, a discriminatory
patent license (a) in connection with copies of the covered work
conveyed by you (or copies made from those copies), or (b) primarily
for and in connection with specific products or compilations that
contain the covered work, unless you entered into that arrangement,
or that patent license was granted, prior to 28 March 2007.
Nothing in this License shall be construed as excluding or limiting
any implied license or other defenses to infringement that may
otherwise be available to you under applicable patent law.
12. No Surrender of Others' Freedom.
If conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot convey a
covered work so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you may
not convey it at all. For example, if you agree to terms that obligate you
to collect a royalty for further conveying from those to whom you convey
the Program, the only way you could satisfy both those terms and this
License would be to refrain entirely from conveying the Program.
13. Remote Network Interaction; Use with the GNU General Public License.
Notwithstanding any other provision of this License, if you modify the
Program, your modified version must prominently offer all users
interacting with it remotely through a computer network (if your version
supports such interaction) an opportunity to receive the Corresponding
Source of your version by providing access to the Corresponding Source
from a network server at no charge, through some standard or customary
means of facilitating copying of software. This Corresponding Source
shall include the Corresponding Source for any work covered by version 3
of the GNU General Public License that is incorporated pursuant to the
following paragraph.
Notwithstanding any other provision of this License, you have
permission to link or combine any covered work with a work licensed
under version 3 of the GNU General Public License into a single
combined work, and to convey the resulting work. The terms of this
License will continue to apply to the part which is the covered work,
but the work with which it is combined will remain governed by version
3 of the GNU General Public License.
14. Revised Versions of this License.
The Free Software Foundation may publish revised and/or new versions of
the GNU Affero General Public License from time to time. Such new versions
will be similar in spirit to the present version, but may differ in detail to
address new problems or concerns.
Each version is given a distinguishing version number. If the
Program specifies that a certain numbered version of the GNU Affero General
Public License "or any later version" applies to it, you have the
option of following the terms and conditions either of that numbered
version or of any later version published by the Free Software
Foundation. If the Program does not specify a version number of the
GNU Affero General Public License, you may choose any version ever published
by the Free Software Foundation.
If the Program specifies that a proxy can decide which future
versions of the GNU Affero General Public License can be used, that proxy's
public statement of acceptance of a version permanently authorizes you
to choose that version for the Program.
Later license versions may give you additional or different
permissions. However, no additional obligations are imposed on any
author or copyright holder as a result of your choosing to follow a
later version.
15. Disclaimer of Warranty.
THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
16. Limitation of Liability.
IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
SUCH DAMAGES.
17. Interpretation of Sections 15 and 16.
If the disclaimer of warranty and limitation of liability provided
above cannot be given local legal effect according to their terms,
reviewing courts shall apply local law that most closely approximates
an absolute waiver of all civil liability in connection with the
Program, unless a warranty or assumption of liability accompanies a
copy of the Program in return for a fee.
END OF TERMS AND CONDITIONS
How to Apply These Terms to Your New Programs
If you develop a new program, and you want it to be of the greatest
possible use to the public, the best way to achieve this is to make it
free software which everyone can redistribute and change under these terms.
To do so, attach the following notices to the program. It is safest
to attach them to the start of each source file to most effectively
state the exclusion of warranty; and each file should have at least
the "copyright" line and a pointer to where the full notice is found.
<one line to give the program's name and a brief idea of what it does.>
Copyright (C) <year> <name of author>
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU Affero General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU Affero General Public License for more details.
You should have received a copy of the GNU Affero General Public License
along with this program. If not, see <https://www.gnu.org/licenses/>.
Also add information on how to contact you by electronic and paper mail.
If your software can interact with users remotely through a computer
network, you should also make sure that it provides a way for users to
get its source. For example, if your program is a web application, its
interface could display a "Source" link that leads users to an archive
of the code. There are many ways you could offer source, and different
solutions will be better for different programs; see section 13 for the
specific requirements.
You should also get your employer (if you work as a programmer) or school,
if any, to sign a "copyright disclaimer" for the program, if necessary.
For more information on this, and how to apply and follow the GNU AGPL, see
<https://www.gnu.org/licenses/>.

205
README.md Normal file
View File

@ -0,0 +1,205 @@
# Stable Diffusion web UI
A web interface for Stable Diffusion, implemented using Gradio library.
![](screenshot.png)
## Features
[Detailed feature showcase with images](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features):
- Original txt2img and img2img modes
- One click install and run script (but you still must install python and git)
- Outpainting
- Inpainting
- Color Sketch
- Prompt Matrix
- Stable Diffusion Upscale
- Attention, specify parts of text that the model should pay more attention to
- a man in a `((tuxedo))` - will pay more attention to tuxedo
- a man in a `(tuxedo:1.21)` - alternative syntax
- select text and press `Ctrl+Up` or `Ctrl+Down` (or `Command+Up` or `Command+Down` if you're on a MacOS) to automatically adjust attention to selected text (code contributed by anonymous user)
- Loopback, run img2img processing multiple times
- X/Y/Z plot, a way to draw a 3 dimensional plot of images with different parameters
- Textual Inversion
- have as many embeddings as you want and use any names you like for them
- use multiple embeddings with different numbers of vectors per token
- works with half precision floating point numbers
- train embeddings on 8GB (also reports of 6GB working)
- Extras tab with:
- GFPGAN, neural network that fixes faces
- CodeFormer, face restoration tool as an alternative to GFPGAN
- RealESRGAN, neural network upscaler
- ESRGAN, neural network upscaler with a lot of third party models
- SwinIR and Swin2SR ([see here](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/2092)), neural network upscalers
- LDSR, Latent diffusion super resolution upscaling
- Resizing aspect ratio options
- Sampling method selection
- Adjust sampler eta values (noise multiplier)
- More advanced noise setting options
- Interrupt processing at any time
- 4GB video card support (also reports of 2GB working)
- Correct seeds for batches
- Live prompt token length validation
- Generation parameters
- parameters you used to generate images are saved with that image
- in PNG chunks for PNG, in EXIF for JPEG
- can drag the image to PNG info tab to restore generation parameters and automatically copy them into UI
- can be disabled in settings
- drag and drop an image/text-parameters to promptbox
- Read Generation Parameters Button, loads parameters in promptbox to UI
- Settings page
- Running arbitrary python code from UI (must run with `--allow-code` to enable)
- Mouseover hints for most UI elements
- Possible to change defaults/mix/max/step values for UI elements via text config
- Tiling support, a checkbox to create images that can be tiled like textures
- Progress bar and live image generation preview
- Can use a separate neural network to produce previews with almost none VRAM or compute requirement
- Negative prompt, an extra text field that allows you to list what you don't want to see in generated image
- Styles, a way to save part of prompt and easily apply them via dropdown later
- Variations, a way to generate same image but with tiny differences
- Seed resizing, a way to generate same image but at slightly different resolution
- CLIP interrogator, a button that tries to guess prompt from an image
- Prompt Editing, a way to change prompt mid-generation, say to start making a watermelon and switch to anime girl midway
- Batch Processing, process a group of files using img2img
- Img2img Alternative, reverse Euler method of cross attention control
- Highres Fix, a convenience option to produce high resolution pictures in one click without usual distortions
- Reloading checkpoints on the fly
- Checkpoint Merger, a tab that allows you to merge up to 3 checkpoints into one
- [Custom scripts](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Custom-Scripts) with many extensions from community
- [Composable-Diffusion](https://energy-based-model.github.io/Compositional-Visual-Generation-with-Composable-Diffusion-Models/), a way to use multiple prompts at once
- separate prompts using uppercase `AND`
- also supports weights for prompts: `a cat :1.2 AND a dog AND a penguin :2.2`
- No token limit for prompts (original stable diffusion lets you use up to 75 tokens)
- DeepDanbooru integration, creates danbooru style tags for anime prompts
- [xformers](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Xformers), major speed increase for select cards: (add `--xformers` to commandline args)
- via extension: [History tab](https://github.com/yfszzx/stable-diffusion-webui-images-browser): view, direct and delete images conveniently within the UI
- Generate forever option
- Training tab
- hypernetworks and embeddings options
- Preprocessing images: cropping, mirroring, autotagging using BLIP or deepdanbooru (for anime)
- Clip skip
- Hypernetworks
- Loras (same as Hypernetworks but more pretty)
- A separate UI where you can choose, with preview, which embeddings, hypernetworks or Loras to add to your prompt
- Can select to load a different VAE from settings screen
- Estimated completion time in progress bar
- API
- Support for dedicated [inpainting model](https://github.com/runwayml/stable-diffusion#inpainting-with-stable-diffusion) by RunwayML
- via extension: [Aesthetic Gradients](https://github.com/AUTOMATIC1111/stable-diffusion-webui-aesthetic-gradients), a way to generate images with a specific aesthetic by using clip images embeds (implementation of [https://github.com/vicgalle/stable-diffusion-aesthetic-gradients](https://github.com/vicgalle/stable-diffusion-aesthetic-gradients))
- [Stable Diffusion 2.0](https://github.com/Stability-AI/stablediffusion) support - see [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#stable-diffusion-20) for instructions
- [Alt-Diffusion](https://arxiv.org/abs/2211.06679) support - see [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#alt-diffusion) for instructions
- Now without any bad letters!
- Load checkpoints in safetensors format
- Eased resolution restriction: generated image's dimensions must be a multiple of 8 rather than 64
- Now with a license!
- Reorder elements in the UI from settings screen
- [Segmind Stable Diffusion](https://huggingface.co/segmind/SSD-1B) support
## Installation and Running
Make sure the required [dependencies](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Dependencies) are met and follow the instructions available for:
- [NVidia](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-NVidia-GPUs) (recommended)
- [AMD](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-AMD-GPUs) GPUs.
- [Intel CPUs, Intel GPUs (both integrated and discrete)](https://github.com/openvinotoolkit/stable-diffusion-webui/wiki/Installation-on-Intel-Silicon) (external wiki page)
- [Ascend NPUs](https://github.com/wangshuai09/stable-diffusion-webui/wiki/Install-and-run-on-Ascend-NPUs) (external wiki page)
Alternatively, use online services (like Google Colab):
- [List of Online Services](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Online-Services)
### Installation on Windows 10/11 with NVidia-GPUs using release package
1. Download `sd.webui.zip` from [v1.0.0-pre](https://github.com/AUTOMATIC1111/stable-diffusion-webui/releases/tag/v1.0.0-pre) and extract its contents.
2. Run `update.bat`.
3. Run `run.bat`.
> For more details see [Install-and-Run-on-NVidia-GPUs](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-NVidia-GPUs)
### Automatic Installation on Windows
1. Install [Python 3.10.6](https://www.python.org/downloads/release/python-3106/) (Newer version of Python does not support torch), checking "Add Python to PATH".
2. Install [git](https://git-scm.com/download/win).
3. Download the stable-diffusion-webui repository, for example by running `git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git`.
4. Run `webui-user.bat` from Windows Explorer as normal, non-administrator, user.
### Automatic Installation on Linux
1. Install the dependencies:
```bash
# Debian-based:
sudo apt install wget git python3 python3-venv libgl1 libglib2.0-0
# Red Hat-based:
sudo dnf install wget git python3 gperftools-libs libglvnd-glx
# openSUSE-based:
sudo zypper install wget git python3 libtcmalloc4 libglvnd
# Arch-based:
sudo pacman -S wget git python3
```
If your system is very new, you need to install python3.11 or python3.10:
```bash
# Ubuntu 24.04
sudo add-apt-repository ppa:deadsnakes/ppa
sudo apt update
sudo apt install python3.11
# Manjaro/Arch
sudo pacman -S yay
yay -S python311 # do not confuse with python3.11 package
# Only for 3.11
# Then set up env variable in launch script
export python_cmd="python3.11"
# or in webui-user.sh
python_cmd="python3.11"
```
2. Navigate to the directory you would like the webui to be installed and execute the following command:
```bash
wget -q https://raw.githubusercontent.com/AUTOMATIC1111/stable-diffusion-webui/master/webui.sh
```
Or just clone the repo wherever you want:
```bash
git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui
```
3. Run `webui.sh`.
4. Check `webui-user.sh` for options.
### Installation on Apple Silicon
Find the instructions [here](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Installation-on-Apple-Silicon).
## Contributing
Here's how to add code to this repo: [Contributing](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Contributing)
## Documentation
The documentation was moved from this README over to the project's [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki).
For the purposes of getting Google and other search engines to crawl the wiki, here's a link to the (not for humans) [crawlable wiki](https://github-wiki-see.page/m/AUTOMATIC1111/stable-diffusion-webui/wiki).
## Credits
Licenses for borrowed code can be found in `Settings -> Licenses` screen, and also in `html/licenses.html` file.
- Stable Diffusion - https://github.com/Stability-AI/stablediffusion, https://github.com/CompVis/taming-transformers, https://github.com/mcmonkey4eva/sd3-ref
- k-diffusion - https://github.com/crowsonkb/k-diffusion.git
- Spandrel - https://github.com/chaiNNer-org/spandrel implementing
- GFPGAN - https://github.com/TencentARC/GFPGAN.git
- CodeFormer - https://github.com/sczhou/CodeFormer
- ESRGAN - https://github.com/xinntao/ESRGAN
- SwinIR - https://github.com/JingyunLiang/SwinIR
- Swin2SR - https://github.com/mv-lab/swin2sr
- LDSR - https://github.com/Hafiidz/latent-diffusion
- MiDaS - https://github.com/isl-org/MiDaS
- Ideas for optimizations - https://github.com/basujindal/stable-diffusion
- Cross Attention layer optimization - Doggettx - https://github.com/Doggettx/stable-diffusion, original idea for prompt editing.
- Cross Attention layer optimization - InvokeAI, lstein - https://github.com/invoke-ai/InvokeAI (originally http://github.com/lstein/stable-diffusion)
- Sub-quadratic Cross Attention layer optimization - Alex Birch (https://github.com/Birch-san/diffusers/pull/1), Amin Rezaei (https://github.com/AminRezaei0x443/memory-efficient-attention)
- Textual Inversion - Rinon Gal - https://github.com/rinongal/textual_inversion (we're not using his code, but we are using his ideas).
- Idea for SD upscale - https://github.com/jquesnelle/txt2imghd
- Noise generation for outpainting mk2 - https://github.com/parlance-zz/g-diffuser-bot
- CLIP interrogator idea and borrowing some code - https://github.com/pharmapsychotic/clip-interrogator
- Idea for Composable Diffusion - https://github.com/energy-based-model/Compositional-Visual-Generation-with-Composable-Diffusion-Models-PyTorch
- xformers - https://github.com/facebookresearch/xformers
- DeepDanbooru - interrogator for anime diffusers https://github.com/KichangKim/DeepDanbooru
- Sampling in float32 precision from a float16 UNet - marunine for the idea, Birch-san for the example Diffusers implementation (https://github.com/Birch-san/diffusers-play/tree/92feee6)
- Instruct pix2pix - Tim Brooks (star), Aleksander Holynski (star), Alexei A. Efros (no star) - https://github.com/timothybrooks/instruct-pix2pix
- Security advice - RyotaK
- UniPC sampler - Wenliang Zhao - https://github.com/wl-zhao/UniPC
- TAESD - Ollin Boer Bohan - https://github.com/madebyollin/taesd
- LyCORIS - KohakuBlueleaf
- Restart sampling - lambertae - https://github.com/Newbeeer/diffusion_restart_sampling
- Hypertile - tfernd - https://github.com/tfernd/HyperTile
- Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user.
- (You)

5
_typos.toml Normal file
View File

@ -0,0 +1,5 @@
[default.extend-words]
# Part of "RGBa" (Pillow's pre-multiplied alpha RGB mode)
Ba = "Ba"
# HSA is something AMD uses for their GPUs
HSA = "HSA"

72
configs/alt-diffusion-inference.yaml Normal file
View File

@ -0,0 +1,72 @@
model:
base_learning_rate: 1.0e-04
target: ldm.models.diffusion.ddpm.LatentDiffusion
params:
linear_start: 0.00085
linear_end: 0.0120
num_timesteps_cond: 1
log_every_t: 200
timesteps: 1000
first_stage_key: "jpg"
cond_stage_key: "txt"
image_size: 64
channels: 4
cond_stage_trainable: false # Note: different from the one we trained before
conditioning_key: crossattn
monitor: val/loss_simple_ema
scale_factor: 0.18215
use_ema: False
scheduler_config: # 10000 warmup steps
target: ldm.lr_scheduler.LambdaLinearScheduler
params:
warm_up_steps: [ 10000 ]
cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
f_start: [ 1.e-6 ]
f_max: [ 1. ]
f_min: [ 1. ]
unet_config:
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
params:
image_size: 32 # unused
in_channels: 4
out_channels: 4
model_channels: 320
attention_resolutions: [ 4, 2, 1 ]
num_res_blocks: 2
channel_mult: [ 1, 2, 4, 4 ]
num_heads: 8
use_spatial_transformer: True
transformer_depth: 1
context_dim: 768
use_checkpoint: False
legacy: False
first_stage_config:
target: ldm.models.autoencoder.AutoencoderKL
params:
embed_dim: 4
monitor: val/rec_loss
ddconfig:
double_z: true
z_channels: 4
resolution: 256
in_channels: 3
out_ch: 3
ch: 128
ch_mult:
- 1
- 2
- 4
- 4
num_res_blocks: 2
attn_resolutions: []
dropout: 0.0
lossconfig:
target: torch.nn.Identity
cond_stage_config:
target: modules.xlmr.BertSeriesModelWithTransformation
params:
name: "XLMR-Large"

73
configs/alt-diffusion-m18-inference.yaml Normal file
View File

@ -0,0 +1,73 @@
model:
base_learning_rate: 1.0e-04
target: ldm.models.diffusion.ddpm.LatentDiffusion
params:
linear_start: 0.00085
linear_end: 0.0120
num_timesteps_cond: 1
log_every_t: 200
timesteps: 1000
first_stage_key: "jpg"
cond_stage_key: "txt"
image_size: 64
channels: 4
cond_stage_trainable: false # Note: different from the one we trained before
conditioning_key: crossattn
monitor: val/loss_simple_ema
scale_factor: 0.18215
use_ema: False
scheduler_config: # 10000 warmup steps
target: ldm.lr_scheduler.LambdaLinearScheduler
params:
warm_up_steps: [ 10000 ]
cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
f_start: [ 1.e-6 ]
f_max: [ 1. ]
f_min: [ 1. ]
unet_config:
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
params:
image_size: 32 # unused
in_channels: 4
out_channels: 4
model_channels: 320
attention_resolutions: [ 4, 2, 1 ]
num_res_blocks: 2
channel_mult: [ 1, 2, 4, 4 ]
num_head_channels: 64
use_spatial_transformer: True
use_linear_in_transformer: True
transformer_depth: 1
context_dim: 1024
use_checkpoint: False
legacy: False
first_stage_config:
target: ldm.models.autoencoder.AutoencoderKL
params:
embed_dim: 4
monitor: val/rec_loss
ddconfig:
double_z: true
z_channels: 4
resolution: 256
in_channels: 3
out_ch: 3
ch: 128
ch_mult:
- 1
- 2
- 4
- 4
num_res_blocks: 2
attn_resolutions: []
dropout: 0.0
lossconfig:
target: torch.nn.Identity
cond_stage_config:
target: modules.xlmr_m18.BertSeriesModelWithTransformation
params:
name: "XLMR-Large"

98
configs/instruct-pix2pix.yaml Normal file
View File

@ -0,0 +1,98 @@
# File modified by authors of InstructPix2Pix from original (https://github.com/CompVis/stable-diffusion).
# See more details in LICENSE.
model:
base_learning_rate: 1.0e-04
target: modules.models.diffusion.ddpm_edit.LatentDiffusion
params:
linear_start: 0.00085
linear_end: 0.0120
num_timesteps_cond: 1
log_every_t: 200
timesteps: 1000
first_stage_key: edited
cond_stage_key: edit
# image_size: 64
# image_size: 32
image_size: 16
channels: 4
cond_stage_trainable: false # Note: different from the one we trained before
conditioning_key: hybrid
monitor: val/loss_simple_ema
scale_factor: 0.18215
use_ema: false
scheduler_config: # 10000 warmup steps
target: ldm.lr_scheduler.LambdaLinearScheduler
params:
warm_up_steps: [ 0 ]
cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
f_start: [ 1.e-6 ]
f_max: [ 1. ]
f_min: [ 1. ]
unet_config:
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
params:
image_size: 32 # unused
in_channels: 8
out_channels: 4
model_channels: 320
attention_resolutions: [ 4, 2, 1 ]
num_res_blocks: 2
channel_mult: [ 1, 2, 4, 4 ]
num_heads: 8
use_spatial_transformer: True
transformer_depth: 1
context_dim: 768
use_checkpoint: False
legacy: False
first_stage_config:
target: ldm.models.autoencoder.AutoencoderKL
params:
embed_dim: 4
monitor: val/rec_loss
ddconfig:
double_z: true
z_channels: 4
resolution: 256
in_channels: 3
out_ch: 3
ch: 128
ch_mult:
- 1
- 2
- 4
- 4
num_res_blocks: 2
attn_resolutions: []
dropout: 0.0
lossconfig:
target: torch.nn.Identity
cond_stage_config:
target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
data:
target: main.DataModuleFromConfig
params:
batch_size: 128
num_workers: 1
wrap: false
validation:
target: edit_dataset.EditDataset
params:
path: data/clip-filtered-dataset
cache_dir: data/
cache_name: data_10k
split: val
min_text_sim: 0.2
min_image_sim: 0.75
min_direction_sim: 0.2
max_samples_per_prompt: 1
min_resize_res: 512
max_resize_res: 512
crop_res: 512
output_as_edit: False
real_input: True

5
configs/sd3-inference.yaml Normal file
View File

@ -0,0 +1,5 @@
model:
target: modules.models.sd3.sd3_model.SD3Inferencer
params:
shift: 3
state_dict: null

98
configs/sd_xl_inpaint.yaml Normal file
View File

@ -0,0 +1,98 @@
model:
target: sgm.models.diffusion.DiffusionEngine
params:
scale_factor: 0.13025
disable_first_stage_autocast: True
denoiser_config:
target: sgm.modules.diffusionmodules.denoiser.DiscreteDenoiser
params:
num_idx: 1000
weighting_config:
target: sgm.modules.diffusionmodules.denoiser_weighting.EpsWeighting
scaling_config:
target: sgm.modules.diffusionmodules.denoiser_scaling.EpsScaling
discretization_config:
target: sgm.modules.diffusionmodules.discretizer.LegacyDDPMDiscretization
network_config:
target: sgm.modules.diffusionmodules.openaimodel.UNetModel
params:
adm_in_channels: 2816
num_classes: sequential
use_checkpoint: False
in_channels: 9
out_channels: 4
model_channels: 320
attention_resolutions: [4, 2]
num_res_blocks: 2
channel_mult: [1, 2, 4]
num_head_channels: 64
use_spatial_transformer: True
use_linear_in_transformer: True
transformer_depth: [1, 2, 10] # note: the first is unused (due to attn_res starting at 2) 32, 16, 8 --> 64, 32, 16
context_dim: 2048
spatial_transformer_attn_type: softmax-xformers
legacy: False
conditioner_config:
target: sgm.modules.GeneralConditioner
params:
emb_models:
# crossattn cond
- is_trainable: False
input_key: txt
target: sgm.modules.encoders.modules.FrozenCLIPEmbedder
params:
layer: hidden
layer_idx: 11
# crossattn and vector cond
- is_trainable: False
input_key: txt
target: sgm.modules.encoders.modules.FrozenOpenCLIPEmbedder2
params:
arch: ViT-bigG-14
version: laion2b_s39b_b160k
freeze: True
layer: penultimate
always_return_pooled: True
legacy: False
# vector cond
- is_trainable: False
input_key: original_size_as_tuple
target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
params:
outdim: 256 # multiplied by two
# vector cond
- is_trainable: False
input_key: crop_coords_top_left
target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
params:
outdim: 256 # multiplied by two
# vector cond
- is_trainable: False
input_key: target_size_as_tuple
target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
params:
outdim: 256 # multiplied by two
first_stage_config:
target: sgm.models.autoencoder.AutoencoderKLInferenceWrapper
params:
embed_dim: 4
monitor: val/rec_loss
ddconfig:
attn_type: vanilla-xformers
double_z: true
z_channels: 4
resolution: 256
in_channels: 3
out_ch: 3
ch: 128
ch_mult: [1, 2, 4, 4]
num_res_blocks: 2
attn_resolutions: []
dropout: 0.0
lossconfig:
target: torch.nn.Identity

70
configs/v1-inference.yaml Normal file
View File

@ -0,0 +1,70 @@
model:
base_learning_rate: 1.0e-04
target: ldm.models.diffusion.ddpm.LatentDiffusion
params:
linear_start: 0.00085
linear_end: 0.0120
num_timesteps_cond: 1
log_every_t: 200
timesteps: 1000
first_stage_key: "jpg"
cond_stage_key: "txt"
image_size: 64
channels: 4
cond_stage_trainable: false # Note: different from the one we trained before
conditioning_key: crossattn
monitor: val/loss_simple_ema
scale_factor: 0.18215
use_ema: False
scheduler_config: # 10000 warmup steps
target: ldm.lr_scheduler.LambdaLinearScheduler
params:
warm_up_steps: [ 10000 ]
cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
f_start: [ 1.e-6 ]
f_max: [ 1. ]
f_min: [ 1. ]
unet_config:
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
params:
image_size: 32 # unused
in_channels: 4
out_channels: 4
model_channels: 320
attention_resolutions: [ 4, 2, 1 ]
num_res_blocks: 2
channel_mult: [ 1, 2, 4, 4 ]
num_heads: 8
use_spatial_transformer: True
transformer_depth: 1
context_dim: 768
use_checkpoint: False
legacy: False
first_stage_config:
target: ldm.models.autoencoder.AutoencoderKL
params:
embed_dim: 4
monitor: val/rec_loss
ddconfig:
double_z: true
z_channels: 4
resolution: 256
in_channels: 3
out_ch: 3
ch: 128
ch_mult:
- 1
- 2
- 4
- 4
num_res_blocks: 2
attn_resolutions: []
dropout: 0.0
lossconfig:
target: torch.nn.Identity
cond_stage_config:
target: ldm.modules.encoders.modules.FrozenCLIPEmbedder

70
configs/v1-inpainting-inference.yaml Normal file
View File

@ -0,0 +1,70 @@
model:
base_learning_rate: 7.5e-05
target: ldm.models.diffusion.ddpm.LatentInpaintDiffusion
params:
linear_start: 0.00085
linear_end: 0.0120
num_timesteps_cond: 1
log_every_t: 200
timesteps: 1000
first_stage_key: "jpg"
cond_stage_key: "txt"
image_size: 64
channels: 4
cond_stage_trainable: false # Note: different from the one we trained before
conditioning_key: hybrid # important
monitor: val/loss_simple_ema
scale_factor: 0.18215
finetune_keys: null
scheduler_config: # 10000 warmup steps
target: ldm.lr_scheduler.LambdaLinearScheduler
params:
warm_up_steps: [ 2500 ] # NOTE for resuming. use 10000 if starting from scratch
cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
f_start: [ 1.e-6 ]
f_max: [ 1. ]
f_min: [ 1. ]
unet_config:
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
params:
image_size: 32 # unused
in_channels: 9 # 4 data + 4 downscaled image + 1 mask
out_channels: 4
model_channels: 320
attention_resolutions: [ 4, 2, 1 ]
num_res_blocks: 2
channel_mult: [ 1, 2, 4, 4 ]
num_heads: 8
use_spatial_transformer: True
transformer_depth: 1
context_dim: 768
use_checkpoint: False
legacy: False
first_stage_config:
target: ldm.models.autoencoder.AutoencoderKL
params:
embed_dim: 4
monitor: val/rec_loss
ddconfig:
double_z: true
z_channels: 4
resolution: 256
in_channels: 3
out_ch: 3
ch: 128
ch_mult:
- 1
- 2
- 4
- 4
num_res_blocks: 2
attn_resolutions: []
dropout: 0.0
lossconfig:
target: torch.nn.Identity
cond_stage_config:
target: ldm.modules.encoders.modules.FrozenCLIPEmbedder

11
environment-wsl2.yaml Normal file
View File

@ -0,0 +1,11 @@
name: automatic
channels:
- pytorch
- defaults
dependencies:
- python=3.10
- pip=23.0
- cudatoolkit=11.8
- pytorch=2.0
- torchvision=0.15
- numpy=1.23

250
extensions-builtin/LDSR/ldsr_model_arch.py Normal file
View File

@ -0,0 +1,250 @@
import os
import gc
import time
import numpy as np
import torch
import torchvision
from PIL import Image
from einops import rearrange, repeat
from omegaconf import OmegaConf
import safetensors.torch
from ldm.models.diffusion.ddim import DDIMSampler
from ldm.util import instantiate_from_config, ismap
from modules import shared, sd_hijack, devices
cached_ldsr_model: torch.nn.Module = None
# Create LDSR Class
class LDSR:
def load_model_from_config(self, half_attention):
global cached_ldsr_model
if shared.opts.ldsr_cached and cached_ldsr_model is not None:
print("Loading model from cache")
model: torch.nn.Module = cached_ldsr_model
else:
print(f"Loading model from {self.modelPath}")
_, extension = os.path.splitext(self.modelPath)
if extension.lower() == ".safetensors":
pl_sd = safetensors.torch.load_file(self.modelPath, device="cpu")
else:
pl_sd = torch.load(self.modelPath, map_location="cpu")
sd = pl_sd["state_dict"] if "state_dict" in pl_sd else pl_sd
config = OmegaConf.load(self.yamlPath)
config.model.target = "ldm.models.diffusion.ddpm.LatentDiffusionV1"
model: torch.nn.Module = instantiate_from_config(config.model)
model.load_state_dict(sd, strict=False)
model = model.to(shared.device)
if half_attention:
model = model.half()
if shared.cmd_opts.opt_channelslast:
model = model.to(memory_format=torch.channels_last)
sd_hijack.model_hijack.hijack(model) # apply optimization
model.eval()
if shared.opts.ldsr_cached:
cached_ldsr_model = model
return {"model": model}
def __init__(self, model_path, yaml_path):
self.modelPath = model_path
self.yamlPath = yaml_path
@staticmethod
def run(model, selected_path, custom_steps, eta):
example = get_cond(selected_path)
n_runs = 1
guider = None
ckwargs = None
ddim_use_x0_pred = False
temperature = 1.
eta = eta
custom_shape = None
height, width = example["image"].shape[1:3]
split_input = height >= 128 and width >= 128
if split_input:
ks = 128
stride = 64
vqf = 4 #
model.split_input_params = {"ks": (ks, ks), "stride": (stride, stride),
"vqf": vqf,
"patch_distributed_vq": True,
"tie_braker": False,
"clip_max_weight": 0.5,
"clip_min_weight": 0.01,
"clip_max_tie_weight": 0.5,
"clip_min_tie_weight": 0.01}
else:
if hasattr(model, "split_input_params"):
delattr(model, "split_input_params")
x_t = None
logs = None
for _ in range(n_runs):
if custom_shape is not None:
x_t = torch.randn(1, custom_shape[1], custom_shape[2], custom_shape[3]).to(model.device)
x_t = repeat(x_t, '1 c h w -> b c h w', b=custom_shape[0])
logs = make_convolutional_sample(example, model,
custom_steps=custom_steps,
eta=eta, quantize_x0=False,
custom_shape=custom_shape,
temperature=temperature, noise_dropout=0.,
corrector=guider, corrector_kwargs=ckwargs, x_T=x_t,
ddim_use_x0_pred=ddim_use_x0_pred
)
return logs
def super_resolution(self, image, steps=100, target_scale=2, half_attention=False):
model = self.load_model_from_config(half_attention)
# Run settings
diffusion_steps = int(steps)
eta = 1.0
gc.collect()
devices.torch_gc()
im_og = image
width_og, height_og = im_og.size
# If we can adjust the max upscale size, then the 4 below should be our variable
down_sample_rate = target_scale / 4
wd = width_og * down_sample_rate
hd = height_og * down_sample_rate
width_downsampled_pre = int(np.ceil(wd))
height_downsampled_pre = int(np.ceil(hd))
if down_sample_rate != 1:
print(
f'Downsampling from [{width_og}, {height_og}] to [{width_downsampled_pre}, {height_downsampled_pre}]')
im_og = im_og.resize((width_downsampled_pre, height_downsampled_pre), Image.LANCZOS)
else:
print(f"Down sample rate is 1 from {target_scale} / 4 (Not downsampling)")
# pad width and height to multiples of 64, pads with the edge values of image to avoid artifacts
pad_w, pad_h = np.max(((2, 2), np.ceil(np.array(im_og.size) / 64).astype(int)), axis=0) * 64 - im_og.size
im_padded = Image.fromarray(np.pad(np.array(im_og), ((0, pad_h), (0, pad_w), (0, 0)), mode='edge'))
logs = self.run(model["model"], im_padded, diffusion_steps, eta)
sample = logs["sample"]
sample = sample.detach().cpu()
sample = torch.clamp(sample, -1., 1.)
sample = (sample + 1.) / 2. * 255
sample = sample.numpy().astype(np.uint8)
sample = np.transpose(sample, (0, 2, 3, 1))
a = Image.fromarray(sample[0])
# remove padding
a = a.crop((0, 0) + tuple(np.array(im_og.size) * 4))
del model
gc.collect()
devices.torch_gc()
return a
def get_cond(selected_path):
example = {}
up_f = 4
c = selected_path.convert('RGB')
c = torch.unsqueeze(torchvision.transforms.ToTensor()(c), 0)
c_up = torchvision.transforms.functional.resize(c, size=[up_f * c.shape[2], up_f * c.shape[3]],
antialias=True)
c_up = rearrange(c_up, '1 c h w -> 1 h w c')
c = rearrange(c, '1 c h w -> 1 h w c')
c = 2. * c - 1.
c = c.to(shared.device)
example["LR_image"] = c
example["image"] = c_up
return example
@torch.no_grad()
def convsample_ddim(model, cond, steps, shape, eta=1.0, callback=None, normals_sequence=None,
mask=None, x0=None, quantize_x0=False, temperature=1., score_corrector=None,
corrector_kwargs=None, x_t=None
):
ddim = DDIMSampler(model)
bs = shape[0]
shape = shape[1:]
print(f"Sampling with eta = {eta}; steps: {steps}")
samples, intermediates = ddim.sample(steps, batch_size=bs, shape=shape, conditioning=cond, callback=callback,
normals_sequence=normals_sequence, quantize_x0=quantize_x0, eta=eta,
mask=mask, x0=x0, temperature=temperature, verbose=False,
score_corrector=score_corrector,
corrector_kwargs=corrector_kwargs, x_t=x_t)
return samples, intermediates
@torch.no_grad()
def make_convolutional_sample(batch, model, custom_steps=None, eta=1.0, quantize_x0=False, custom_shape=None, temperature=1., noise_dropout=0., corrector=None,
corrector_kwargs=None, x_T=None, ddim_use_x0_pred=False):
log = {}
z, c, x, xrec, xc = model.get_input(batch, model.first_stage_key,
return_first_stage_outputs=True,
force_c_encode=not (hasattr(model, 'split_input_params')
and model.cond_stage_key == 'coordinates_bbox'),
return_original_cond=True)
if custom_shape is not None:
z = torch.randn(custom_shape)
print(f"Generating {custom_shape[0]} samples of shape {custom_shape[1:]}")
z0 = None
log["input"] = x
log["reconstruction"] = xrec
if ismap(xc):
log["original_conditioning"] = model.to_rgb(xc)
if hasattr(model, 'cond_stage_key'):
log[model.cond_stage_key] = model.to_rgb(xc)
else:
log["original_conditioning"] = xc if xc is not None else torch.zeros_like(x)
if model.cond_stage_model:
log[model.cond_stage_key] = xc if xc is not None else torch.zeros_like(x)
if model.cond_stage_key == 'class_label':
log[model.cond_stage_key] = xc[model.cond_stage_key]
with model.ema_scope("Plotting"):
t0 = time.time()
sample, intermediates = convsample_ddim(model, c, steps=custom_steps, shape=z.shape,
eta=eta,
quantize_x0=quantize_x0, mask=None, x0=z0,
temperature=temperature, score_corrector=corrector, corrector_kwargs=corrector_kwargs,
x_t=x_T)
t1 = time.time()
if ddim_use_x0_pred:
sample = intermediates['pred_x0'][-1]
x_sample = model.decode_first_stage(sample)
try:
x_sample_noquant = model.decode_first_stage(sample, force_not_quantize=True)
log["sample_noquant"] = x_sample_noquant
log["sample_diff"] = torch.abs(x_sample_noquant - x_sample)
except Exception:
pass
log["sample"] = x_sample
log["time"] = t1 - t0
return log

6
extensions-builtin/LDSR/preload.py Normal file
View File

@ -0,0 +1,6 @@
import os
from modules import paths
def preload(parser):
parser.add_argument("--ldsr-models-path", type=str, help="Path to directory with LDSR model file(s).", default=os.path.join(paths.models_path, 'LDSR'))

68
extensions-builtin/LDSR/scripts/ldsr_model.py Normal file
View File

@ -0,0 +1,68 @@
import os
from modules.modelloader import load_file_from_url
from modules.upscaler import Upscaler, UpscalerData
from ldsr_model_arch import LDSR
from modules import shared, script_callbacks, errors
import sd_hijack_autoencoder # noqa: F401
import sd_hijack_ddpm_v1 # noqa: F401
class UpscalerLDSR(Upscaler):
def __init__(self, user_path):
self.name = "LDSR"
self.user_path = user_path
self.model_url = "https://heibox.uni-heidelberg.de/f/578df07c8fc04ffbadf3/?dl=1"
self.yaml_url = "https://heibox.uni-heidelberg.de/f/31a76b13ea27482981b4/?dl=1"
super().__init__()
scaler_data = UpscalerData("LDSR", None, self)
self.scalers = [scaler_data]
def load_model(self, path: str):
# Remove incorrect project.yaml file if too big
yaml_path = os.path.join(self.model_path, "project.yaml")
old_model_path = os.path.join(self.model_path, "model.pth")
new_model_path = os.path.join(self.model_path, "model.ckpt")
local_model_paths = self.find_models(ext_filter=[".ckpt", ".safetensors"])
local_ckpt_path = next(iter([local_model for local_model in local_model_paths if local_model.endswith("model.ckpt")]), None)
local_safetensors_path = next(iter([local_model for local_model in local_model_paths if local_model.endswith("model.safetensors")]), None)
local_yaml_path = next(iter([local_model for local_model in local_model_paths if local_model.endswith("project.yaml")]), None)
if os.path.exists(yaml_path):
statinfo = os.stat(yaml_path)
if statinfo.st_size >= 10485760:
print("Removing invalid LDSR YAML file.")
os.remove(yaml_path)
if os.path.exists(old_model_path):
print("Renaming model from model.pth to model.ckpt")
os.rename(old_model_path, new_model_path)
if local_safetensors_path is not None and os.path.exists(local_safetensors_path):
model = local_safetensors_path
else:
model = local_ckpt_path or load_file_from_url(self.model_url, model_dir=self.model_download_path, file_name="model.ckpt")
yaml = local_yaml_path or load_file_from_url(self.yaml_url, model_dir=self.model_download_path, file_name="project.yaml")
return LDSR(model, yaml)
def do_upscale(self, img, path):
try:
ldsr = self.load_model(path)
except Exception:
errors.report(f"Failed loading LDSR model {path}", exc_info=True)
return img
ddim_steps = shared.opts.ldsr_steps
return ldsr.super_resolution(img, ddim_steps, self.scale)
def on_ui_settings():
import gradio as gr
shared.opts.add_option("ldsr_steps", shared.OptionInfo(100, "LDSR processing steps. Lower = faster", gr.Slider, {"minimum": 1, "maximum": 200, "step": 1}, section=('upscaling', "Upscaling")))
shared.opts.add_option("ldsr_cached", shared.OptionInfo(False, "Cache LDSR model in memory", gr.Checkbox, {"interactive": True}, section=('upscaling', "Upscaling")))
script_callbacks.on_ui_settings(on_ui_settings)

293
extensions-builtin/LDSR/sd_hijack_autoencoder.py Normal file
View File

@ -0,0 +1,293 @@
# The content of this file comes from the ldm/models/autoencoder.py file of the compvis/stable-diffusion repo
# The VQModel & VQModelInterface were subsequently removed from ldm/models/autoencoder.py when we moved to the stability-ai/stablediffusion repo
# As the LDSR upscaler relies on VQModel & VQModelInterface, the hijack aims to put them back into the ldm.models.autoencoder
import numpy as np
import torch
import pytorch_lightning as pl
import torch.nn.functional as F
from contextlib import contextmanager
from torch.optim.lr_scheduler import LambdaLR
from ldm.modules.ema import LitEma
from vqvae_quantize import VectorQuantizer2 as VectorQuantizer
from ldm.modules.diffusionmodules.model import Encoder, Decoder
from ldm.util import instantiate_from_config
import ldm.models.autoencoder
from packaging import version
class VQModel(pl.LightningModule):
def __init__(self,
ddconfig,
lossconfig,
n_embed,
embed_dim,
ckpt_path=None,
ignore_keys=None,
image_key="image",
colorize_nlabels=None,
monitor=None,
batch_resize_range=None,
scheduler_config=None,
lr_g_factor=1.0,
remap=None,
sane_index_shape=False, # tell vector quantizer to return indices as bhw
use_ema=False
):
super().__init__()
self.embed_dim = embed_dim
self.n_embed = n_embed
self.image_key = image_key
self.encoder = Encoder(**ddconfig)
self.decoder = Decoder(**ddconfig)
self.loss = instantiate_from_config(lossconfig)
self.quantize = VectorQuantizer(n_embed, embed_dim, beta=0.25,
remap=remap,
sane_index_shape=sane_index_shape)
self.quant_conv = torch.nn.Conv2d(ddconfig["z_channels"], embed_dim, 1)
self.post_quant_conv = torch.nn.Conv2d(embed_dim, ddconfig["z_channels"], 1)
if colorize_nlabels is not None:
assert type(colorize_nlabels)==int
self.register_buffer("colorize", torch.randn(3, colorize_nlabels, 1, 1))
if monitor is not None:
self.monitor = monitor
self.batch_resize_range = batch_resize_range
if self.batch_resize_range is not None:
print(f"{self.__class__.__name__}: Using per-batch resizing in range {batch_resize_range}.")
self.use_ema = use_ema
if self.use_ema:
self.model_ema = LitEma(self)
print(f"Keeping EMAs of {len(list(self.model_ema.buffers()))}.")
if ckpt_path is not None:
self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys or [])
self.scheduler_config = scheduler_config
self.lr_g_factor = lr_g_factor
@contextmanager
def ema_scope(self, context=None):
if self.use_ema:
self.model_ema.store(self.parameters())
self.model_ema.copy_to(self)
if context is not None:
print(f"{context}: Switched to EMA weights")
try:
yield None
finally:
if self.use_ema:
self.model_ema.restore(self.parameters())
if context is not None:
print(f"{context}: Restored training weights")
def init_from_ckpt(self, path, ignore_keys=None):
sd = torch.load(path, map_location="cpu")["state_dict"]
keys = list(sd.keys())
for k in keys:
for ik in ignore_keys or []:
if k.startswith(ik):
print("Deleting key {} from state_dict.".format(k))
del sd[k]
missing, unexpected = self.load_state_dict(sd, strict=False)
print(f"Restored from {path} with {len(missing)} missing and {len(unexpected)} unexpected keys")
if missing:
print(f"Missing Keys: {missing}")
if unexpected:
print(f"Unexpected Keys: {unexpected}")
def on_train_batch_end(self, *args, **kwargs):
if self.use_ema:
self.model_ema(self)
def encode(self, x):
h = self.encoder(x)
h = self.quant_conv(h)
quant, emb_loss, info = self.quantize(h)
return quant, emb_loss, info
def encode_to_prequant(self, x):
h = self.encoder(x)
h = self.quant_conv(h)
return h
def decode(self, quant):
quant = self.post_quant_conv(quant)
dec = self.decoder(quant)
return dec
def decode_code(self, code_b):
quant_b = self.quantize.embed_code(code_b)
dec = self.decode(quant_b)
return dec
def forward(self, input, return_pred_indices=False):
quant, diff, (_,_,ind) = self.encode(input)
dec = self.decode(quant)
if return_pred_indices:
return dec, diff, ind
return dec, diff
def get_input(self, batch, k):
x = batch[k]
if len(x.shape) == 3:
x = x[..., None]
x = x.permute(0, 3, 1, 2).to(memory_format=torch.contiguous_format).float()
if self.batch_resize_range is not None:
lower_size = self.batch_resize_range[0]
upper_size = self.batch_resize_range[1]
if self.global_step <= 4:
# do the first few batches with max size to avoid later oom
new_resize = upper_size
else:
new_resize = np.random.choice(np.arange(lower_size, upper_size+16, 16))
if new_resize != x.shape[2]:
x = F.interpolate(x, size=new_resize, mode="bicubic")
x = x.detach()
return x
def training_step(self, batch, batch_idx, optimizer_idx):
# https://github.com/pytorch/pytorch/issues/37142
# try not to fool the heuristics
x = self.get_input(batch, self.image_key)
xrec, qloss, ind = self(x, return_pred_indices=True)
if optimizer_idx == 0:
# autoencode
aeloss, log_dict_ae = self.loss(qloss, x, xrec, optimizer_idx, self.global_step,
last_layer=self.get_last_layer(), split="train",
predicted_indices=ind)
self.log_dict(log_dict_ae, prog_bar=False, logger=True, on_step=True, on_epoch=True)
return aeloss
if optimizer_idx == 1:
# discriminator
discloss, log_dict_disc = self.loss(qloss, x, xrec, optimizer_idx, self.global_step,
last_layer=self.get_last_layer(), split="train")
self.log_dict(log_dict_disc, prog_bar=False, logger=True, on_step=True, on_epoch=True)
return discloss
def validation_step(self, batch, batch_idx):
log_dict = self._validation_step(batch, batch_idx)
with self.ema_scope():
self._validation_step(batch, batch_idx, suffix="_ema")
return log_dict
def _validation_step(self, batch, batch_idx, suffix=""):
x = self.get_input(batch, self.image_key)
xrec, qloss, ind = self(x, return_pred_indices=True)
aeloss, log_dict_ae = self.loss(qloss, x, xrec, 0,
self.global_step,
last_layer=self.get_last_layer(),
split="val"+suffix,
predicted_indices=ind
)
discloss, log_dict_disc = self.loss(qloss, x, xrec, 1,
self.global_step,
last_layer=self.get_last_layer(),
split="val"+suffix,
predicted_indices=ind
)
rec_loss = log_dict_ae[f"val{suffix}/rec_loss"]
self.log(f"val{suffix}/rec_loss", rec_loss,
prog_bar=True, logger=True, on_step=False, on_epoch=True, sync_dist=True)
self.log(f"val{suffix}/aeloss", aeloss,
prog_bar=True, logger=True, on_step=False, on_epoch=True, sync_dist=True)
if version.parse(pl.__version__) >= version.parse('1.4.0'):
del log_dict_ae[f"val{suffix}/rec_loss"]
self.log_dict(log_dict_ae)
self.log_dict(log_dict_disc)
return self.log_dict
def configure_optimizers(self):
lr_d = self.learning_rate
lr_g = self.lr_g_factor*self.learning_rate
print("lr_d", lr_d)
print("lr_g", lr_g)
opt_ae = torch.optim.Adam(list(self.encoder.parameters())+
list(self.decoder.parameters())+
list(self.quantize.parameters())+
list(self.quant_conv.parameters())+
list(self.post_quant_conv.parameters()),
lr=lr_g, betas=(0.5, 0.9))
opt_disc = torch.optim.Adam(self.loss.discriminator.parameters(),
lr=lr_d, betas=(0.5, 0.9))
if self.scheduler_config is not None:
scheduler = instantiate_from_config(self.scheduler_config)
print("Setting up LambdaLR scheduler...")
scheduler = [
{
'scheduler': LambdaLR(opt_ae, lr_lambda=scheduler.schedule),
'interval': 'step',
'frequency': 1
},
{
'scheduler': LambdaLR(opt_disc, lr_lambda=scheduler.schedule),
'interval': 'step',
'frequency': 1
},
]
return [opt_ae, opt_disc], scheduler
return [opt_ae, opt_disc], []
def get_last_layer(self):
return self.decoder.conv_out.weight
def log_images(self, batch, only_inputs=False, plot_ema=False, **kwargs):
log = {}
x = self.get_input(batch, self.image_key)
x = x.to(self.device)
if only_inputs:
log["inputs"] = x
return log
xrec, _ = self(x)
if x.shape[1] > 3:
# colorize with random projection
assert xrec.shape[1] > 3
x = self.to_rgb(x)
xrec = self.to_rgb(xrec)
log["inputs"] = x
log["reconstructions"] = xrec
if plot_ema:
with self.ema_scope():
xrec_ema, _ = self(x)
if x.shape[1] > 3:
xrec_ema = self.to_rgb(xrec_ema)
log["reconstructions_ema"] = xrec_ema
return log
def to_rgb(self, x):
assert self.image_key == "segmentation"
if not hasattr(self, "colorize"):
self.register_buffer("colorize", torch.randn(3, x.shape[1], 1, 1).to(x))
x = F.conv2d(x, weight=self.colorize)
x = 2.*(x-x.min())/(x.max()-x.min()) - 1.
return x
class VQModelInterface(VQModel):
def __init__(self, embed_dim, *args, **kwargs):
super().__init__(*args, embed_dim=embed_dim, **kwargs)
self.embed_dim = embed_dim
def encode(self, x):
h = self.encoder(x)
h = self.quant_conv(h)
return h
def decode(self, h, force_not_quantize=False):
# also go through quantization layer
if not force_not_quantize:
quant, emb_loss, info = self.quantize(h)
else:
quant = h
quant = self.post_quant_conv(quant)
dec = self.decoder(quant)
return dec
ldm.models.autoencoder.VQModel = VQModel
ldm.models.autoencoder.VQModelInterface = VQModelInterface

1443
extensions-builtin/LDSR/sd_hijack_ddpm_v1.py Normal file
View File

File diff suppressed because it is too large Load Diff

147
extensions-builtin/LDSR/vqvae_quantize.py Normal file
View File

@ -0,0 +1,147 @@
# Vendored from https://raw.githubusercontent.com/CompVis/taming-transformers/24268930bf1dce879235a7fddd0b2355b84d7ea6/taming/modules/vqvae/quantize.py,
# where the license is as follows:
#
# Copyright (c) 2020 Patrick Esser and Robin Rombach and Björn Ommer
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in all
# copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
# IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
# DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
# OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE
# OR OTHER DEALINGS IN THE SOFTWARE./
import torch
import torch.nn as nn
import numpy as np
from einops import rearrange
class VectorQuantizer2(nn.Module):
"""
Improved version over VectorQuantizer, can be used as a drop-in replacement. Mostly
avoids costly matrix multiplications and allows for post-hoc remapping of indices.
"""
# NOTE: due to a bug the beta term was applied to the wrong term. for
# backwards compatibility we use the buggy version by default, but you can
# specify legacy=False to fix it.
def __init__(self, n_e, e_dim, beta, remap=None, unknown_index="random",
sane_index_shape=False, legacy=True):
super().__init__()
self.n_e = n_e
self.e_dim = e_dim
self.beta = beta
self.legacy = legacy
self.embedding = nn.Embedding(self.n_e, self.e_dim)
self.embedding.weight.data.uniform_(-1.0 / self.n_e, 1.0 / self.n_e)
self.remap = remap
if self.remap is not None:
self.register_buffer("used", torch.tensor(np.load(self.remap)))
self.re_embed = self.used.shape[0]
self.unknown_index = unknown_index # "random" or "extra" or integer
if self.unknown_index == "extra":
self.unknown_index = self.re_embed
self.re_embed = self.re_embed + 1
print(f"Remapping {self.n_e} indices to {self.re_embed} indices. "
f"Using {self.unknown_index} for unknown indices.")
else:
self.re_embed = n_e
self.sane_index_shape = sane_index_shape
def remap_to_used(self, inds):
ishape = inds.shape
assert len(ishape) > 1
inds = inds.reshape(ishape[0], -1)
used = self.used.to(inds)
match = (inds[:, :, None] == used[None, None, ...]).long()
new = match.argmax(-1)
unknown = match.sum(2) < 1
if self.unknown_index == "random":
new[unknown] = torch.randint(0, self.re_embed, size=new[unknown].shape).to(device=new.device)
else:
new[unknown] = self.unknown_index
return new.reshape(ishape)
def unmap_to_all(self, inds):
ishape = inds.shape
assert len(ishape) > 1
inds = inds.reshape(ishape[0], -1)
used = self.used.to(inds)
if self.re_embed > self.used.shape[0]: # extra token
inds[inds >= self.used.shape[0]] = 0 # simply set to zero
back = torch.gather(used[None, :][inds.shape[0] * [0], :], 1, inds)
return back.reshape(ishape)
def forward(self, z, temp=None, rescale_logits=False, return_logits=False):
assert temp is None or temp == 1.0, "Only for interface compatible with Gumbel"
assert rescale_logits is False, "Only for interface compatible with Gumbel"
assert return_logits is False, "Only for interface compatible with Gumbel"
# reshape z -> (batch, height, width, channel) and flatten
z = rearrange(z, 'b c h w -> b h w c').contiguous()
z_flattened = z.view(-1, self.e_dim)
# distances from z to embeddings e_j (z - e)^2 = z^2 + e^2 - 2 e * z
d = torch.sum(z_flattened ** 2, dim=1, keepdim=True) + \
torch.sum(self.embedding.weight ** 2, dim=1) - 2 * \
torch.einsum('bd,dn->bn', z_flattened, rearrange(self.embedding.weight, 'n d -> d n'))
min_encoding_indices = torch.argmin(d, dim=1)
z_q = self.embedding(min_encoding_indices).view(z.shape)
perplexity = None
min_encodings = None
# compute loss for embedding
if not self.legacy:
loss = self.beta * torch.mean((z_q.detach() - z) ** 2) + \
torch.mean((z_q - z.detach()) ** 2)
else:
loss = torch.mean((z_q.detach() - z) ** 2) + self.beta * \
torch.mean((z_q - z.detach()) ** 2)
# preserve gradients
z_q = z + (z_q - z).detach()
# reshape back to match original input shape
z_q = rearrange(z_q, 'b h w c -> b c h w').contiguous()
if self.remap is not None:
min_encoding_indices = min_encoding_indices.reshape(z.shape[0], -1) # add batch axis
min_encoding_indices = self.remap_to_used(min_encoding_indices)
min_encoding_indices = min_encoding_indices.reshape(-1, 1) # flatten
if self.sane_index_shape:
min_encoding_indices = min_encoding_indices.reshape(
z_q.shape[0], z_q.shape[2], z_q.shape[3])
return z_q, loss, (perplexity, min_encodings, min_encoding_indices)
def get_codebook_entry(self, indices, shape):
# shape specifying (batch, height, width, channel)
if self.remap is not None:
indices = indices.reshape(shape[0], -1) # add batch axis
indices = self.unmap_to_all(indices)
indices = indices.reshape(-1) # flatten again
# get quantized latent vectors
z_q = self.embedding(indices)
if shape is not None:
z_q = z_q.view(shape)
# reshape back to match original input shape
z_q = z_q.permute(0, 3, 1, 2).contiguous()
return z_q

62
extensions-builtin/Lora/extra_networks_lora.py Normal file
View File

@ -0,0 +1,62 @@
from modules import extra_networks, shared
import networks
class ExtraNetworkLora(extra_networks.ExtraNetwork):
def __init__(self):
super().__init__('lora')
self.errors = {}
"""mapping of network names to the number of errors the network had during operation"""
remove_symbols = str.maketrans('', '', ":,")
def activate(self, p, params_list):
additional = shared.opts.sd_lora
self.errors.clear()
if additional != "None" and additional in networks.available_networks and not any(x for x in params_list if x.items[0] == additional):
p.all_prompts = [x + f"<lora:{additional}:{shared.opts.extra_networks_default_multiplier}>" for x in p.all_prompts]
params_list.append(extra_networks.ExtraNetworkParams(items=[additional, shared.opts.extra_networks_default_multiplier]))
names = []
te_multipliers = []
unet_multipliers = []
dyn_dims = []
for params in params_list:
assert params.items
names.append(params.positional[0])
te_multiplier = float(params.positional[1]) if len(params.positional) > 1 else 1.0
te_multiplier = float(params.named.get("te", te_multiplier))
unet_multiplier = float(params.positional[2]) if len(params.positional) > 2 else te_multiplier
unet_multiplier = float(params.named.get("unet", unet_multiplier))
dyn_dim = int(params.positional[3]) if len(params.positional) > 3 else None
dyn_dim = int(params.named["dyn"]) if "dyn" in params.named else dyn_dim
te_multipliers.append(te_multiplier)
unet_multipliers.append(unet_multiplier)
dyn_dims.append(dyn_dim)
networks.load_networks(names, te_multipliers, unet_multipliers, dyn_dims)
if shared.opts.lora_add_hashes_to_infotext:
if not getattr(p, "is_hr_pass", False) or not hasattr(p, "lora_hashes"):
p.lora_hashes = {}
for item in networks.loaded_networks:
if item.network_on_disk.shorthash and item.mentioned_name:
p.lora_hashes[item.mentioned_name.translate(self.remove_symbols)] = item.network_on_disk.shorthash
if p.lora_hashes:
p.extra_generation_params["Lora hashes"] = ', '.join(f'{k}: {v}' for k, v in p.lora_hashes.items())
def deactivate(self, p):
if self.errors:
p.comment("Networks with errors: " + ", ".join(f"{k} ({v})" for k, v in self.errors.items()))
self.errors.clear()

9
extensions-builtin/Lora/lora.py Normal file
View File

@ -0,0 +1,9 @@
import networks
list_available_loras = networks.list_available_networks
available_loras = networks.available_networks
available_lora_aliases = networks.available_network_aliases
available_lora_hash_lookup = networks.available_network_hash_lookup
forbidden_lora_aliases = networks.forbidden_network_aliases
loaded_loras = networks.loaded_networks

33
extensions-builtin/Lora/lora_logger.py Normal file
View File

@ -0,0 +1,33 @@
import sys
import copy
import logging
class ColoredFormatter(logging.Formatter):
COLORS = {
"DEBUG": "\033[0;36m", # CYAN
"INFO": "\033[0;32m", # GREEN
"WARNING": "\033[0;33m", # YELLOW
"ERROR": "\033[0;31m", # RED
"CRITICAL": "\033[0;37;41m", # WHITE ON RED
"RESET": "\033[0m", # RESET COLOR
}
def format(self, record):
colored_record = copy.copy(record)
levelname = colored_record.levelname
seq = self.COLORS.get(levelname, self.COLORS["RESET"])
colored_record.levelname = f"{seq}{levelname}{self.COLORS['RESET']}"
return super().format(colored_record)
logger = logging.getLogger("lora")
logger.propagate = False
if not logger.handlers:
handler = logging.StreamHandler(sys.stdout)
handler.setFormatter(
ColoredFormatter("[%(name)s]-%(levelname)s: %(message)s")
)
logger.addHandler(handler)

31
extensions-builtin/Lora/lora_patches.py Normal file
View File

@ -0,0 +1,31 @@
import torch
import networks
from modules import patches
class LoraPatches:
def __init__(self):
self.Linear_forward = patches.patch(__name__, torch.nn.Linear, 'forward', networks.network_Linear_forward)
self.Linear_load_state_dict = patches.patch(__name__, torch.nn.Linear, '_load_from_state_dict', networks.network_Linear_load_state_dict)
self.Conv2d_forward = patches.patch(__name__, torch.nn.Conv2d, 'forward', networks.network_Conv2d_forward)
self.Conv2d_load_state_dict = patches.patch(__name__, torch.nn.Conv2d, '_load_from_state_dict', networks.network_Conv2d_load_state_dict)
self.GroupNorm_forward = patches.patch(__name__, torch.nn.GroupNorm, 'forward', networks.network_GroupNorm_forward)
self.GroupNorm_load_state_dict = patches.patch(__name__, torch.nn.GroupNorm, '_load_from_state_dict', networks.network_GroupNorm_load_state_dict)
self.LayerNorm_forward = patches.patch(__name__, torch.nn.LayerNorm, 'forward', networks.network_LayerNorm_forward)
self.LayerNorm_load_state_dict = patches.patch(__name__, torch.nn.LayerNorm, '_load_from_state_dict', networks.network_LayerNorm_load_state_dict)
self.MultiheadAttention_forward = patches.patch(__name__, torch.nn.MultiheadAttention, 'forward', networks.network_MultiheadAttention_forward)
self.MultiheadAttention_load_state_dict = patches.patch(__name__, torch.nn.MultiheadAttention, '_load_from_state_dict', networks.network_MultiheadAttention_load_state_dict)
def undo(self):
self.Linear_forward = patches.undo(__name__, torch.nn.Linear, 'forward')
self.Linear_load_state_dict = patches.undo(__name__, torch.nn.Linear, '_load_from_state_dict')
self.Conv2d_forward = patches.undo(__name__, torch.nn.Conv2d, 'forward')
self.Conv2d_load_state_dict = patches.undo(__name__, torch.nn.Conv2d, '_load_from_state_dict')
self.GroupNorm_forward = patches.undo(__name__, torch.nn.GroupNorm, 'forward')
self.GroupNorm_load_state_dict = patches.undo(__name__, torch.nn.GroupNorm, '_load_from_state_dict')
self.LayerNorm_forward = patches.undo(__name__, torch.nn.LayerNorm, 'forward')
self.LayerNorm_load_state_dict = patches.undo(__name__, torch.nn.LayerNorm, '_load_from_state_dict')
self.MultiheadAttention_forward = patches.undo(__name__, torch.nn.MultiheadAttention, 'forward')
self.MultiheadAttention_load_state_dict = patches.undo(__name__, torch.nn.MultiheadAttention, '_load_from_state_dict')

68
extensions-builtin/Lora/lyco_helpers.py Normal file
View File

@ -0,0 +1,68 @@
import torch
def make_weight_cp(t, wa, wb):
temp = torch.einsum('i j k l, j r -> i r k l', t, wb)
return torch.einsum('i j k l, i r -> r j k l', temp, wa)
def rebuild_conventional(up, down, shape, dyn_dim=None):
up = up.reshape(up.size(0), -1)
down = down.reshape(down.size(0), -1)
if dyn_dim is not None:
up = up[:, :dyn_dim]
down = down[:dyn_dim, :]
return (up @ down).reshape(shape)
def rebuild_cp_decomposition(up, down, mid):
up = up.reshape(up.size(0), -1)
down = down.reshape(down.size(0), -1)
return torch.einsum('n m k l, i n, m j -> i j k l', mid, up, down)
# copied from https://github.com/KohakuBlueleaf/LyCORIS/blob/dev/lycoris/modules/lokr.py
def factorization(dimension: int, factor:int=-1) -> tuple[int, int]:
'''
return a tuple of two value of input dimension decomposed by the number closest to factor
second value is higher or equal than first value.
In LoRA with Kroneckor Product, first value is a value for weight scale.
secon value is a value for weight.
Because of non-commutative property, A⊗B ≠ B⊗A. Meaning of two matrices is slightly different.
examples)
factor
-1 2 4 8 16 ...
127 -> 1, 127 127 -> 1, 127 127 -> 1, 127 127 -> 1, 127 127 -> 1, 127
128 -> 8, 16 128 -> 2, 64 128 -> 4, 32 128 -> 8, 16 128 -> 8, 16
250 -> 10, 25 250 -> 2, 125 250 -> 2, 125 250 -> 5, 50 250 -> 10, 25
360 -> 8, 45 360 -> 2, 180 360 -> 4, 90 360 -> 8, 45 360 -> 12, 30
512 -> 16, 32 512 -> 2, 256 512 -> 4, 128 512 -> 8, 64 512 -> 16, 32
1024 -> 32, 32 1024 -> 2, 512 1024 -> 4, 256 1024 -> 8, 128 1024 -> 16, 64
'''
if factor > 0 and (dimension % factor) == 0:
m = factor
n = dimension // factor
if m > n:
n, m = m, n
return m, n
if factor < 0:
factor = dimension
m, n = 1, dimension
length = m + n
while m<n:
new_m = m + 1
while dimension%new_m != 0:
new_m += 1
new_n = dimension // new_m
if new_m + new_n > length or new_m>factor:
break
else:
m, n = new_m, new_n
if m > n:
n, m = m, n
return m, n

228
extensions-builtin/Lora/network.py Normal file
View File

@ -0,0 +1,228 @@
from __future__ import annotations
import os
from collections import namedtuple
import enum
import torch.nn as nn
import torch.nn.functional as F
from modules import sd_models, cache, errors, hashes, shared
import modules.models.sd3.mmdit
NetworkWeights = namedtuple('NetworkWeights', ['network_key', 'sd_key', 'w', 'sd_module'])
metadata_tags_order = {"ss_sd_model_name": 1, "ss_resolution": 2, "ss_clip_skip": 3, "ss_num_train_images": 10, "ss_tag_frequency": 20}
class SdVersion(enum.Enum):
Unknown = 1
SD1 = 2
SD2 = 3
SDXL = 4
class NetworkOnDisk:
def __init__(self, name, filename):
self.name = name
self.filename = filename
self.metadata = {}
self.is_safetensors = os.path.splitext(filename)[1].lower() == ".safetensors"
def read_metadata():
metadata = sd_models.read_metadata_from_safetensors(filename)
return metadata
if self.is_safetensors:
try:
self.metadata = cache.cached_data_for_file('safetensors-metadata', "lora/" + self.name, filename, read_metadata)
except Exception as e:
errors.display(e, f"reading lora {filename}")
if self.metadata:
m = {}
for k, v in sorted(self.metadata.items(), key=lambda x: metadata_tags_order.get(x[0], 999)):
m[k] = v
self.metadata = m
self.alias = self.metadata.get('ss_output_name', self.name)
self.hash = None
self.shorthash = None
self.set_hash(
self.metadata.get('sshs_model_hash') or
hashes.sha256_from_cache(self.filename, "lora/" + self.name, use_addnet_hash=self.is_safetensors) or
''
)
self.sd_version = self.detect_version()
def detect_version(self):
if str(self.metadata.get('ss_base_model_version', "")).startswith("sdxl_"):
return SdVersion.SDXL
elif str(self.metadata.get('ss_v2', "")) == "True":
return SdVersion.SD2
elif len(self.metadata):
return SdVersion.SD1
return SdVersion.Unknown
def set_hash(self, v):
self.hash = v
self.shorthash = self.hash[0:12]
if self.shorthash:
import networks
networks.available_network_hash_lookup[self.shorthash] = self
def read_hash(self):
if not self.hash:
self.set_hash(hashes.sha256(self.filename, "lora/" + self.name, use_addnet_hash=self.is_safetensors) or '')
def get_alias(self):
import networks
if shared.opts.lora_preferred_name == "Filename" or self.alias.lower() in networks.forbidden_network_aliases:
return self.name
else:
return self.alias
class Network: # LoraModule
def __init__(self, name, network_on_disk: NetworkOnDisk):
self.name = name
self.network_on_disk = network_on_disk
self.te_multiplier = 1.0
self.unet_multiplier = 1.0
self.dyn_dim = None
self.modules = {}
self.bundle_embeddings = {}
self.mtime = None
self.mentioned_name = None
"""the text that was used to add the network to prompt - can be either name or an alias"""
class ModuleType:
def create_module(self, net: Network, weights: NetworkWeights) -> Network | None:
return None
class NetworkModule:
def __init__(self, net: Network, weights: NetworkWeights):
self.network = net
self.network_key = weights.network_key
self.sd_key = weights.sd_key
self.sd_module = weights.sd_module
if isinstance(self.sd_module, modules.models.sd3.mmdit.QkvLinear):
s = self.sd_module.weight.shape
self.shape = (s[0] // 3, s[1])
elif hasattr(self.sd_module, 'weight'):
self.shape = self.sd_module.weight.shape
elif isinstance(self.sd_module, nn.MultiheadAttention):
# For now, only self-attn use Pytorch's MHA
# So assume all qkvo proj have same shape
self.shape = self.sd_module.out_proj.weight.shape
else:
self.shape = None
self.ops = None
self.extra_kwargs = {}
if isinstance(self.sd_module, nn.Conv2d):
self.ops = F.conv2d
self.extra_kwargs = {
'stride': self.sd_module.stride,
'padding': self.sd_module.padding
}
elif isinstance(self.sd_module, nn.Linear):
self.ops = F.linear
elif isinstance(self.sd_module, nn.LayerNorm):
self.ops = F.layer_norm
self.extra_kwargs = {
'normalized_shape': self.sd_module.normalized_shape,
'eps': self.sd_module.eps
}
elif isinstance(self.sd_module, nn.GroupNorm):
self.ops = F.group_norm
self.extra_kwargs = {
'num_groups': self.sd_module.num_groups,
'eps': self.sd_module.eps
}
self.dim = None
self.bias = weights.w.get("bias")
self.alpha = weights.w["alpha"].item() if "alpha" in weights.w else None
self.scale = weights.w["scale"].item() if "scale" in weights.w else None
self.dora_scale = weights.w.get("dora_scale", None)
self.dora_norm_dims = len(self.shape) - 1
def multiplier(self):
if 'transformer' in self.sd_key[:20]:
return self.network.te_multiplier
else:
return self.network.unet_multiplier
def calc_scale(self):
if self.scale is not None:
return self.scale
if self.dim is not None and self.alpha is not None:
return self.alpha / self.dim
return 1.0
def apply_weight_decompose(self, updown, orig_weight):
# Match the device/dtype
orig_weight = orig_weight.to(updown.dtype)
dora_scale = self.dora_scale.to(device=orig_weight.device, dtype=updown.dtype)
updown = updown.to(orig_weight.device)
merged_scale1 = updown + orig_weight
merged_scale1_norm = (
merged_scale1.transpose(0, 1)
.reshape(merged_scale1.shape[1], -1)
.norm(dim=1, keepdim=True)
.reshape(merged_scale1.shape[1], *[1] * self.dora_norm_dims)
.transpose(0, 1)
)
dora_merged = (
merged_scale1 * (dora_scale / merged_scale1_norm)
)
final_updown = dora_merged - orig_weight
return final_updown
def finalize_updown(self, updown, orig_weight, output_shape, ex_bias=None):
if self.bias is not None:
updown = updown.reshape(self.bias.shape)
updown += self.bias.to(orig_weight.device, dtype=updown.dtype)
updown = updown.reshape(output_shape)
if len(output_shape) == 4:
updown = updown.reshape(output_shape)
if orig_weight.size().numel() == updown.size().numel():
updown = updown.reshape(orig_weight.shape)
if ex_bias is not None:
ex_bias = ex_bias * self.multiplier()
updown = updown * self.calc_scale()
if self.dora_scale is not None:
updown = self.apply_weight_decompose(updown, orig_weight)
return updown * self.multiplier(), ex_bias
def calc_updown(self, target):
raise NotImplementedError()
def forward(self, x, y):
"""A general forward implementation for all modules"""
if self.ops is None:
raise NotImplementedError()
else:
updown, ex_bias = self.calc_updown(self.sd_module.weight)
return y + self.ops(x, weight=updown, bias=ex_bias, **self.extra_kwargs)

27
extensions-builtin/Lora/network_full.py Normal file
View File

@ -0,0 +1,27 @@
import network
class ModuleTypeFull(network.ModuleType):
def create_module(self, net: network.Network, weights: network.NetworkWeights):
if all(x in weights.w for x in ["diff"]):
return NetworkModuleFull(net, weights)
return None
class NetworkModuleFull(network.NetworkModule):
def __init__(self, net: network.Network, weights: network.NetworkWeights):
super().__init__(net, weights)
self.weight = weights.w.get("diff")
self.ex_bias = weights.w.get("diff_b")
def calc_updown(self, orig_weight):
output_shape = self.weight.shape
updown = self.weight.to(orig_weight.device)
if self.ex_bias is not None:
ex_bias = self.ex_bias.to(orig_weight.device)
else:
ex_bias = None
return self.finalize_updown(updown, orig_weight, output_shape, ex_bias)

33
extensions-builtin/Lora/network_glora.py Normal file
View File

@ -0,0 +1,33 @@
import network
class ModuleTypeGLora(network.ModuleType):
def create_module(self, net: network.Network, weights: network.NetworkWeights):
if all(x in weights.w for x in ["a1.weight", "a2.weight", "alpha", "b1.weight", "b2.weight"]):
return NetworkModuleGLora(net, weights)
return None
# adapted from https://github.com/KohakuBlueleaf/LyCORIS
class NetworkModuleGLora(network.NetworkModule):
def __init__(self, net: network.Network, weights: network.NetworkWeights):
super().__init__(net, weights)
if hasattr(self.sd_module, 'weight'):
self.shape = self.sd_module.weight.shape
self.w1a = weights.w["a1.weight"]
self.w1b = weights.w["b1.weight"]
self.w2a = weights.w["a2.weight"]
self.w2b = weights.w["b2.weight"]
def calc_updown(self, orig_weight):
w1a = self.w1a.to(orig_weight.device)
w1b = self.w1b.to(orig_weight.device)
w2a = self.w2a.to(orig_weight.device)
w2b = self.w2b.to(orig_weight.device)
output_shape = [w1a.size(0), w1b.size(1)]
updown = ((w2b @ w1b) + ((orig_weight.to(dtype = w1a.dtype) @ w2a) @ w1a))
return self.finalize_updown(updown, orig_weight, output_shape)

55
extensions-builtin/Lora/network_hada.py Normal file
View File

@ -0,0 +1,55 @@
import lyco_helpers
import network
class ModuleTypeHada(network.ModuleType):
def create_module(self, net: network.Network, weights: network.NetworkWeights):
if all(x in weights.w for x in ["hada_w1_a", "hada_w1_b", "hada_w2_a", "hada_w2_b"]):
return NetworkModuleHada(net, weights)
return None
class NetworkModuleHada(network.NetworkModule):
def __init__(self, net: network.Network, weights: network.NetworkWeights):
super().__init__(net, weights)
if hasattr(self.sd_module, 'weight'):
self.shape = self.sd_module.weight.shape
self.w1a = weights.w["hada_w1_a"]
self.w1b = weights.w["hada_w1_b"]
self.dim = self.w1b.shape[0]
self.w2a = weights.w["hada_w2_a"]
self.w2b = weights.w["hada_w2_b"]
self.t1 = weights.w.get("hada_t1")
self.t2 = weights.w.get("hada_t2")
def calc_updown(self, orig_weight):
w1a = self.w1a.to(orig_weight.device)
w1b = self.w1b.to(orig_weight.device)
w2a = self.w2a.to(orig_weight.device)
w2b = self.w2b.to(orig_weight.device)
output_shape = [w1a.size(0), w1b.size(1)]
if self.t1 is not None:
output_shape = [w1a.size(1), w1b.size(1)]
t1 = self.t1.to(orig_weight.device)
updown1 = lyco_helpers.make_weight_cp(t1, w1a, w1b)
output_shape += t1.shape[2:]
else:
if len(w1b.shape) == 4:
output_shape += w1b.shape[2:]
updown1 = lyco_helpers.rebuild_conventional(w1a, w1b, output_shape)
if self.t2 is not None:
t2 = self.t2.to(orig_weight.device)
updown2 = lyco_helpers.make_weight_cp(t2, w2a, w2b)
else:
updown2 = lyco_helpers.rebuild_conventional(w2a, w2b, output_shape)
updown = updown1 * updown2
return self.finalize_updown(updown, orig_weight, output_shape)

30
extensions-builtin/Lora/network_ia3.py Normal file
View File

@ -0,0 +1,30 @@
import network
class ModuleTypeIa3(network.ModuleType):
def create_module(self, net: network.Network, weights: network.NetworkWeights):
if all(x in weights.w for x in ["weight"]):
return NetworkModuleIa3(net, weights)
return None
class NetworkModuleIa3(network.NetworkModule):
def __init__(self, net: network.Network, weights: network.NetworkWeights):
super().__init__(net, weights)
self.w = weights.w["weight"]
self.on_input = weights.w["on_input"].item()
def calc_updown(self, orig_weight):
w = self.w.to(orig_weight.device)
output_shape = [w.size(0), orig_weight.size(1)]
if self.on_input:
output_shape.reverse()
else:
w = w.reshape(-1, 1)
updown = orig_weight * w
return self.finalize_updown(updown, orig_weight, output_shape)

64
extensions-builtin/Lora/network_lokr.py Normal file
View File

@ -0,0 +1,64 @@
import torch
import lyco_helpers
import network
class ModuleTypeLokr(network.ModuleType):
def create_module(self, net: network.Network, weights: network.NetworkWeights):
has_1 = "lokr_w1" in weights.w or ("lokr_w1_a" in weights.w and "lokr_w1_b" in weights.w)
has_2 = "lokr_w2" in weights.w or ("lokr_w2_a" in weights.w and "lokr_w2_b" in weights.w)
if has_1 and has_2:
return NetworkModuleLokr(net, weights)
return None
def make_kron(orig_shape, w1, w2):
if len(w2.shape) == 4:
w1 = w1.unsqueeze(2).unsqueeze(2)
w2 = w2.contiguous()
return torch.kron(w1, w2).reshape(orig_shape)
class NetworkModuleLokr(network.NetworkModule):
def __init__(self, net: network.Network, weights: network.NetworkWeights):
super().__init__(net, weights)
self.w1 = weights.w.get("lokr_w1")
self.w1a = weights.w.get("lokr_w1_a")
self.w1b = weights.w.get("lokr_w1_b")
self.dim = self.w1b.shape[0] if self.w1b is not None else self.dim
self.w2 = weights.w.get("lokr_w2")
self.w2a = weights.w.get("lokr_w2_a")
self.w2b = weights.w.get("lokr_w2_b")
self.dim = self.w2b.shape[0] if self.w2b is not None else self.dim
self.t2 = weights.w.get("lokr_t2")
def calc_updown(self, orig_weight):
if self.w1 is not None:
w1 = self.w1.to(orig_weight.device)
else:
w1a = self.w1a.to(orig_weight.device)
w1b = self.w1b.to(orig_weight.device)
w1 = w1a @ w1b
if self.w2 is not None:
w2 = self.w2.to(orig_weight.device)
elif self.t2 is None:
w2a = self.w2a.to(orig_weight.device)
w2b = self.w2b.to(orig_weight.device)
w2 = w2a @ w2b
else:
t2 = self.t2.to(orig_weight.device)
w2a = self.w2a.to(orig_weight.device)
w2b = self.w2b.to(orig_weight.device)
w2 = lyco_helpers.make_weight_cp(t2, w2a, w2b)
output_shape = [w1.size(0) * w2.size(0), w1.size(1) * w2.size(1)]
if len(orig_weight.shape) == 4:
output_shape = orig_weight.shape
updown = make_kron(output_shape, w1, w2)
return self.finalize_updown(updown, orig_weight, output_shape)

94
extensions-builtin/Lora/network_lora.py Normal file
View File

@ -0,0 +1,94 @@
import torch
import lyco_helpers
import modules.models.sd3.mmdit
import network
from modules import devices
class ModuleTypeLora(network.ModuleType):
def create_module(self, net: network.Network, weights: network.NetworkWeights):
if all(x in weights.w for x in ["lora_up.weight", "lora_down.weight"]):
return NetworkModuleLora(net, weights)
if all(x in weights.w for x in ["lora_A.weight", "lora_B.weight"]):
w = weights.w.copy()
weights.w.clear()
weights.w.update({"lora_up.weight": w["lora_B.weight"], "lora_down.weight": w["lora_A.weight"]})
return NetworkModuleLora(net, weights)
return None
class NetworkModuleLora(network.NetworkModule):
def __init__(self, net: network.Network, weights: network.NetworkWeights):
super().__init__(net, weights)
self.up_model = self.create_module(weights.w, "lora_up.weight")
self.down_model = self.create_module(weights.w, "lora_down.weight")
self.mid_model = self.create_module(weights.w, "lora_mid.weight", none_ok=True)
self.dim = weights.w["lora_down.weight"].shape[0]
def create_module(self, weights, key, none_ok=False):
weight = weights.get(key)
if weight is None and none_ok:
return None
is_linear = type(self.sd_module) in [torch.nn.Linear, torch.nn.modules.linear.NonDynamicallyQuantizableLinear, torch.nn.MultiheadAttention, modules.models.sd3.mmdit.QkvLinear]
is_conv = type(self.sd_module) in [torch.nn.Conv2d]
if is_linear:
weight = weight.reshape(weight.shape[0], -1)
module = torch.nn.Linear(weight.shape[1], weight.shape[0], bias=False)
elif is_conv and key == "lora_down.weight" or key == "dyn_up":
if len(weight.shape) == 2:
weight = weight.reshape(weight.shape[0], -1, 1, 1)
if weight.shape[2] != 1 or weight.shape[3] != 1:
module = torch.nn.Conv2d(weight.shape[1], weight.shape[0], self.sd_module.kernel_size, self.sd_module.stride, self.sd_module.padding, bias=False)
else:
module = torch.nn.Conv2d(weight.shape[1], weight.shape[0], (1, 1), bias=False)
elif is_conv and key == "lora_mid.weight":
module = torch.nn.Conv2d(weight.shape[1], weight.shape[0], self.sd_module.kernel_size, self.sd_module.stride, self.sd_module.padding, bias=False)
elif is_conv and key == "lora_up.weight" or key == "dyn_down":
module = torch.nn.Conv2d(weight.shape[1], weight.shape[0], (1, 1), bias=False)
else:
raise AssertionError(f'Lora layer {self.network_key} matched a layer with unsupported type: {type(self.sd_module).__name__}')
with torch.no_grad():
if weight.shape != module.weight.shape:
weight = weight.reshape(module.weight.shape)
module.weight.copy_(weight)
module.to(device=devices.cpu, dtype=devices.dtype)
module.weight.requires_grad_(False)
return module
def calc_updown(self, orig_weight):
up = self.up_model.weight.to(orig_weight.device)
down = self.down_model.weight.to(orig_weight.device)
output_shape = [up.size(0), down.size(1)]
if self.mid_model is not None:
# cp-decomposition
mid = self.mid_model.weight.to(orig_weight.device)
updown = lyco_helpers.rebuild_cp_decomposition(up, down, mid)
output_shape += mid.shape[2:]
else:
if len(down.shape) == 4:
output_shape += down.shape[2:]
updown = lyco_helpers.rebuild_conventional(up, down, output_shape, self.network.dyn_dim)
return self.finalize_updown(updown, orig_weight, output_shape)
def forward(self, x, y):
self.up_model.to(device=devices.device)
self.down_model.to(device=devices.device)
return y + self.up_model(self.down_model(x)) * self.multiplier() * self.calc_scale()

28
extensions-builtin/Lora/network_norm.py Normal file
View File

@ -0,0 +1,28 @@
import network
class ModuleTypeNorm(network.ModuleType):
def create_module(self, net: network.Network, weights: network.NetworkWeights):
if all(x in weights.w for x in ["w_norm", "b_norm"]):
return NetworkModuleNorm(net, weights)
return None
class NetworkModuleNorm(network.NetworkModule):
def __init__(self, net: network.Network, weights: network.NetworkWeights):
super().__init__(net, weights)
self.w_norm = weights.w.get("w_norm")
self.b_norm = weights.w.get("b_norm")
def calc_updown(self, orig_weight):
output_shape = self.w_norm.shape
updown = self.w_norm.to(orig_weight.device)
if self.b_norm is not None:
ex_bias = self.b_norm.to(orig_weight.device)
else:
ex_bias = None
return self.finalize_updown(updown, orig_weight, output_shape, ex_bias)

118
extensions-builtin/Lora/network_oft.py Normal file
View File

@ -0,0 +1,118 @@
import torch
import network
from einops import rearrange
class ModuleTypeOFT(network.ModuleType):
def create_module(self, net: network.Network, weights: network.NetworkWeights):
if all(x in weights.w for x in ["oft_blocks"]) or all(x in weights.w for x in ["oft_diag"]):
return NetworkModuleOFT(net, weights)
return None
# Supports both kohya-ss' implementation of COFT https://github.com/kohya-ss/sd-scripts/blob/main/networks/oft.py
# and KohakuBlueleaf's implementation of OFT/COFT https://github.com/KohakuBlueleaf/LyCORIS/blob/dev/lycoris/modules/diag_oft.py
class NetworkModuleOFT(network.NetworkModule):
def __init__(self, net: network.Network, weights: network.NetworkWeights):
super().__init__(net, weights)
self.lin_module = None
self.org_module: list[torch.Module] = [self.sd_module]
self.scale = 1.0
self.is_R = False
self.is_boft = False
# kohya-ss/New LyCORIS OFT/BOFT
if "oft_blocks" in weights.w.keys():
self.oft_blocks = weights.w["oft_blocks"] # (num_blocks, block_size, block_size)
self.alpha = weights.w.get("alpha", None) # alpha is constraint
self.dim = self.oft_blocks.shape[0] # lora dim
# Old LyCORIS OFT
elif "oft_diag" in weights.w.keys():
self.is_R = True
self.oft_blocks = weights.w["oft_diag"]
# self.alpha is unused
self.dim = self.oft_blocks.shape[1] # (num_blocks, block_size, block_size)
is_linear = type(self.sd_module) in [torch.nn.Linear, torch.nn.modules.linear.NonDynamicallyQuantizableLinear]
is_conv = type(self.sd_module) in [torch.nn.Conv2d]
is_other_linear = type(self.sd_module) in [torch.nn.MultiheadAttention] # unsupported
if is_linear:
self.out_dim = self.sd_module.out_features
elif is_conv:
self.out_dim = self.sd_module.out_channels
elif is_other_linear:
self.out_dim = self.sd_module.embed_dim
# LyCORIS BOFT
if self.oft_blocks.dim() == 4:
self.is_boft = True
self.rescale = weights.w.get('rescale', None)
if self.rescale is not None and not is_other_linear:
self.rescale = self.rescale.reshape(-1, *[1]*(self.org_module[0].weight.dim() - 1))
self.num_blocks = self.dim
self.block_size = self.out_dim // self.dim
self.constraint = (0 if self.alpha is None else self.alpha) * self.out_dim
if self.is_R:
self.constraint = None
self.block_size = self.dim
self.num_blocks = self.out_dim // self.dim
elif self.is_boft:
self.boft_m = self.oft_blocks.shape[0]
self.num_blocks = self.oft_blocks.shape[1]
self.block_size = self.oft_blocks.shape[2]
self.boft_b = self.block_size
def calc_updown(self, orig_weight):
oft_blocks = self.oft_blocks.to(orig_weight.device)
eye = torch.eye(self.block_size, device=oft_blocks.device)
if not self.is_R:
block_Q = oft_blocks - oft_blocks.transpose(-1, -2) # ensure skew-symmetric orthogonal matrix
if self.constraint != 0:
norm_Q = torch.norm(block_Q.flatten())
new_norm_Q = torch.clamp(norm_Q, max=self.constraint.to(oft_blocks.device))
block_Q = block_Q * ((new_norm_Q + 1e-8) / (norm_Q + 1e-8))
oft_blocks = torch.matmul(eye + block_Q, (eye - block_Q).float().inverse())
R = oft_blocks.to(orig_weight.device)
if not self.is_boft:
# This errors out for MultiheadAttention, might need to be handled up-stream
merged_weight = rearrange(orig_weight, '(k n) ... -> k n ...', k=self.num_blocks, n=self.block_size)
merged_weight = torch.einsum(
'k n m, k n ... -> k m ...',
R,
merged_weight
)
merged_weight = rearrange(merged_weight, 'k m ... -> (k m) ...')
else:
# TODO: determine correct value for scale
scale = 1.0
m = self.boft_m
b = self.boft_b
r_b = b // 2
inp = orig_weight
for i in range(m):
bi = R[i] # b_num, b_size, b_size
if i == 0:
# Apply multiplier/scale and rescale into first weight
bi = bi * scale + (1 - scale) * eye
inp = rearrange(inp, "(c g k) ... -> (c k g) ...", g=2, k=2**i * r_b)
inp = rearrange(inp, "(d b) ... -> d b ...", b=b)
inp = torch.einsum("b i j, b j ... -> b i ...", bi, inp)
inp = rearrange(inp, "d b ... -> (d b) ...")
inp = rearrange(inp, "(c k g) ... -> (c g k) ...", g=2, k=2**i * r_b)
merged_weight = inp
# Rescale mechanism
if self.rescale is not None:
merged_weight = self.rescale.to(merged_weight) * merged_weight
updown = merged_weight.to(orig_weight.device) - orig_weight.to(merged_weight.dtype)
output_shape = orig_weight.shape
return self.finalize_updown(updown, orig_weight, output_shape)

737
extensions-builtin/Lora/networks.py Normal file
View File

@ -0,0 +1,737 @@
from __future__ import annotations
import gradio as gr
import logging
import os
import re
import lora_patches
import network
import network_lora
import network_glora
import network_hada
import network_ia3
import network_lokr
import network_full
import network_norm
import network_oft
import torch
from typing import Union
from modules import shared, devices, sd_models, errors, scripts, sd_hijack
import modules.textual_inversion.textual_inversion as textual_inversion
import modules.models.sd3.mmdit
from lora_logger import logger
module_types = [
network_lora.ModuleTypeLora(),
network_hada.ModuleTypeHada(),
network_ia3.ModuleTypeIa3(),
network_lokr.ModuleTypeLokr(),
network_full.ModuleTypeFull(),
network_norm.ModuleTypeNorm(),
network_glora.ModuleTypeGLora(),
network_oft.ModuleTypeOFT(),
]
re_digits = re.compile(r"\d+")
re_x_proj = re.compile(r"(.*)_([qkv]_proj)$")
re_compiled = {}
suffix_conversion = {
"attentions": {},
"resnets": {
"conv1": "in_layers_2",
"conv2": "out_layers_3",
"norm1": "in_layers_0",
"norm2": "out_layers_0",
"time_emb_proj": "emb_layers_1",
"conv_shortcut": "skip_connection",
}
}
def convert_diffusers_name_to_compvis(key, is_sd2):
def match(match_list, regex_text):
regex = re_compiled.get(regex_text)
if regex is None:
regex = re.compile(regex_text)
re_compiled[regex_text] = regex
r = re.match(regex, key)
if not r:
return False
match_list.clear()
match_list.extend([int(x) if re.match(re_digits, x) else x for x in r.groups()])
return True
m = []
if match(m, r"lora_unet_conv_in(.*)"):
return f'diffusion_model_input_blocks_0_0{m[0]}'
if match(m, r"lora_unet_conv_out(.*)"):
return f'diffusion_model_out_2{m[0]}'
if match(m, r"lora_unet_time_embedding_linear_(\d+)(.*)"):
return f"diffusion_model_time_embed_{m[0] * 2 - 2}{m[1]}"
if match(m, r"lora_unet_down_blocks_(\d+)_(attentions|resnets)_(\d+)_(.+)"):
suffix = suffix_conversion.get(m[1], {}).get(m[3], m[3])
return f"diffusion_model_input_blocks_{1 + m[0] * 3 + m[2]}_{1 if m[1] == 'attentions' else 0}_{suffix}"
if match(m, r"lora_unet_mid_block_(attentions|resnets)_(\d+)_(.+)"):
suffix = suffix_conversion.get(m[0], {}).get(m[2], m[2])
return f"diffusion_model_middle_block_{1 if m[0] == 'attentions' else m[1] * 2}_{suffix}"
if match(m, r"lora_unet_up_blocks_(\d+)_(attentions|resnets)_(\d+)_(.+)"):
suffix = suffix_conversion.get(m[1], {}).get(m[3], m[3])
return f"diffusion_model_output_blocks_{m[0] * 3 + m[2]}_{1 if m[1] == 'attentions' else 0}_{suffix}"
if match(m, r"lora_unet_down_blocks_(\d+)_downsamplers_0_conv"):
return f"diffusion_model_input_blocks_{3 + m[0] * 3}_0_op"
if match(m, r"lora_unet_up_blocks_(\d+)_upsamplers_0_conv"):
return f"diffusion_model_output_blocks_{2 + m[0] * 3}_{2 if m[0]>0 else 1}_conv"
if match(m, r"lora_te_text_model_encoder_layers_(\d+)_(.+)"):
if is_sd2:
if 'mlp_fc1' in m[1]:
return f"model_transformer_resblocks_{m[0]}_{m[1].replace('mlp_fc1', 'mlp_c_fc')}"
elif 'mlp_fc2' in m[1]:
return f"model_transformer_resblocks_{m[0]}_{m[1].replace('mlp_fc2', 'mlp_c_proj')}"
else:
return f"model_transformer_resblocks_{m[0]}_{m[1].replace('self_attn', 'attn')}"
return f"transformer_text_model_encoder_layers_{m[0]}_{m[1]}"
if match(m, r"lora_te2_text_model_encoder_layers_(\d+)_(.+)"):
if 'mlp_fc1' in m[1]:
return f"1_model_transformer_resblocks_{m[0]}_{m[1].replace('mlp_fc1', 'mlp_c_fc')}"
elif 'mlp_fc2' in m[1]:
return f"1_model_transformer_resblocks_{m[0]}_{m[1].replace('mlp_fc2', 'mlp_c_proj')}"
else:
return f"1_model_transformer_resblocks_{m[0]}_{m[1].replace('self_attn', 'attn')}"
return key
def assign_network_names_to_compvis_modules(sd_model):
network_layer_mapping = {}
if shared.sd_model.is_sdxl:
for i, embedder in enumerate(shared.sd_model.conditioner.embedders):
if not hasattr(embedder, 'wrapped'):
continue
for name, module in embedder.wrapped.named_modules():
network_name = f'{i}_{name.replace(".", "_")}'
network_layer_mapping[network_name] = module
module.network_layer_name = network_name
else:
cond_stage_model = getattr(shared.sd_model.cond_stage_model, 'wrapped', shared.sd_model.cond_stage_model)
for name, module in cond_stage_model.named_modules():
network_name = name.replace(".", "_")
network_layer_mapping[network_name] = module
module.network_layer_name = network_name
for name, module in shared.sd_model.model.named_modules():
network_name = name.replace(".", "_")
network_layer_mapping[network_name] = module
module.network_layer_name = network_name
sd_model.network_layer_mapping = network_layer_mapping
class BundledTIHash(str):
def __init__(self, hash_str):
self.hash = hash_str
def __str__(self):
return self.hash if shared.opts.lora_bundled_ti_to_infotext else ''
def load_network(name, network_on_disk):
net = network.Network(name, network_on_disk)
net.mtime = os.path.getmtime(network_on_disk.filename)
sd = sd_models.read_state_dict(network_on_disk.filename)
# this should not be needed but is here as an emergency fix for an unknown error people are experiencing in 1.2.0
if not hasattr(shared.sd_model, 'network_layer_mapping'):
assign_network_names_to_compvis_modules(shared.sd_model)
keys_failed_to_match = {}
is_sd2 = 'model_transformer_resblocks' in shared.sd_model.network_layer_mapping
if hasattr(shared.sd_model, 'diffusers_weight_map'):
diffusers_weight_map = shared.sd_model.diffusers_weight_map
elif hasattr(shared.sd_model, 'diffusers_weight_mapping'):
diffusers_weight_map = {}
for k, v in shared.sd_model.diffusers_weight_mapping():
diffusers_weight_map[k] = v
shared.sd_model.diffusers_weight_map = diffusers_weight_map
else:
diffusers_weight_map = None
matched_networks = {}
bundle_embeddings = {}
for key_network, weight in sd.items():
if diffusers_weight_map:
key_network_without_network_parts, network_name, network_weight = key_network.rsplit(".", 2)
network_part = network_name + '.' + network_weight
else:
key_network_without_network_parts, _, network_part = key_network.partition(".")
if key_network_without_network_parts == "bundle_emb":
emb_name, vec_name = network_part.split(".", 1)
emb_dict = bundle_embeddings.get(emb_name, {})
if vec_name.split('.')[0] == 'string_to_param':
_, k2 = vec_name.split('.', 1)
emb_dict['string_to_param'] = {k2: weight}
else:
emb_dict[vec_name] = weight
bundle_embeddings[emb_name] = emb_dict
if diffusers_weight_map:
key = diffusers_weight_map.get(key_network_without_network_parts, key_network_without_network_parts)
else:
key = convert_diffusers_name_to_compvis(key_network_without_network_parts, is_sd2)
sd_module = shared.sd_model.network_layer_mapping.get(key, None)
if sd_module is None:
m = re_x_proj.match(key)
if m:
sd_module = shared.sd_model.network_layer_mapping.get(m.group(1), None)
# SDXL loras seem to already have correct compvis keys, so only need to replace "lora_unet" with "diffusion_model"
if sd_module is None and "lora_unet" in key_network_without_network_parts:
key = key_network_without_network_parts.replace("lora_unet", "diffusion_model")
sd_module = shared.sd_model.network_layer_mapping.get(key, None)
elif sd_module is None and "lora_te1_text_model" in key_network_without_network_parts:
key = key_network_without_network_parts.replace("lora_te1_text_model", "0_transformer_text_model")
sd_module = shared.sd_model.network_layer_mapping.get(key, None)
# some SD1 Loras also have correct compvis keys
if sd_module is None:
key = key_network_without_network_parts.replace("lora_te1_text_model", "transformer_text_model")
sd_module = shared.sd_model.network_layer_mapping.get(key, None)
# kohya_ss OFT module
elif sd_module is None and "oft_unet" in key_network_without_network_parts:
key = key_network_without_network_parts.replace("oft_unet", "diffusion_model")
sd_module = shared.sd_model.network_layer_mapping.get(key, None)
# KohakuBlueLeaf OFT module
if sd_module is None and "oft_diag" in key:
key = key_network_without_network_parts.replace("lora_unet", "diffusion_model")
key = key_network_without_network_parts.replace("lora_te1_text_model", "0_transformer_text_model")
sd_module = shared.sd_model.network_layer_mapping.get(key, None)
if sd_module is None:
keys_failed_to_match[key_network] = key
continue
if key not in matched_networks:
matched_networks[key] = network.NetworkWeights(network_key=key_network, sd_key=key, w={}, sd_module=sd_module)
matched_networks[key].w[network_part] = weight
for key, weights in matched_networks.items():
net_module = None
for nettype in module_types:
net_module = nettype.create_module(net, weights)
if net_module is not None:
break
if net_module is None:
raise AssertionError(f"Could not find a module type (out of {', '.join([x.__class__.__name__ for x in module_types])}) that would accept those keys: {', '.join(weights.w)}")
net.modules[key] = net_module
embeddings = {}
for emb_name, data in bundle_embeddings.items():
embedding = textual_inversion.create_embedding_from_data(data, emb_name, filename=network_on_disk.filename + "/" + emb_name)
embedding.loaded = None
embedding.shorthash = BundledTIHash(name)
embeddings[emb_name] = embedding
net.bundle_embeddings = embeddings
if keys_failed_to_match:
logging.debug(f"Network {network_on_disk.filename} didn't match keys: {keys_failed_to_match}")
return net
def purge_networks_from_memory():
while len(networks_in_memory) > shared.opts.lora_in_memory_limit and len(networks_in_memory) > 0:
name = next(iter(networks_in_memory))
networks_in_memory.pop(name, None)
devices.torch_gc()
def load_networks(names, te_multipliers=None, unet_multipliers=None, dyn_dims=None):
emb_db = sd_hijack.model_hijack.embedding_db
already_loaded = {}
for net in loaded_networks:
if net.name in names:
already_loaded[net.name] = net
for emb_name, embedding in net.bundle_embeddings.items():
if embedding.loaded:
emb_db.register_embedding_by_name(None, shared.sd_model, emb_name)
loaded_networks.clear()
unavailable_networks = []
for name in names:
if name.lower() in forbidden_network_aliases and available_networks.get(name) is None:
unavailable_networks.append(name)
elif available_network_aliases.get(name) is None:
unavailable_networks.append(name)
if unavailable_networks:
update_available_networks_by_names(unavailable_networks)
networks_on_disk = [available_networks.get(name, None) if name.lower() in forbidden_network_aliases else available_network_aliases.get(name, None) for name in names]
if any(x is None for x in networks_on_disk):
list_available_networks()
networks_on_disk = [available_networks.get(name, None) if name.lower() in forbidden_network_aliases else available_network_aliases.get(name, None) for name in names]
failed_to_load_networks = []
for i, (network_on_disk, name) in enumerate(zip(networks_on_disk, names)):
net = already_loaded.get(name, None)
if network_on_disk is not None:
if net is None:
net = networks_in_memory.get(name)
if net is None or os.path.getmtime(network_on_disk.filename) > net.mtime:
try:
net = load_network(name, network_on_disk)
networks_in_memory.pop(name, None)
networks_in_memory[name] = net
except Exception as e:
errors.display(e, f"loading network {network_on_disk.filename}")
continue
net.mentioned_name = name
network_on_disk.read_hash()
if net is None:
failed_to_load_networks.append(name)
logging.info(f"Couldn't find network with name {name}")
continue
net.te_multiplier = te_multipliers[i] if te_multipliers else 1.0
net.unet_multiplier = unet_multipliers[i] if unet_multipliers else 1.0
net.dyn_dim = dyn_dims[i] if dyn_dims else 1.0
loaded_networks.append(net)
for emb_name, embedding in net.bundle_embeddings.items():
if embedding.loaded is None and emb_name in emb_db.word_embeddings:
logger.warning(
f'Skip bundle embedding: "{emb_name}"'
' as it was already loaded from embeddings folder'
)
continue
embedding.loaded = False
if emb_db.expected_shape == -1 or emb_db.expected_shape == embedding.shape:
embedding.loaded = True
emb_db.register_embedding(embedding, shared.sd_model)
else:
emb_db.skipped_embeddings[name] = embedding
if failed_to_load_networks:
lora_not_found_message = f'Lora not found: {", ".join(failed_to_load_networks)}'
sd_hijack.model_hijack.comments.append(lora_not_found_message)
if shared.opts.lora_not_found_warning_console:
print(f'\n{lora_not_found_message}\n')
if shared.opts.lora_not_found_gradio_warning:
gr.Warning(lora_not_found_message)
purge_networks_from_memory()
def allowed_layer_without_weight(layer):
if isinstance(layer, torch.nn.LayerNorm) and not layer.elementwise_affine:
return True
return False
def store_weights_backup(weight):
if weight is None:
return None
return weight.to(devices.cpu, copy=True)
def restore_weights_backup(obj, field, weight):
if weight is None:
setattr(obj, field, None)
return
getattr(obj, field).copy_(weight)
def network_restore_weights_from_backup(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn.GroupNorm, torch.nn.LayerNorm, torch.nn.MultiheadAttention]):
weights_backup = getattr(self, "network_weights_backup", None)
bias_backup = getattr(self, "network_bias_backup", None)
if weights_backup is None and bias_backup is None:
return
if weights_backup is not None:
if isinstance(self, torch.nn.MultiheadAttention):
restore_weights_backup(self, 'in_proj_weight', weights_backup[0])
restore_weights_backup(self.out_proj, 'weight', weights_backup[1])
else:
restore_weights_backup(self, 'weight', weights_backup)
if isinstance(self, torch.nn.MultiheadAttention):
restore_weights_backup(self.out_proj, 'bias', bias_backup)
else:
restore_weights_backup(self, 'bias', bias_backup)
def network_apply_weights(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn.GroupNorm, torch.nn.LayerNorm, torch.nn.MultiheadAttention]):
"""
Applies the currently selected set of networks to the weights of torch layer self.
If weights already have this particular set of networks applied, does nothing.
If not, restores original weights from backup and alters weights according to networks.
"""
network_layer_name = getattr(self, 'network_layer_name', None)
if network_layer_name is None:
return
current_names = getattr(self, "network_current_names", ())
wanted_names = tuple((x.name, x.te_multiplier, x.unet_multiplier, x.dyn_dim) for x in loaded_networks)
weights_backup = getattr(self, "network_weights_backup", None)
if weights_backup is None and wanted_names != ():
if current_names != () and not allowed_layer_without_weight(self):
raise RuntimeError(f"{network_layer_name} - no backup weights found and current weights are not unchanged")
if isinstance(self, torch.nn.MultiheadAttention):
weights_backup = (store_weights_backup(self.in_proj_weight), store_weights_backup(self.out_proj.weight))
else:
weights_backup = store_weights_backup(self.weight)
self.network_weights_backup = weights_backup
bias_backup = getattr(self, "network_bias_backup", None)
if bias_backup is None and wanted_names != ():
if isinstance(self, torch.nn.MultiheadAttention) and self.out_proj.bias is not None:
bias_backup = store_weights_backup(self.out_proj.bias)
elif getattr(self, 'bias', None) is not None:
bias_backup = store_weights_backup(self.bias)
else:
bias_backup = None
# Unlike weight which always has value, some modules don't have bias.
# Only report if bias is not None and current bias are not unchanged.
if bias_backup is not None and current_names != ():
raise RuntimeError("no backup bias found and current bias are not unchanged")
self.network_bias_backup = bias_backup
if current_names != wanted_names:
network_restore_weights_from_backup(self)
for net in loaded_networks:
module = net.modules.get(network_layer_name, None)
if module is not None and hasattr(self, 'weight') and not isinstance(module, modules.models.sd3.mmdit.QkvLinear):
try:
with torch.no_grad():
if getattr(self, 'fp16_weight', None) is None:
weight = self.weight
bias = self.bias
else:
weight = self.fp16_weight.clone().to(self.weight.device)
bias = getattr(self, 'fp16_bias', None)
if bias is not None:
bias = bias.clone().to(self.bias.device)
updown, ex_bias = module.calc_updown(weight)
if len(weight.shape) == 4 and weight.shape[1] == 9:
# inpainting model. zero pad updown to make channel[1] 4 to 9
updown = torch.nn.functional.pad(updown, (0, 0, 0, 0, 0, 5))
self.weight.copy_((weight.to(dtype=updown.dtype) + updown).to(dtype=self.weight.dtype))
if ex_bias is not None and hasattr(self, 'bias'):
if self.bias is None:
self.bias = torch.nn.Parameter(ex_bias).to(self.weight.dtype)
else:
self.bias.copy_((bias + ex_bias).to(dtype=self.bias.dtype))
except RuntimeError as e:
logging.debug(f"Network {net.name} layer {network_layer_name}: {e}")
extra_network_lora.errors[net.name] = extra_network_lora.errors.get(net.name, 0) + 1
continue
module_q = net.modules.get(network_layer_name + "_q_proj", None)
module_k = net.modules.get(network_layer_name + "_k_proj", None)
module_v = net.modules.get(network_layer_name + "_v_proj", None)
module_out = net.modules.get(network_layer_name + "_out_proj", None)
if isinstance(self, torch.nn.MultiheadAttention) and module_q and module_k and module_v and module_out:
try:
with torch.no_grad():
# Send "real" orig_weight into MHA's lora module
qw, kw, vw = self.in_proj_weight.chunk(3, 0)
updown_q, _ = module_q.calc_updown(qw)
updown_k, _ = module_k.calc_updown(kw)
updown_v, _ = module_v.calc_updown(vw)
del qw, kw, vw
updown_qkv = torch.vstack([updown_q, updown_k, updown_v])
updown_out, ex_bias = module_out.calc_updown(self.out_proj.weight)
self.in_proj_weight += updown_qkv
self.out_proj.weight += updown_out
if ex_bias is not None:
if self.out_proj.bias is None:
self.out_proj.bias = torch.nn.Parameter(ex_bias)
else:
self.out_proj.bias += ex_bias
except RuntimeError as e:
logging.debug(f"Network {net.name} layer {network_layer_name}: {e}")
extra_network_lora.errors[net.name] = extra_network_lora.errors.get(net.name, 0) + 1
continue
if isinstance(self, modules.models.sd3.mmdit.QkvLinear) and module_q and module_k and module_v:
try:
with torch.no_grad():
# Send "real" orig_weight into MHA's lora module
qw, kw, vw = self.weight.chunk(3, 0)
updown_q, _ = module_q.calc_updown(qw)
updown_k, _ = module_k.calc_updown(kw)
updown_v, _ = module_v.calc_updown(vw)
del qw, kw, vw
updown_qkv = torch.vstack([updown_q, updown_k, updown_v])
self.weight += updown_qkv
except RuntimeError as e:
logging.debug(f"Network {net.name} layer {network_layer_name}: {e}")
extra_network_lora.errors[net.name] = extra_network_lora.errors.get(net.name, 0) + 1
continue
if module is None:
continue
logging.debug(f"Network {net.name} layer {network_layer_name}: couldn't find supported operation")
extra_network_lora.errors[net.name] = extra_network_lora.errors.get(net.name, 0) + 1
self.network_current_names = wanted_names
def network_forward(org_module, input, original_forward):
"""
Old way of applying Lora by executing operations during layer's forward.
Stacking many loras this way results in big performance degradation.
"""
if len(loaded_networks) == 0:
return original_forward(org_module, input)
input = devices.cond_cast_unet(input)
network_restore_weights_from_backup(org_module)
network_reset_cached_weight(org_module)
y = original_forward(org_module, input)
network_layer_name = getattr(org_module, 'network_layer_name', None)
for lora in loaded_networks:
module = lora.modules.get(network_layer_name, None)
if module is None:
continue
y = module.forward(input, y)
return y
def network_reset_cached_weight(self: Union[torch.nn.Conv2d, torch.nn.Linear]):
self.network_current_names = ()
self.network_weights_backup = None
self.network_bias_backup = None
def network_Linear_forward(self, input):
if shared.opts.lora_functional:
return network_forward(self, input, originals.Linear_forward)
network_apply_weights(self)
return originals.Linear_forward(self, input)
def network_Linear_load_state_dict(self, *args, **kwargs):
network_reset_cached_weight(self)
return originals.Linear_load_state_dict(self, *args, **kwargs)
def network_Conv2d_forward(self, input):
if shared.opts.lora_functional:
return network_forward(self, input, originals.Conv2d_forward)
network_apply_weights(self)
return originals.Conv2d_forward(self, input)
def network_Conv2d_load_state_dict(self, *args, **kwargs):
network_reset_cached_weight(self)
return originals.Conv2d_load_state_dict(self, *args, **kwargs)
def network_GroupNorm_forward(self, input):
if shared.opts.lora_functional:
return network_forward(self, input, originals.GroupNorm_forward)
network_apply_weights(self)
return originals.GroupNorm_forward(self, input)
def network_GroupNorm_load_state_dict(self, *args, **kwargs):
network_reset_cached_weight(self)
return originals.GroupNorm_load_state_dict(self, *args, **kwargs)
def network_LayerNorm_forward(self, input):
if shared.opts.lora_functional:
return network_forward(self, input, originals.LayerNorm_forward)
network_apply_weights(self)
return originals.LayerNorm_forward(self, input)
def network_LayerNorm_load_state_dict(self, *args, **kwargs):
network_reset_cached_weight(self)
return originals.LayerNorm_load_state_dict(self, *args, **kwargs)
def network_MultiheadAttention_forward(self, *args, **kwargs):
network_apply_weights(self)
return originals.MultiheadAttention_forward(self, *args, **kwargs)
def network_MultiheadAttention_load_state_dict(self, *args, **kwargs):
network_reset_cached_weight(self)
return originals.MultiheadAttention_load_state_dict(self, *args, **kwargs)
def process_network_files(names: list[str] | None = None):
candidates = list(shared.walk_files(shared.cmd_opts.lora_dir, allowed_extensions=[".pt", ".ckpt", ".safetensors"]))
candidates += list(shared.walk_files(shared.cmd_opts.lyco_dir_backcompat, allowed_extensions=[".pt", ".ckpt", ".safetensors"]))
for filename in candidates:
if os.path.isdir(filename):
continue
name = os.path.splitext(os.path.basename(filename))[0]
# if names is provided, only load networks with names in the list
if names and name not in names:
continue
try:
entry = network.NetworkOnDisk(name, filename)
except OSError: # should catch FileNotFoundError and PermissionError etc.
errors.report(f"Failed to load network {name} from {filename}", exc_info=True)
continue
available_networks[name] = entry
if entry.alias in available_network_aliases:
forbidden_network_aliases[entry.alias.lower()] = 1
available_network_aliases[name] = entry
available_network_aliases[entry.alias] = entry
def update_available_networks_by_names(names: list[str]):
process_network_files(names)
def list_available_networks():
available_networks.clear()
available_network_aliases.clear()
forbidden_network_aliases.clear()
available_network_hash_lookup.clear()
forbidden_network_aliases.update({"none": 1, "Addams": 1})
os.makedirs(shared.cmd_opts.lora_dir, exist_ok=True)
process_network_files()
re_network_name = re.compile(r"(.*)\s*\([0-9a-fA-F]+\)")
def infotext_pasted(infotext, params):
if "AddNet Module 1" in [x[1] for x in scripts.scripts_txt2img.infotext_fields]:
return # if the other extension is active, it will handle those fields, no need to do anything
added = []
for k in params:
if not k.startswith("AddNet Model "):
continue
num = k[13:]
if params.get("AddNet Module " + num) != "LoRA":
continue
name = params.get("AddNet Model " + num)
if name is None:
continue
m = re_network_name.match(name)
if m:
name = m.group(1)
multiplier = params.get("AddNet Weight A " + num, "1.0")
added.append(f"<lora:{name}:{multiplier}>")
if added:
params["Prompt"] += "\n" + "".join(added)
originals: lora_patches.LoraPatches = None
extra_network_lora = None
available_networks = {}
available_network_aliases = {}
loaded_networks = []
loaded_bundle_embeddings = {}
networks_in_memory = {}
available_network_hash_lookup = {}
forbidden_network_aliases = {}
list_available_networks()

8
extensions-builtin/Lora/preload.py Normal file
View File

@ -0,0 +1,8 @@
import os
from modules import paths
from modules.paths_internal import normalized_filepath
def preload(parser):
parser.add_argument("--lora-dir", type=normalized_filepath, help="Path to directory with Lora networks.", default=os.path.join(paths.models_path, 'Lora'))
parser.add_argument("--lyco-dir-backcompat", type=normalized_filepath, help="Path to directory with LyCORIS networks (for backawards compatibility; can also use --lyco-dir).", default=os.path.join(paths.models_path, 'LyCORIS'))

102
extensions-builtin/Lora/scripts/lora_script.py Normal file
View File

@ -0,0 +1,102 @@
import re
import gradio as gr
from fastapi import FastAPI
import network
import networks
import lora # noqa:F401
import lora_patches
import extra_networks_lora
import ui_extra_networks_lora
from modules import script_callbacks, ui_extra_networks, extra_networks, shared
def unload():
networks.originals.undo()
def before_ui():
ui_extra_networks.register_page(ui_extra_networks_lora.ExtraNetworksPageLora())
networks.extra_network_lora = extra_networks_lora.ExtraNetworkLora()
extra_networks.register_extra_network(networks.extra_network_lora)
extra_networks.register_extra_network_alias(networks.extra_network_lora, "lyco")
networks.originals = lora_patches.LoraPatches()
script_callbacks.on_model_loaded(networks.assign_network_names_to_compvis_modules)
script_callbacks.on_script_unloaded(unload)
script_callbacks.on_before_ui(before_ui)
script_callbacks.on_infotext_pasted(networks.infotext_pasted)
shared.options_templates.update(shared.options_section(('extra_networks', "Extra Networks"), {
"sd_lora": shared.OptionInfo("None", "Add network to prompt", gr.Dropdown, lambda: {"choices": ["None", *networks.available_networks]}, refresh=networks.list_available_networks),
"lora_preferred_name": shared.OptionInfo("Alias from file", "When adding to prompt, refer to Lora by", gr.Radio, {"choices": ["Alias from file", "Filename"]}),
"lora_add_hashes_to_infotext": shared.OptionInfo(True, "Add Lora hashes to infotext"),
"lora_bundled_ti_to_infotext": shared.OptionInfo(True, "Add Lora name as TI hashes for bundled Textual Inversion").info('"Add Textual Inversion hashes to infotext" needs to be enabled'),
"lora_show_all": shared.OptionInfo(False, "Always show all networks on the Lora page").info("otherwise, those detected as for incompatible version of Stable Diffusion will be hidden"),
"lora_hide_unknown_for_versions": shared.OptionInfo([], "Hide networks of unknown versions for model versions", gr.CheckboxGroup, {"choices": ["SD1", "SD2", "SDXL"]}),
"lora_in_memory_limit": shared.OptionInfo(0, "Number of Lora networks to keep cached in memory", gr.Number, {"precision": 0}),
"lora_not_found_warning_console": shared.OptionInfo(False, "Lora not found warning in console"),
"lora_not_found_gradio_warning": shared.OptionInfo(False, "Lora not found warning popup in webui"),
}))
shared.options_templates.update(shared.options_section(('compatibility', "Compatibility"), {
"lora_functional": shared.OptionInfo(False, "Lora/Networks: use old method that takes longer when you have multiple Loras active and produces same results as kohya-ss/sd-webui-additional-networks extension"),
}))
def create_lora_json(obj: network.NetworkOnDisk):
return {
"name": obj.name,
"alias": obj.alias,
"path": obj.filename,
"metadata": obj.metadata,
}
def api_networks(_: gr.Blocks, app: FastAPI):
@app.get("/sdapi/v1/loras")
async def get_loras():
return [create_lora_json(obj) for obj in networks.available_networks.values()]
@app.post("/sdapi/v1/refresh-loras")
async def refresh_loras():
return networks.list_available_networks()
script_callbacks.on_app_started(api_networks)
re_lora = re.compile("<lora:([^:]+):")
def infotext_pasted(infotext, d):
hashes = d.get("Lora hashes")
if not hashes:
return
hashes = [x.strip().split(':', 1) for x in hashes.split(",")]
hashes = {x[0].strip().replace(",", ""): x[1].strip() for x in hashes}
def network_replacement(m):
alias = m.group(1)
shorthash = hashes.get(alias)
if shorthash is None:
return m.group(0)
network_on_disk = networks.available_network_hash_lookup.get(shorthash)
if network_on_disk is None:
return m.group(0)
return f'<lora:{network_on_disk.get_alias()}:'
d["Prompt"] = re.sub(re_lora, network_replacement, d["Prompt"])
script_callbacks.on_infotext_pasted(infotext_pasted)
shared.opts.onchange("lora_in_memory_limit", networks.purge_networks_from_memory)

226
extensions-builtin/Lora/ui_edit_user_metadata.py Normal file
View File

@ -0,0 +1,226 @@
import datetime
import html
import random
import gradio as gr
import re
from modules import ui_extra_networks_user_metadata
def is_non_comma_tagset(tags):
average_tag_length = sum(len(x) for x in tags.keys()) / len(tags)
return average_tag_length >= 16
re_word = re.compile(r"[-_\w']+")
re_comma = re.compile(r" *, *")
def build_tags(metadata):
tags = {}
ss_tag_frequency = metadata.get("ss_tag_frequency", {})
if ss_tag_frequency is not None and hasattr(ss_tag_frequency, 'items'):
for _, tags_dict in ss_tag_frequency.items():
for tag, tag_count in tags_dict.items():
tag = tag.strip()
tags[tag] = tags.get(tag, 0) + int(tag_count)
if tags and is_non_comma_tagset(tags):
new_tags = {}
for text, text_count in tags.items():
for word in re.findall(re_word, text):
if len(word) < 3:
continue
new_tags[word] = new_tags.get(word, 0) + text_count
tags = new_tags
ordered_tags = sorted(tags.keys(), key=tags.get, reverse=True)
return [(tag, tags[tag]) for tag in ordered_tags]
class LoraUserMetadataEditor(ui_extra_networks_user_metadata.UserMetadataEditor):
def __init__(self, ui, tabname, page):
super().__init__(ui, tabname, page)
self.select_sd_version = None
self.taginfo = None
self.edit_activation_text = None
self.slider_preferred_weight = None
self.edit_notes = None
def save_lora_user_metadata(self, name, desc, sd_version, activation_text, preferred_weight, negative_text, notes):
user_metadata = self.get_user_metadata(name)
user_metadata["description"] = desc
user_metadata["sd version"] = sd_version
user_metadata["activation text"] = activation_text
user_metadata["preferred weight"] = preferred_weight
user_metadata["negative text"] = negative_text
user_metadata["notes"] = notes
self.write_user_metadata(name, user_metadata)
def get_metadata_table(self, name):
table = super().get_metadata_table(name)
item = self.page.items.get(name, {})
metadata = item.get("metadata") or {}
keys = {
'ss_output_name': "Output name:",
'ss_sd_model_name': "Model:",
'ss_clip_skip': "Clip skip:",
'ss_network_module': "Kohya module:",
}
for key, label in keys.items():
value = metadata.get(key, None)
if value is not None and str(value) != "None":
table.append((label, html.escape(value)))
ss_training_started_at = metadata.get('ss_training_started_at')
if ss_training_started_at:
table.append(("Date trained:", datetime.datetime.utcfromtimestamp(float(ss_training_started_at)).strftime('%Y-%m-%d %H:%M')))
ss_bucket_info = metadata.get("ss_bucket_info")
if ss_bucket_info and "buckets" in ss_bucket_info:
resolutions = {}
for _, bucket in ss_bucket_info["buckets"].items():
resolution = bucket["resolution"]
resolution = f'{resolution[1]}x{resolution[0]}'
resolutions[resolution] = resolutions.get(resolution, 0) + int(bucket["count"])
resolutions_list = sorted(resolutions.keys(), key=resolutions.get, reverse=True)
resolutions_text = html.escape(", ".join(resolutions_list[0:4]))
if len(resolutions) > 4:
resolutions_text += ", ..."
resolutions_text = f"<span title='{html.escape(', '.join(resolutions_list))}'>{resolutions_text}</span>"
table.append(('Resolutions:' if len(resolutions_list) > 1 else 'Resolution:', resolutions_text))
image_count = 0
for _, params in metadata.get("ss_dataset_dirs", {}).items():
image_count += int(params.get("img_count", 0))
if image_count:
table.append(("Dataset size:", image_count))
return table
def put_values_into_components(self, name):
user_metadata = self.get_user_metadata(name)
values = super().put_values_into_components(name)
item = self.page.items.get(name, {})
metadata = item.get("metadata") or {}
tags = build_tags(metadata)
gradio_tags = [(tag, str(count)) for tag, count in tags[0:24]]
return [
*values[0:5],
item.get("sd_version", "Unknown"),
gr.HighlightedText.update(value=gradio_tags, visible=True if tags else False),
user_metadata.get('activation text', ''),
float(user_metadata.get('preferred weight', 0.0)),
user_metadata.get('negative text', ''),
gr.update(visible=True if tags else False),
gr.update(value=self.generate_random_prompt_from_tags(tags), visible=True if tags else False),
]
def generate_random_prompt(self, name):
item = self.page.items.get(name, {})
metadata = item.get("metadata") or {}
tags = build_tags(metadata)
return self.generate_random_prompt_from_tags(tags)
def generate_random_prompt_from_tags(self, tags):
max_count = None
res = []
for tag, count in tags:
if not max_count:
max_count = count
v = random.random() * max_count
if count > v:
for x in "({[]})":
tag = tag.replace(x, '\\' + x)
res.append(tag)
return ", ".join(sorted(res))
def create_extra_default_items_in_left_column(self):
# this would be a lot better as gr.Radio but I can't make it work
self.select_sd_version = gr.Dropdown(['SD1', 'SD2', 'SDXL', 'Unknown'], value='Unknown', label='Stable Diffusion version', interactive=True)
def create_editor(self):
self.create_default_editor_elems()
self.taginfo = gr.HighlightedText(label="Training dataset tags")
self.edit_activation_text = gr.Text(label='Activation text', info="Will be added to prompt along with Lora")
self.slider_preferred_weight = gr.Slider(label='Preferred weight', info="Set to 0 to disable", minimum=0.0, maximum=2.0, step=0.01)
self.edit_negative_text = gr.Text(label='Negative prompt', info="Will be added to negative prompts")
with gr.Row() as row_random_prompt:
with gr.Column(scale=8):
random_prompt = gr.Textbox(label='Random prompt', lines=4, max_lines=4, interactive=False)
with gr.Column(scale=1, min_width=120):
generate_random_prompt = gr.Button('Generate', size="lg", scale=1)
self.edit_notes = gr.TextArea(label='Notes', lines=4)
generate_random_prompt.click(fn=self.generate_random_prompt, inputs=[self.edit_name_input], outputs=[random_prompt], show_progress=False)
def select_tag(activation_text, evt: gr.SelectData):
tag = evt.value[0]
words = re.split(re_comma, activation_text)
if tag in words:
words = [x for x in words if x != tag and x.strip()]
return ", ".join(words)
return activation_text + ", " + tag if activation_text else tag
self.taginfo.select(fn=select_tag, inputs=[self.edit_activation_text], outputs=[self.edit_activation_text], show_progress=False)
self.create_default_buttons()
viewed_components = [
self.edit_name,
self.edit_description,
self.html_filedata,
self.html_preview,
self.edit_notes,
self.select_sd_version,
self.taginfo,
self.edit_activation_text,
self.slider_preferred_weight,
self.edit_negative_text,
row_random_prompt,
random_prompt,
]
self.button_edit\
.click(fn=self.put_values_into_components, inputs=[self.edit_name_input], outputs=viewed_components)\
.then(fn=lambda: gr.update(visible=True), inputs=[], outputs=[self.box])
edited_components = [
self.edit_description,
self.select_sd_version,
self.edit_activation_text,
self.slider_preferred_weight,
self.edit_negative_text,
self.edit_notes,
]
self.setup_save_handler(self.button_save, self.save_lora_user_metadata, edited_components)

90
extensions-builtin/Lora/ui_extra_networks_lora.py Normal file
View File

@ -0,0 +1,90 @@
import os
import network
import networks
from modules import shared, ui_extra_networks
from modules.ui_extra_networks import quote_js
from ui_edit_user_metadata import LoraUserMetadataEditor
class ExtraNetworksPageLora(ui_extra_networks.ExtraNetworksPage):
def __init__(self):
super().__init__('Lora')
def refresh(self):
networks.list_available_networks()
def create_item(self, name, index=None, enable_filter=True):
lora_on_disk = networks.available_networks.get(name)
if lora_on_disk is None:
return
path, ext = os.path.splitext(lora_on_disk.filename)
alias = lora_on_disk.get_alias()
search_terms = [self.search_terms_from_path(lora_on_disk.filename)]
if lora_on_disk.hash:
search_terms.append(lora_on_disk.hash)
item = {
"name": name,
"filename": lora_on_disk.filename,
"shorthash": lora_on_disk.shorthash,
"preview": self.find_preview(path) or self.find_embedded_preview(path, name, lora_on_disk.metadata),
"description": self.find_description(path),
"search_terms": search_terms,
"local_preview": f"{path}.{shared.opts.samples_format}",
"metadata": lora_on_disk.metadata,
"sort_keys": {'default': index, **self.get_sort_keys(lora_on_disk.filename)},
"sd_version": lora_on_disk.sd_version.name,
}
self.read_user_metadata(item)
activation_text = item["user_metadata"].get("activation text")
preferred_weight = item["user_metadata"].get("preferred weight", 0.0)
item["prompt"] = quote_js(f"<lora:{alias}:") + " + " + (str(preferred_weight) if preferred_weight else "opts.extra_networks_default_multiplier") + " + " + quote_js(">")
if activation_text:
item["prompt"] += " + " + quote_js(" " + activation_text)
negative_prompt = item["user_metadata"].get("negative text")
item["negative_prompt"] = quote_js("")
if negative_prompt:
item["negative_prompt"] = quote_js('(' + negative_prompt + ':1)')
sd_version = item["user_metadata"].get("sd version")
if sd_version in network.SdVersion.__members__:
item["sd_version"] = sd_version
sd_version = network.SdVersion[sd_version]
else:
sd_version = lora_on_disk.sd_version
if shared.opts.lora_show_all or not enable_filter or not shared.sd_model:
pass
elif sd_version == network.SdVersion.Unknown:
model_version = network.SdVersion.SDXL if shared.sd_model.is_sdxl else network.SdVersion.SD2 if shared.sd_model.is_sd2 else network.SdVersion.SD1
if model_version.name in shared.opts.lora_hide_unknown_for_versions:
return None
elif shared.sd_model.is_sdxl and sd_version != network.SdVersion.SDXL:
return None
elif shared.sd_model.is_sd2 and sd_version != network.SdVersion.SD2:
return None
elif shared.sd_model.is_sd1 and sd_version != network.SdVersion.SD1:
return None
return item
def list_items(self):
# instantiate a list to protect against concurrent modification
names = list(networks.available_networks)
for index, name in enumerate(names):
item = self.create_item(name, index)
if item is not None:
yield item
def allowed_directories_for_previews(self):
return [shared.cmd_opts.lora_dir, shared.cmd_opts.lyco_dir_backcompat]
def create_user_metadata_editor(self, ui, tabname):
return LoraUserMetadataEditor(ui, tabname, self)

6
extensions-builtin/ScuNET/preload.py Normal file
View File

@ -0,0 +1,6 @@
import os
from modules import paths
def preload(parser):
parser.add_argument("--scunet-models-path", type=str, help="Path to directory with ScuNET model file(s).", default=os.path.join(paths.models_path, 'ScuNET'))

74
extensions-builtin/ScuNET/scripts/scunet_model.py Normal file
View File

@ -0,0 +1,74 @@
import sys
import PIL.Image
import modules.upscaler
from modules import devices, errors, modelloader, script_callbacks, shared, upscaler_utils
class UpscalerScuNET(modules.upscaler.Upscaler):
def __init__(self, dirname):
self.name = "ScuNET"
self.model_name = "ScuNET GAN"
self.model_name2 = "ScuNET PSNR"
self.model_url = "https://github.com/cszn/KAIR/releases/download/v1.0/scunet_color_real_gan.pth"
self.model_url2 = "https://github.com/cszn/KAIR/releases/download/v1.0/scunet_color_real_psnr.pth"
self.user_path = dirname
super().__init__()
model_paths = self.find_models(ext_filter=[".pth"])
scalers = []
add_model2 = True
for file in model_paths:
if file.startswith("http"):
name = self.model_name
else:
name = modelloader.friendly_name(file)
if name == self.model_name2 or file == self.model_url2:
add_model2 = False
try:
scaler_data = modules.upscaler.UpscalerData(name, file, self, 4)
scalers.append(scaler_data)
except Exception:
errors.report(f"Error loading ScuNET model: {file}", exc_info=True)
if add_model2:
scaler_data2 = modules.upscaler.UpscalerData(self.model_name2, self.model_url2, self)
scalers.append(scaler_data2)
self.scalers = scalers
def do_upscale(self, img: PIL.Image.Image, selected_file):
devices.torch_gc()
try:
model = self.load_model(selected_file)
except Exception as e:
print(f"ScuNET: Unable to load model from {selected_file}: {e}", file=sys.stderr)
return img
img = upscaler_utils.upscale_2(
img,
model,
tile_size=shared.opts.SCUNET_tile,
tile_overlap=shared.opts.SCUNET_tile_overlap,
scale=1, # ScuNET is a denoising model, not an upscaler
desc='ScuNET',
)
devices.torch_gc()
return img
def load_model(self, path: str):
device = devices.get_device_for('scunet')
if path.startswith("http"):
# TODO: this doesn't use `path` at all?
filename = modelloader.load_file_from_url(self.model_url, model_dir=self.model_download_path, file_name=f"{self.name}.pth")
else:
filename = path
return modelloader.load_spandrel_model(filename, device=device, expected_architecture='SCUNet')
def on_ui_settings():
import gradio as gr
shared.opts.add_option("SCUNET_tile", shared.OptionInfo(256, "Tile size for SCUNET upscalers.", gr.Slider, {"minimum": 0, "maximum": 512, "step": 16}, section=('upscaling', "Upscaling")).info("0 = no tiling"))
shared.opts.add_option("SCUNET_tile_overlap", shared.OptionInfo(8, "Tile overlap for SCUNET upscalers.", gr.Slider, {"minimum": 0, "maximum": 64, "step": 1}, section=('upscaling', "Upscaling")).info("Low values = visible seam"))
script_callbacks.on_ui_settings(on_ui_settings)

6
extensions-builtin/SwinIR/preload.py Normal file
View File

@ -0,0 +1,6 @@
import os
from modules import paths
def preload(parser):
parser.add_argument("--swinir-models-path", type=str, help="Path to directory with SwinIR model file(s).", default=os.path.join(paths.models_path, 'SwinIR'))

95
extensions-builtin/SwinIR/scripts/swinir_model.py Normal file
View File

@ -0,0 +1,95 @@
import logging
import sys
import torch
from PIL import Image
from modules import devices, modelloader, script_callbacks, shared, upscaler_utils
from modules.upscaler import Upscaler, UpscalerData
SWINIR_MODEL_URL = "https://github.com/JingyunLiang/SwinIR/releases/download/v0.0/003_realSR_BSRGAN_DFOWMFC_s64w8_SwinIR-L_x4_GAN.pth"
logger = logging.getLogger(__name__)
class UpscalerSwinIR(Upscaler):
def __init__(self, dirname):
self._cached_model = None # keep the model when SWIN_torch_compile is on to prevent re-compile every runs
self._cached_model_config = None # to clear '_cached_model' when changing model (v1/v2) or settings
self.name = "SwinIR"
self.model_url = SWINIR_MODEL_URL
self.model_name = "SwinIR 4x"
self.user_path = dirname
super().__init__()
scalers = []
model_files = self.find_models(ext_filter=[".pt", ".pth"])
for model in model_files:
if model.startswith("http"):
name = self.model_name
else:
name = modelloader.friendly_name(model)
model_data = UpscalerData(name, model, self)
scalers.append(model_data)
self.scalers = scalers
def do_upscale(self, img: Image.Image, model_file: str) -> Image.Image:
current_config = (model_file, shared.opts.SWIN_tile)
if self._cached_model_config == current_config:
model = self._cached_model
else:
try:
model = self.load_model(model_file)
except Exception as e:
print(f"Failed loading SwinIR model {model_file}: {e}", file=sys.stderr)
return img
self._cached_model = model
self._cached_model_config = current_config
img = upscaler_utils.upscale_2(
img,
model,
tile_size=shared.opts.SWIN_tile,
tile_overlap=shared.opts.SWIN_tile_overlap,
scale=model.scale,
desc="SwinIR",
)
devices.torch_gc()
return img
def load_model(self, path, scale=4):
if path.startswith("http"):
filename = modelloader.load_file_from_url(
url=path,
model_dir=self.model_download_path,
file_name=f"{self.model_name.replace(' ', '_')}.pth",
)
else:
filename = path
model_descriptor = modelloader.load_spandrel_model(
filename,
device=self._get_device(),
prefer_half=(devices.dtype == torch.float16),
expected_architecture="SwinIR",
)
if getattr(shared.opts, 'SWIN_torch_compile', False):
try:
model_descriptor.model.compile()
except Exception:
logger.warning("Failed to compile SwinIR model, fallback to JIT", exc_info=True)
return model_descriptor
def _get_device(self):
return devices.get_device_for('swinir')
def on_ui_settings():
import gradio as gr
shared.opts.add_option("SWIN_tile", shared.OptionInfo(192, "Tile size for all SwinIR.", gr.Slider, {"minimum": 16, "maximum": 512, "step": 16}, section=('upscaling', "Upscaling")))
shared.opts.add_option("SWIN_tile_overlap", shared.OptionInfo(8, "Tile overlap, in pixels for SwinIR. Low values = visible seam.", gr.Slider, {"minimum": 0, "maximum": 48, "step": 1}, section=('upscaling', "Upscaling")))
shared.opts.add_option("SWIN_torch_compile", shared.OptionInfo(False, "Use torch.compile to accelerate SwinIR.", gr.Checkbox, {"interactive": True}, section=('upscaling', "Upscaling")).info("Takes longer on first run"))
script_callbacks.on_ui_settings(on_ui_settings)

995
extensions-builtin/canvas-zoom-and-pan/javascript/zoom.js Normal file
View File

@ -0,0 +1,995 @@
onUiLoaded(async() => {
const elementIDs = {
img2imgTabs: "#mode_img2img .tab-nav",
inpaint: "#img2maskimg",
inpaintSketch: "#inpaint_sketch",
rangeGroup: "#img2img_column_size",
sketch: "#img2img_sketch"
};
const tabNameToElementId = {
"Inpaint sketch": elementIDs.inpaintSketch,
"Inpaint": elementIDs.inpaint,
"Sketch": elementIDs.sketch
};
// Helper functions
// Get active tab
/**
* Waits for an element to be present in the DOM.
*/
const waitForElement = (id) => new Promise(resolve => {
const checkForElement = () => {
const element = document.querySelector(id);
if (element) return resolve(element);
setTimeout(checkForElement, 100);
};
checkForElement();
});
function getActiveTab(elements, all = false) {
if (!elements.img2imgTabs) return null;
const tabs = elements.img2imgTabs.querySelectorAll("button");
if (all) return tabs;
for (let tab of tabs) {
if (tab.classList.contains("selected")) {
return tab;
}
}
}
// Get tab ID
function getTabId(elements) {
const activeTab = getActiveTab(elements);
if (!activeTab) return null;
return tabNameToElementId[activeTab.innerText];
}
// Wait until opts loaded
async function waitForOpts() {
for (; ;) {
if (window.opts && Object.keys(window.opts).length) {
return window.opts;
}
await new Promise(resolve => setTimeout(resolve, 100));
}
}
// Detect whether the element has a horizontal scroll bar
function hasHorizontalScrollbar(element) {
return element.scrollWidth > element.clientWidth;
}
// Function for defining the "Ctrl", "Shift" and "Alt" keys
function isModifierKey(event, key) {
switch (key) {
case "Ctrl":
return event.ctrlKey;
case "Shift":
return event.shiftKey;
case "Alt":
return event.altKey;
default:
return false;
}
}
// Check if hotkey is valid
function isValidHotkey(value) {
const specialKeys = ["Ctrl", "Alt", "Shift", "Disable"];
return (
(typeof value === "string" &&
value.length === 1 &&
/[a-z]/i.test(value)) ||
specialKeys.includes(value)
);
}
// Normalize hotkey
function normalizeHotkey(hotkey) {
return hotkey.length === 1 ? "Key" + hotkey.toUpperCase() : hotkey;
}
// Format hotkey for display
function formatHotkeyForDisplay(hotkey) {
return hotkey.startsWith("Key") ? hotkey.slice(3) : hotkey;
}
// Create hotkey configuration with the provided options
function createHotkeyConfig(defaultHotkeysConfig, hotkeysConfigOpts) {
const result = {}; // Resulting hotkey configuration
const usedKeys = new Set(); // Set of used hotkeys
// Iterate through defaultHotkeysConfig keys
for (const key in defaultHotkeysConfig) {
const userValue = hotkeysConfigOpts[key]; // User-provided hotkey value
const defaultValue = defaultHotkeysConfig[key]; // Default hotkey value
// Apply appropriate value for undefined, boolean, or object userValue
if (
userValue === undefined ||
typeof userValue === "boolean" ||
typeof userValue === "object" ||
userValue === "disable"
) {
result[key] =
userValue === undefined ? defaultValue : userValue;
} else if (isValidHotkey(userValue)) {
const normalizedUserValue = normalizeHotkey(userValue);
// Check for conflicting hotkeys
if (!usedKeys.has(normalizedUserValue)) {
usedKeys.add(normalizedUserValue);
result[key] = normalizedUserValue;
} else {
console.error(
`Hotkey: ${formatHotkeyForDisplay(
userValue
)} for ${key} is repeated and conflicts with another hotkey. The default hotkey is used: ${formatHotkeyForDisplay(
defaultValue
)}`
);
result[key] = defaultValue;
}
} else {
console.error(
`Hotkey: ${formatHotkeyForDisplay(
userValue
)} for ${key} is not valid. The default hotkey is used: ${formatHotkeyForDisplay(
defaultValue
)}`
);
result[key] = defaultValue;
}
}
return result;
}
// Disables functions in the config object based on the provided list of function names
function disableFunctions(config, disabledFunctions) {
// Bind the hasOwnProperty method to the functionMap object to avoid errors
const hasOwnProperty =
Object.prototype.hasOwnProperty.bind(functionMap);
// Loop through the disabledFunctions array and disable the corresponding functions in the config object
disabledFunctions.forEach(funcName => {
if (hasOwnProperty(funcName)) {
const key = functionMap[funcName];
config[key] = "disable";
}
});
// Return the updated config object
return config;
}
/**
* The restoreImgRedMask function displays a red mask around an image to indicate the aspect ratio.
* If the image display property is set to 'none', the mask breaks. To fix this, the function
* temporarily sets the display property to 'block' and then hides the mask again after 300 milliseconds
* to avoid breaking the canvas. Additionally, the function adjusts the mask to work correctly on
* very long images.
*/
function restoreImgRedMask(elements) {
const mainTabId = getTabId(elements);
if (!mainTabId) return;
const mainTab = gradioApp().querySelector(mainTabId);
const img = mainTab.querySelector("img");
const imageARPreview = gradioApp().querySelector("#imageARPreview");
if (!img || !imageARPreview) return;
imageARPreview.style.transform = "";
if (parseFloat(mainTab.style.width) > 865) {
const transformString = mainTab.style.transform;
const scaleMatch = transformString.match(
/scale\(([-+]?[0-9]*\.?[0-9]+)\)/
);
let zoom = 1; // default zoom
if (scaleMatch && scaleMatch[1]) {
zoom = Number(scaleMatch[1]);
}
imageARPreview.style.transformOrigin = "0 0";
imageARPreview.style.transform = `scale(${zoom})`;
}
if (img.style.display !== "none") return;
img.style.display = "block";
setTimeout(() => {
img.style.display = "none";
}, 400);
}
const hotkeysConfigOpts = await waitForOpts();
// Default config
const defaultHotkeysConfig = {
canvas_hotkey_zoom: "Alt",
canvas_hotkey_adjust: "Ctrl",
canvas_hotkey_reset: "KeyR",
canvas_hotkey_fullscreen: "KeyS",
canvas_hotkey_move: "KeyF",
canvas_hotkey_overlap: "KeyO",
canvas_hotkey_shrink_brush: "KeyQ",
canvas_hotkey_grow_brush: "KeyW",
canvas_disabled_functions: [],
canvas_show_tooltip: true,
canvas_auto_expand: true,
canvas_blur_prompt: false,
};
const functionMap = {
"Zoom": "canvas_hotkey_zoom",
"Adjust brush size": "canvas_hotkey_adjust",
"Hotkey shrink brush": "canvas_hotkey_shrink_brush",
"Hotkey enlarge brush": "canvas_hotkey_grow_brush",
"Moving canvas": "canvas_hotkey_move",
"Fullscreen": "canvas_hotkey_fullscreen",
"Reset Zoom": "canvas_hotkey_reset",
"Overlap": "canvas_hotkey_overlap"
};
// Loading the configuration from opts
const preHotkeysConfig = createHotkeyConfig(
defaultHotkeysConfig,
hotkeysConfigOpts
);
// Disable functions that are not needed by the user
const hotkeysConfig = disableFunctions(
preHotkeysConfig,
preHotkeysConfig.canvas_disabled_functions
);
let isMoving = false;
let mouseX, mouseY;
let activeElement;
let interactedWithAltKey = false;
const elements = Object.fromEntries(
Object.keys(elementIDs).map(id => [
id,
gradioApp().querySelector(elementIDs[id])
])
);
const elemData = {};
// Apply functionality to the range inputs. Restore redmask and correct for long images.
const rangeInputs = elements.rangeGroup ?
Array.from(elements.rangeGroup.querySelectorAll("input")) :
[
gradioApp().querySelector("#img2img_width input[type='range']"),
gradioApp().querySelector("#img2img_height input[type='range']")
];
for (const input of rangeInputs) {
input?.addEventListener("input", () => restoreImgRedMask(elements));
}
function applyZoomAndPan(elemId, isExtension = true) {
const targetElement = gradioApp().querySelector(elemId);
if (!targetElement) {
console.log("Element not found", elemId);
return;
}
targetElement.style.transformOrigin = "0 0";
elemData[elemId] = {
zoom: 1,
panX: 0,
panY: 0
};
let fullScreenMode = false;
// Create tooltip
function createTooltip() {
const toolTipElement =
targetElement.querySelector(".image-container");
const tooltip = document.createElement("div");
tooltip.className = "canvas-tooltip";
// Creating an item of information
const info = document.createElement("i");
info.className = "canvas-tooltip-info";
info.textContent = "";
// Create a container for the contents of the tooltip
const tooltipContent = document.createElement("div");
tooltipContent.className = "canvas-tooltip-content";
// Define an array with hotkey information and their actions
const hotkeysInfo = [
{
configKey: "canvas_hotkey_zoom",
action: "Zoom canvas",
keySuffix: " + wheel"
},
{
configKey: "canvas_hotkey_adjust",
action: "Adjust brush size",
keySuffix: " + wheel"
},
{configKey: "canvas_hotkey_reset", action: "Reset zoom"},
{
configKey: "canvas_hotkey_fullscreen",
action: "Fullscreen mode"
},
{configKey: "canvas_hotkey_move", action: "Move canvas"},
{configKey: "canvas_hotkey_overlap", action: "Overlap"}
];
// Create hotkeys array with disabled property based on the config values
const hotkeys = hotkeysInfo.map(info => {
const configValue = hotkeysConfig[info.configKey];
const key = info.keySuffix ?
`${configValue}${info.keySuffix}` :
configValue.charAt(configValue.length - 1);
return {
key,
action: info.action,
disabled: configValue === "disable"
};
});
for (const hotkey of hotkeys) {
if (hotkey.disabled) {
continue;
}
const p = document.createElement("p");
p.innerHTML = `<b>${hotkey.key}</b> - ${hotkey.action}`;
tooltipContent.appendChild(p);
}
// Add information and content elements to the tooltip element
tooltip.appendChild(info);
tooltip.appendChild(tooltipContent);
// Add a hint element to the target element
toolTipElement.appendChild(tooltip);
}
//Show tool tip if setting enable
if (hotkeysConfig.canvas_show_tooltip) {
createTooltip();
}
// In the course of research, it was found that the tag img is very harmful when zooming and creates white canvases. This hack allows you to almost never think about this problem, it has no effect on webui.
function fixCanvas() {
const activeTab = getActiveTab(elements)?.textContent.trim();
if (activeTab && activeTab !== "img2img") {
const img = targetElement.querySelector(`${elemId} img`);
if (img && img.style.display !== "none") {
img.style.display = "none";
img.style.visibility = "hidden";
}
}
}
// Reset the zoom level and pan position of the target element to their initial values
function resetZoom() {
elemData[elemId] = {
zoomLevel: 1,
panX: 0,
panY: 0
};
if (isExtension) {
targetElement.style.overflow = "hidden";
}
targetElement.isZoomed = false;
fixCanvas();
targetElement.style.transform = `scale(${elemData[elemId].zoomLevel}) translate(${elemData[elemId].panX}px, ${elemData[elemId].panY}px)`;
const canvas = gradioApp().querySelector(
`${elemId} canvas[key="interface"]`
);
toggleOverlap("off");
fullScreenMode = false;
const closeBtn = targetElement.querySelector("button[aria-label='Remove Image']");
if (closeBtn) {
closeBtn.addEventListener("click", resetZoom);
}
if (canvas && isExtension) {
const parentElement = targetElement.closest('[id^="component-"]');
if (
canvas &&
parseFloat(canvas.style.width) > parentElement.offsetWidth &&
parseFloat(targetElement.style.width) > parentElement.offsetWidth
) {
fitToElement();
return;
}
}
if (
canvas &&
!isExtension &&
parseFloat(canvas.style.width) > 865 &&
parseFloat(targetElement.style.width) > 865
) {
fitToElement();
return;
}
targetElement.style.width = "";
}
// Toggle the zIndex of the target element between two values, allowing it to overlap or be overlapped by other elements
function toggleOverlap(forced = "") {
const zIndex1 = "0";
const zIndex2 = "998";
targetElement.style.zIndex =
targetElement.style.zIndex !== zIndex2 ? zIndex2 : zIndex1;
if (forced === "off") {
targetElement.style.zIndex = zIndex1;
} else if (forced === "on") {
targetElement.style.zIndex = zIndex2;
}
}
// Adjust the brush size based on the deltaY value from a mouse wheel event
function adjustBrushSize(
elemId,
deltaY,
withoutValue = false,
percentage = 5
) {
const input =
gradioApp().querySelector(
`${elemId} input[aria-label='Brush radius']`
) ||
gradioApp().querySelector(
`${elemId} button[aria-label="Use brush"]`
);
if (input) {
input.click();
if (!withoutValue) {
const maxValue =
parseFloat(input.getAttribute("max")) || 100;
const changeAmount = maxValue * (percentage / 100);
const newValue =
parseFloat(input.value) +
(deltaY > 0 ? -changeAmount : changeAmount);
input.value = Math.min(Math.max(newValue, 0), maxValue);
input.dispatchEvent(new Event("change"));
}
}
}
// Reset zoom when uploading a new image
const fileInput = gradioApp().querySelector(
`${elemId} input[type="file"][accept="image/*"].svelte-116rqfv`
);
fileInput.addEventListener("click", resetZoom);
// Update the zoom level and pan position of the target element based on the values of the zoomLevel, panX and panY variables
function updateZoom(newZoomLevel, mouseX, mouseY) {
newZoomLevel = Math.max(0.1, Math.min(newZoomLevel, 15));
elemData[elemId].panX +=
mouseX - (mouseX * newZoomLevel) / elemData[elemId].zoomLevel;
elemData[elemId].panY +=
mouseY - (mouseY * newZoomLevel) / elemData[elemId].zoomLevel;
targetElement.style.transformOrigin = "0 0";
targetElement.style.transform = `translate(${elemData[elemId].panX}px, ${elemData[elemId].panY}px) scale(${newZoomLevel})`;
toggleOverlap("on");
if (isExtension) {
targetElement.style.overflow = "visible";
}
return newZoomLevel;
}
// Change the zoom level based on user interaction
function changeZoomLevel(operation, e) {
if (isModifierKey(e, hotkeysConfig.canvas_hotkey_zoom)) {
e.preventDefault();
if (hotkeysConfig.canvas_hotkey_zoom === "Alt") {
interactedWithAltKey = true;
}
let zoomPosX, zoomPosY;
let delta = 0.2;
if (elemData[elemId].zoomLevel > 7) {
delta = 0.9;
} else if (elemData[elemId].zoomLevel > 2) {
delta = 0.6;
}
zoomPosX = e.clientX;
zoomPosY = e.clientY;
fullScreenMode = false;
elemData[elemId].zoomLevel = updateZoom(
elemData[elemId].zoomLevel +
(operation === "+" ? delta : -delta),
zoomPosX - targetElement.getBoundingClientRect().left,
zoomPosY - targetElement.getBoundingClientRect().top
);
targetElement.isZoomed = true;
}
}
/**
* This function fits the target element to the screen by calculating
* the required scale and offsets. It also updates the global variables
* zoomLevel, panX, and panY to reflect the new state.
*/
function fitToElement() {
//Reset Zoom
targetElement.style.transform = `translate(${0}px, ${0}px) scale(${1})`;
let parentElement;
if (isExtension) {
parentElement = targetElement.closest('[id^="component-"]');
} else {
parentElement = targetElement.parentElement;
}
// Get element and screen dimensions
const elementWidth = targetElement.offsetWidth;
const elementHeight = targetElement.offsetHeight;
const screenWidth = parentElement.clientWidth;
const screenHeight = parentElement.clientHeight;
// Get element's coordinates relative to the parent element
const elementRect = targetElement.getBoundingClientRect();
const parentRect = parentElement.getBoundingClientRect();
const elementX = elementRect.x - parentRect.x;
// Calculate scale and offsets
const scaleX = screenWidth / elementWidth;
const scaleY = screenHeight / elementHeight;
const scale = Math.min(scaleX, scaleY);
const transformOrigin =
window.getComputedStyle(targetElement).transformOrigin;
const [originX, originY] = transformOrigin.split(" ");
const originXValue = parseFloat(originX);
const originYValue = parseFloat(originY);
const offsetX =
(screenWidth - elementWidth * scale) / 2 -
originXValue * (1 - scale);
const offsetY =
(screenHeight - elementHeight * scale) / 2.5 -
originYValue * (1 - scale);
// Apply scale and offsets to the element
targetElement.style.transform = `translate(${offsetX}px, ${offsetY}px) scale(${scale})`;
// Update global variables
elemData[elemId].zoomLevel = scale;
elemData[elemId].panX = offsetX;
elemData[elemId].panY = offsetY;
fullScreenMode = false;
toggleOverlap("off");
}
/**
* This function fits the target element to the screen by calculating
* the required scale and offsets. It also updates the global variables
* zoomLevel, panX, and panY to reflect the new state.
*/
// Fullscreen mode
function fitToScreen() {
const canvas = gradioApp().querySelector(
`${elemId} canvas[key="interface"]`
);
if (!canvas) return;
if (canvas.offsetWidth > 862 || isExtension) {
targetElement.style.width = (canvas.offsetWidth + 2) + "px";
}
if (isExtension) {
targetElement.style.overflow = "visible";
}
if (fullScreenMode) {
resetZoom();
fullScreenMode = false;
return;
}
//Reset Zoom
targetElement.style.transform = `translate(${0}px, ${0}px) scale(${1})`;
// Get scrollbar width to right-align the image
const scrollbarWidth =
window.innerWidth - document.documentElement.clientWidth;
// Get element and screen dimensions
const elementWidth = targetElement.offsetWidth;
const elementHeight = targetElement.offsetHeight;
const screenWidth = window.innerWidth - scrollbarWidth;
const screenHeight = window.innerHeight;
// Get element's coordinates relative to the page
const elementRect = targetElement.getBoundingClientRect();
const elementY = elementRect.y;
const elementX = elementRect.x;
// Calculate scale and offsets
const scaleX = screenWidth / elementWidth;
const scaleY = screenHeight / elementHeight;
const scale = Math.min(scaleX, scaleY);
// Get the current transformOrigin
const computedStyle = window.getComputedStyle(targetElement);
const transformOrigin = computedStyle.transformOrigin;
const [originX, originY] = transformOrigin.split(" ");
const originXValue = parseFloat(originX);
const originYValue = parseFloat(originY);
// Calculate offsets with respect to the transformOrigin
const offsetX =
(screenWidth - elementWidth * scale) / 2 -
elementX -
originXValue * (1 - scale);
const offsetY =
(screenHeight - elementHeight * scale) / 2 -
elementY -
originYValue * (1 - scale);
// Apply scale and offsets to the element
targetElement.style.transform = `translate(${offsetX}px, ${offsetY}px) scale(${scale})`;
// Update global variables
elemData[elemId].zoomLevel = scale;
elemData[elemId].panX = offsetX;
elemData[elemId].panY = offsetY;
fullScreenMode = true;
toggleOverlap("on");
}
// Handle keydown events
function handleKeyDown(event) {
// Disable key locks to make pasting from the buffer work correctly
if ((event.ctrlKey && event.code === 'KeyV') || (event.ctrlKey && event.code === 'KeyC') || event.code === "F5") {
return;
}
// before activating shortcut, ensure user is not actively typing in an input field
if (!hotkeysConfig.canvas_blur_prompt) {
if (event.target.nodeName === 'TEXTAREA' || event.target.nodeName === 'INPUT') {
return;
}
}
const hotkeyActions = {
[hotkeysConfig.canvas_hotkey_reset]: resetZoom,
[hotkeysConfig.canvas_hotkey_overlap]: toggleOverlap,
[hotkeysConfig.canvas_hotkey_fullscreen]: fitToScreen,
[hotkeysConfig.canvas_hotkey_shrink_brush]: () => adjustBrushSize(elemId, 10),
[hotkeysConfig.canvas_hotkey_grow_brush]: () => adjustBrushSize(elemId, -10)
};
const action = hotkeyActions[event.code];
if (action) {
event.preventDefault();
action(event);
}
if (
isModifierKey(event, hotkeysConfig.canvas_hotkey_zoom) ||
isModifierKey(event, hotkeysConfig.canvas_hotkey_adjust)
) {
event.preventDefault();
}
}
// Get Mouse position
function getMousePosition(e) {
mouseX = e.offsetX;
mouseY = e.offsetY;
}
// Simulation of the function to put a long image into the screen.
// We detect if an image has a scroll bar or not, make a fullscreen to reveal the image, then reduce it to fit into the element.
// We hide the image and show it to the user when it is ready.
targetElement.isExpanded = false;
function autoExpand() {
const canvas = document.querySelector(`${elemId} canvas[key="interface"]`);
if (canvas) {
if (hasHorizontalScrollbar(targetElement) && targetElement.isExpanded === false) {
targetElement.style.visibility = "hidden";
setTimeout(() => {
fitToScreen();
resetZoom();
targetElement.style.visibility = "visible";
targetElement.isExpanded = true;
}, 10);
}
}
}
targetElement.addEventListener("mousemove", getMousePosition);
//observers
// Creating an observer with a callback function to handle DOM changes
const observer = new MutationObserver((mutationsList, observer) => {
for (let mutation of mutationsList) {
// If the style attribute of the canvas has changed, by observation it happens only when the picture changes
if (mutation.type === 'attributes' && mutation.attributeName === 'style' &&
mutation.target.tagName.toLowerCase() === 'canvas') {
targetElement.isExpanded = false;
setTimeout(resetZoom, 10);
}
}
});
// Apply auto expand if enabled
if (hotkeysConfig.canvas_auto_expand) {
targetElement.addEventListener("mousemove", autoExpand);
// Set up an observer to track attribute changes
observer.observe(targetElement, {attributes: true, childList: true, subtree: true});
}
// Handle events only inside the targetElement
let isKeyDownHandlerAttached = false;
function handleMouseMove() {
if (!isKeyDownHandlerAttached) {
document.addEventListener("keydown", handleKeyDown);
isKeyDownHandlerAttached = true;
activeElement = elemId;
}
}
function handleMouseLeave() {
if (isKeyDownHandlerAttached) {
document.removeEventListener("keydown", handleKeyDown);
isKeyDownHandlerAttached = false;
activeElement = null;
}
}
// Add mouse event handlers
targetElement.addEventListener("mousemove", handleMouseMove);
targetElement.addEventListener("mouseleave", handleMouseLeave);
// Reset zoom when click on another tab
if (elements.img2imgTabs) {
elements.img2imgTabs.addEventListener("click", resetZoom);
elements.img2imgTabs.addEventListener("click", () => {
// targetElement.style.width = "";
if (parseInt(targetElement.style.width) > 865) {
setTimeout(fitToElement, 0);
}
});
}
targetElement.addEventListener("wheel", e => {
// change zoom level
const operation = (e.deltaY || -e.wheelDelta) > 0 ? "-" : "+";
changeZoomLevel(operation, e);
// Handle brush size adjustment with ctrl key pressed
if (isModifierKey(e, hotkeysConfig.canvas_hotkey_adjust)) {
e.preventDefault();
if (hotkeysConfig.canvas_hotkey_adjust === "Alt") {
interactedWithAltKey = true;
}
// Increase or decrease brush size based on scroll direction
adjustBrushSize(elemId, e.deltaY);
}
});
// Handle the move event for pan functionality. Updates the panX and panY variables and applies the new transform to the target element.
function handleMoveKeyDown(e) {
// Disable key locks to make pasting from the buffer work correctly
if ((e.ctrlKey && e.code === 'KeyV') || (e.ctrlKey && event.code === 'KeyC') || e.code === "F5") {
return;
}
// before activating shortcut, ensure user is not actively typing in an input field
if (!hotkeysConfig.canvas_blur_prompt) {
if (e.target.nodeName === 'TEXTAREA' || e.target.nodeName === 'INPUT') {
return;
}
}
if (e.code === hotkeysConfig.canvas_hotkey_move) {
if (!e.ctrlKey && !e.metaKey && isKeyDownHandlerAttached) {
e.preventDefault();
document.activeElement.blur();
isMoving = true;
}
}
}
function handleMoveKeyUp(e) {
if (e.code === hotkeysConfig.canvas_hotkey_move) {
isMoving = false;
}
}
document.addEventListener("keydown", handleMoveKeyDown);
document.addEventListener("keyup", handleMoveKeyUp);
// Prevent firefox from opening main menu when alt is used as a hotkey for zoom or brush size
function handleAltKeyUp(e) {
if (e.key !== "Alt" || !interactedWithAltKey) {
return;
}
e.preventDefault();
interactedWithAltKey = false;
}
document.addEventListener("keyup", handleAltKeyUp);
// Detect zoom level and update the pan speed.
function updatePanPosition(movementX, movementY) {
let panSpeed = 2;
if (elemData[elemId].zoomLevel > 8) {
panSpeed = 3.5;
}
elemData[elemId].panX += movementX * panSpeed;
elemData[elemId].panY += movementY * panSpeed;
// Delayed redraw of an element
requestAnimationFrame(() => {
targetElement.style.transform = `translate(${elemData[elemId].panX}px, ${elemData[elemId].panY}px) scale(${elemData[elemId].zoomLevel})`;
toggleOverlap("on");
});
}
function handleMoveByKey(e) {
if (isMoving && elemId === activeElement) {
updatePanPosition(e.movementX, e.movementY);
targetElement.style.pointerEvents = "none";
if (isExtension) {
targetElement.style.overflow = "visible";
}
} else {
targetElement.style.pointerEvents = "auto";
}
}
// Prevents sticking to the mouse
window.onblur = function() {
isMoving = false;
};
// Checks for extension
function checkForOutBox() {
const parentElement = targetElement.closest('[id^="component-"]');
if (parentElement.offsetWidth < targetElement.offsetWidth && !targetElement.isExpanded) {
resetZoom();
targetElement.isExpanded = true;
}
if (parentElement.offsetWidth < targetElement.offsetWidth && elemData[elemId].zoomLevel == 1) {
resetZoom();
}
if (parentElement.offsetWidth < targetElement.offsetWidth && targetElement.offsetWidth * elemData[elemId].zoomLevel > parentElement.offsetWidth && elemData[elemId].zoomLevel < 1 && !targetElement.isZoomed) {
resetZoom();
}
}
if (isExtension) {
targetElement.addEventListener("mousemove", checkForOutBox);
}
window.addEventListener('resize', (e) => {
resetZoom();
if (isExtension) {
targetElement.isExpanded = false;
targetElement.isZoomed = false;
}
});
gradioApp().addEventListener("mousemove", handleMoveByKey);
}
applyZoomAndPan(elementIDs.sketch, false);
applyZoomAndPan(elementIDs.inpaint, false);
applyZoomAndPan(elementIDs.inpaintSketch, false);
// Make the function global so that other extensions can take advantage of this solution
const applyZoomAndPanIntegration = async(id, elementIDs) => {
const mainEl = document.querySelector(id);
if (id.toLocaleLowerCase() === "none") {
for (const elementID of elementIDs) {
const el = await waitForElement(elementID);
if (!el) break;
applyZoomAndPan(elementID);
}
return;
}
if (!mainEl) return;
mainEl.addEventListener("click", async() => {
for (const elementID of elementIDs) {
const el = await waitForElement(elementID);
if (!el) break;
applyZoomAndPan(elementID);
}
}, {once: true});
};
window.applyZoomAndPan = applyZoomAndPan; // Only 1 elements, argument elementID, for example applyZoomAndPan("#txt2img_controlnet_ControlNet_input_image")
window.applyZoomAndPanIntegration = applyZoomAndPanIntegration; // for any extension
/*
The function `applyZoomAndPanIntegration` takes two arguments:
1. `id`: A string identifier for the element to which zoom and pan functionality will be applied on click.
If the `id` value is "none", the functionality will be applied to all elements specified in the second argument without a click event.
2. `elementIDs`: An array of string identifiers for elements. Zoom and pan functionality will be applied to each of these elements on click of the element specified by the first argument.
If "none" is specified in the first argument, the functionality will be applied to each of these elements without a click event.
Example usage:
applyZoomAndPanIntegration("#txt2img_controlnet", ["#txt2img_controlnet_ControlNet_input_image"]);
In this example, zoom and pan functionality will be applied to the element with the identifier "txt2img_controlnet_ControlNet_input_image" upon clicking the element with the identifier "txt2img_controlnet".
*/
// More examples
// Add integration with ControlNet txt2img One TAB
// applyZoomAndPanIntegration("#txt2img_controlnet", ["#txt2img_controlnet_ControlNet_input_image"]);
// Add integration with ControlNet txt2img Tabs
// applyZoomAndPanIntegration("#txt2img_controlnet",Array.from({ length: 10 }, (_, i) => `#txt2img_controlnet_ControlNet-${i}_input_image`));
// Add integration with Inpaint Anything
// applyZoomAndPanIntegration("None", ["#ia_sam_image", "#ia_sel_mask"]);
});

17
extensions-builtin/canvas-zoom-and-pan/scripts/hotkey_config.py Normal file
View File

@ -0,0 +1,17 @@
import gradio as gr
from modules import shared
shared.options_templates.update(shared.options_section(('canvas_hotkey', "Canvas Hotkeys"), {
"canvas_hotkey_zoom": shared.OptionInfo("Alt", "Zoom canvas", gr.Radio, {"choices": ["Shift","Ctrl", "Alt"]}).info("If you choose 'Shift' you cannot scroll horizontally, 'Alt' can cause a little trouble in firefox"),
"canvas_hotkey_adjust": shared.OptionInfo("Ctrl", "Adjust brush size", gr.Radio, {"choices": ["Shift","Ctrl", "Alt"]}).info("If you choose 'Shift' you cannot scroll horizontally, 'Alt' can cause a little trouble in firefox"),
"canvas_hotkey_shrink_brush": shared.OptionInfo("Q", "Shrink the brush size"),
"canvas_hotkey_grow_brush": shared.OptionInfo("W", "Enlarge the brush size"),
"canvas_hotkey_move": shared.OptionInfo("F", "Moving the canvas").info("To work correctly in firefox, turn off 'Automatically search the page text when typing' in the browser settings"),
"canvas_hotkey_fullscreen": shared.OptionInfo("S", "Fullscreen Mode, maximizes the picture so that it fits into the screen and stretches it to its full width "),
"canvas_hotkey_reset": shared.OptionInfo("R", "Reset zoom and canvas position"),
"canvas_hotkey_overlap": shared.OptionInfo("O", "Toggle overlap").info("Technical button, needed for testing"),
"canvas_show_tooltip": shared.OptionInfo(True, "Enable tooltip on the canvas"),
"canvas_auto_expand": shared.OptionInfo(True, "Automatically expands an image that does not fit completely in the canvas area, similar to manually pressing the S and R buttons"),
"canvas_blur_prompt": shared.OptionInfo(False, "Take the focus off the prompt when working with a canvas"),
"canvas_disabled_functions": shared.OptionInfo(["Overlap"], "Disable function that you don't use", gr.CheckboxGroup, {"choices": ["Zoom","Adjust brush size","Hotkey enlarge brush","Hotkey shrink brush","Moving canvas","Fullscreen","Reset Zoom","Overlap"]}),
}))

66
extensions-builtin/canvas-zoom-and-pan/style.css Normal file
View File

@ -0,0 +1,66 @@
.canvas-tooltip-info {
position: absolute;
top: 10px;
left: 10px;
cursor: help;
background-color: rgba(0, 0, 0, 0.3);
width: 20px;
height: 20px;
border-radius: 50%;
display: flex;
align-items: center;
justify-content: center;
flex-direction: column;
z-index: 100;
}
.canvas-tooltip-info::after {
content: '';
display: block;
width: 2px;
height: 7px;
background-color: white;
margin-top: 2px;
}
.canvas-tooltip-info::before {
content: '';
display: block;
width: 2px;
height: 2px;
background-color: white;
}
.canvas-tooltip-content {
display: none;
background-color: #f9f9f9;
color: #333;
border: 1px solid #ddd;
padding: 15px;
position: absolute;
top: 40px;
left: 10px;
width: 250px;
font-size: 16px;
opacity: 0;
border-radius: 8px;
box-shadow: 0px 8px 16px 0px rgba(0,0,0,0.2);
z-index: 100;
}
.canvas-tooltip:hover .canvas-tooltip-content {
display: block;
animation: fadeIn 0.5s;
opacity: 1;
}
@keyframes fadeIn {
from {opacity: 0;}
to {opacity: 1;}
}
.styler {
overflow:inherit !important;
}

82
extensions-builtin/extra-options-section/scripts/extra_options_section.py Normal file
View File

@ -0,0 +1,82 @@
import math
import gradio as gr
from modules import scripts, shared, ui_components, ui_settings, infotext_utils, errors
from modules.ui_components import FormColumn
class ExtraOptionsSection(scripts.Script):
section = "extra_options"
def __init__(self):
self.comps = None
self.setting_names = None
def title(self):
return "Extra options"
def show(self, is_img2img):
return scripts.AlwaysVisible
def ui(self, is_img2img):
self.comps = []
self.setting_names = []
self.infotext_fields = []
extra_options = shared.opts.extra_options_img2img if is_img2img else shared.opts.extra_options_txt2img
elem_id_tabname = "extra_options_" + ("img2img" if is_img2img else "txt2img")
mapping = {k: v for v, k in infotext_utils.infotext_to_setting_name_mapping}
with gr.Blocks() as interface:
with gr.Accordion("Options", open=False, elem_id=elem_id_tabname) if shared.opts.extra_options_accordion and extra_options else gr.Group(elem_id=elem_id_tabname):
row_count = math.ceil(len(extra_options) / shared.opts.extra_options_cols)
for row in range(row_count):
with gr.Row():
for col in range(shared.opts.extra_options_cols):
index = row * shared.opts.extra_options_cols + col
if index >= len(extra_options):
break
setting_name = extra_options[index]
with FormColumn():
try:
comp = ui_settings.create_setting_component(setting_name)
except KeyError:
errors.report(f"Can't add extra options for {setting_name} in ui")
continue
self.comps.append(comp)
self.setting_names.append(setting_name)
setting_infotext_name = mapping.get(setting_name)
if setting_infotext_name is not None:
self.infotext_fields.append((comp, setting_infotext_name))
def get_settings_values():
res = [ui_settings.get_value_for_setting(key) for key in self.setting_names]
return res[0] if len(res) == 1 else res
interface.load(fn=get_settings_values, inputs=[], outputs=self.comps, queue=False, show_progress=False)
return self.comps
def before_process(self, p, *args):
for name, value in zip(self.setting_names, args):
if name not in p.override_settings:
p.override_settings[name] = value
shared.options_templates.update(shared.options_section(('settings_in_ui', "Settings in UI", "ui"), {
"settings_in_ui": shared.OptionHTML("""
This page allows you to add some settings to the main interface of txt2img and img2img tabs.
"""),
"extra_options_txt2img": shared.OptionInfo([], "Settings for txt2img", ui_components.DropdownMulti, lambda: {"choices": list(shared.opts.data_labels.keys())}).js("info", "settingsHintsShowQuicksettings").info("setting entries that also appear in txt2img interfaces").needs_reload_ui(),
"extra_options_img2img": shared.OptionInfo([], "Settings for img2img", ui_components.DropdownMulti, lambda: {"choices": list(shared.opts.data_labels.keys())}).js("info", "settingsHintsShowQuicksettings").info("setting entries that also appear in img2img interfaces").needs_reload_ui(),
"extra_options_cols": shared.OptionInfo(1, "Number of columns for added settings", gr.Slider, {"step": 1, "minimum": 1, "maximum": 20}).info("displayed amount will depend on the actual browser window width").needs_reload_ui(),
"extra_options_accordion": shared.OptionInfo(False, "Place added settings into an accordion").needs_reload_ui()
}))

351
extensions-builtin/hypertile/hypertile.py Normal file
View File

@ -0,0 +1,351 @@
"""
Hypertile module for splitting attention layers in SD-1.5 U-Net and SD-1.5 VAE
Warn: The patch works well only if the input image has a width and height that are multiples of 128
Original author: @tfernd Github: https://github.com/tfernd/HyperTile
"""
from __future__ import annotations
from dataclasses import dataclass
from typing import Callable
from functools import wraps, cache
import math
import torch.nn as nn
import random
from einops import rearrange
@dataclass
class HypertileParams:
depth = 0
layer_name = ""
tile_size: int = 0
swap_size: int = 0
aspect_ratio: float = 1.0
forward = None
enabled = False
# TODO add SD-XL layers
DEPTH_LAYERS = {
0: [
# SD 1.5 U-Net (diffusers)
"down_blocks.0.attentions.0.transformer_blocks.0.attn1",
"down_blocks.0.attentions.1.transformer_blocks.0.attn1",
"up_blocks.3.attentions.0.transformer_blocks.0.attn1",
"up_blocks.3.attentions.1.transformer_blocks.0.attn1",
"up_blocks.3.attentions.2.transformer_blocks.0.attn1",
# SD 1.5 U-Net (ldm)
"input_blocks.1.1.transformer_blocks.0.attn1",
"input_blocks.2.1.transformer_blocks.0.attn1",
"output_blocks.9.1.transformer_blocks.0.attn1",
"output_blocks.10.1.transformer_blocks.0.attn1",
"output_blocks.11.1.transformer_blocks.0.attn1",
# SD 1.5 VAE
"decoder.mid_block.attentions.0",
"decoder.mid.attn_1",
],
1: [
# SD 1.5 U-Net (diffusers)
"down_blocks.1.attentions.0.transformer_blocks.0.attn1",
"down_blocks.1.attentions.1.transformer_blocks.0.attn1",
"up_blocks.2.attentions.0.transformer_blocks.0.attn1",
"up_blocks.2.attentions.1.transformer_blocks.0.attn1",
"up_blocks.2.attentions.2.transformer_blocks.0.attn1",
# SD 1.5 U-Net (ldm)
"input_blocks.4.1.transformer_blocks.0.attn1",
"input_blocks.5.1.transformer_blocks.0.attn1",
"output_blocks.6.1.transformer_blocks.0.attn1",
"output_blocks.7.1.transformer_blocks.0.attn1",
"output_blocks.8.1.transformer_blocks.0.attn1",
],
2: [
# SD 1.5 U-Net (diffusers)
"down_blocks.2.attentions.0.transformer_blocks.0.attn1",
"down_blocks.2.attentions.1.transformer_blocks.0.attn1",
"up_blocks.1.attentions.0.transformer_blocks.0.attn1",
"up_blocks.1.attentions.1.transformer_blocks.0.attn1",
"up_blocks.1.attentions.2.transformer_blocks.0.attn1",
# SD 1.5 U-Net (ldm)
"input_blocks.7.1.transformer_blocks.0.attn1",
"input_blocks.8.1.transformer_blocks.0.attn1",
"output_blocks.3.1.transformer_blocks.0.attn1",
"output_blocks.4.1.transformer_blocks.0.attn1",
"output_blocks.5.1.transformer_blocks.0.attn1",
],
3: [
# SD 1.5 U-Net (diffusers)
"mid_block.attentions.0.transformer_blocks.0.attn1",
# SD 1.5 U-Net (ldm)
"middle_block.1.transformer_blocks.0.attn1",
],
}
# XL layers, thanks for GitHub@gel-crabs for the help
DEPTH_LAYERS_XL = {
0: [
# SD 1.5 U-Net (diffusers)
"down_blocks.0.attentions.0.transformer_blocks.0.attn1",
"down_blocks.0.attentions.1.transformer_blocks.0.attn1",
"up_blocks.3.attentions.0.transformer_blocks.0.attn1",
"up_blocks.3.attentions.1.transformer_blocks.0.attn1",
"up_blocks.3.attentions.2.transformer_blocks.0.attn1",
# SD 1.5 U-Net (ldm)
"input_blocks.4.1.transformer_blocks.0.attn1",
"input_blocks.5.1.transformer_blocks.0.attn1",
"output_blocks.3.1.transformer_blocks.0.attn1",
"output_blocks.4.1.transformer_blocks.0.attn1",
"output_blocks.5.1.transformer_blocks.0.attn1",
# SD 1.5 VAE
"decoder.mid_block.attentions.0",
"decoder.mid.attn_1",
],
1: [
# SD 1.5 U-Net (diffusers)
#"down_blocks.1.attentions.0.transformer_blocks.0.attn1",
#"down_blocks.1.attentions.1.transformer_blocks.0.attn1",
#"up_blocks.2.attentions.0.transformer_blocks.0.attn1",
#"up_blocks.2.attentions.1.transformer_blocks.0.attn1",
#"up_blocks.2.attentions.2.transformer_blocks.0.attn1",
# SD 1.5 U-Net (ldm)
"input_blocks.4.1.transformer_blocks.1.attn1",
"input_blocks.5.1.transformer_blocks.1.attn1",
"output_blocks.3.1.transformer_blocks.1.attn1",
"output_blocks.4.1.transformer_blocks.1.attn1",
"output_blocks.5.1.transformer_blocks.1.attn1",
"input_blocks.7.1.transformer_blocks.0.attn1",
"input_blocks.8.1.transformer_blocks.0.attn1",
"output_blocks.0.1.transformer_blocks.0.attn1",
"output_blocks.1.1.transformer_blocks.0.attn1",
"output_blocks.2.1.transformer_blocks.0.attn1",
"input_blocks.7.1.transformer_blocks.1.attn1",
"input_blocks.8.1.transformer_blocks.1.attn1",
"output_blocks.0.1.transformer_blocks.1.attn1",
"output_blocks.1.1.transformer_blocks.1.attn1",
"output_blocks.2.1.transformer_blocks.1.attn1",
"input_blocks.7.1.transformer_blocks.2.attn1",
"input_blocks.8.1.transformer_blocks.2.attn1",
"output_blocks.0.1.transformer_blocks.2.attn1",
"output_blocks.1.1.transformer_blocks.2.attn1",
"output_blocks.2.1.transformer_blocks.2.attn1",
"input_blocks.7.1.transformer_blocks.3.attn1",
"input_blocks.8.1.transformer_blocks.3.attn1",
"output_blocks.0.1.transformer_blocks.3.attn1",
"output_blocks.1.1.transformer_blocks.3.attn1",
"output_blocks.2.1.transformer_blocks.3.attn1",
"input_blocks.7.1.transformer_blocks.4.attn1",
"input_blocks.8.1.transformer_blocks.4.attn1",
"output_blocks.0.1.transformer_blocks.4.attn1",
"output_blocks.1.1.transformer_blocks.4.attn1",
"output_blocks.2.1.transformer_blocks.4.attn1",
"input_blocks.7.1.transformer_blocks.5.attn1",
"input_blocks.8.1.transformer_blocks.5.attn1",
"output_blocks.0.1.transformer_blocks.5.attn1",
"output_blocks.1.1.transformer_blocks.5.attn1",
"output_blocks.2.1.transformer_blocks.5.attn1",
"input_blocks.7.1.transformer_blocks.6.attn1",
"input_blocks.8.1.transformer_blocks.6.attn1",
"output_blocks.0.1.transformer_blocks.6.attn1",
"output_blocks.1.1.transformer_blocks.6.attn1",
"output_blocks.2.1.transformer_blocks.6.attn1",
"input_blocks.7.1.transformer_blocks.7.attn1",
"input_blocks.8.1.transformer_blocks.7.attn1",
"output_blocks.0.1.transformer_blocks.7.attn1",
"output_blocks.1.1.transformer_blocks.7.attn1",
"output_blocks.2.1.transformer_blocks.7.attn1",
"input_blocks.7.1.transformer_blocks.8.attn1",
"input_blocks.8.1.transformer_blocks.8.attn1",
"output_blocks.0.1.transformer_blocks.8.attn1",
"output_blocks.1.1.transformer_blocks.8.attn1",
"output_blocks.2.1.transformer_blocks.8.attn1",
"input_blocks.7.1.transformer_blocks.9.attn1",
"input_blocks.8.1.transformer_blocks.9.attn1",
"output_blocks.0.1.transformer_blocks.9.attn1",
"output_blocks.1.1.transformer_blocks.9.attn1",
"output_blocks.2.1.transformer_blocks.9.attn1",
],
2: [
# SD 1.5 U-Net (diffusers)
"mid_block.attentions.0.transformer_blocks.0.attn1",
# SD 1.5 U-Net (ldm)
"middle_block.1.transformer_blocks.0.attn1",
"middle_block.1.transformer_blocks.1.attn1",
"middle_block.1.transformer_blocks.2.attn1",
"middle_block.1.transformer_blocks.3.attn1",
"middle_block.1.transformer_blocks.4.attn1",
"middle_block.1.transformer_blocks.5.attn1",
"middle_block.1.transformer_blocks.6.attn1",
"middle_block.1.transformer_blocks.7.attn1",
"middle_block.1.transformer_blocks.8.attn1",
"middle_block.1.transformer_blocks.9.attn1",
],
3 : [] # TODO - separate layers for SD-XL
}
RNG_INSTANCE = random.Random()
@cache
def get_divisors(value: int, min_value: int, /, max_options: int = 1) -> list[int]:
"""
Returns divisors of value that
x * min_value <= value
in big -> small order, amount of divisors is limited by max_options
"""
max_options = max(1, max_options) # at least 1 option should be returned
min_value = min(min_value, value)
divisors = [i for i in range(min_value, value + 1) if value % i == 0] # divisors in small -> big order
ns = [value // i for i in divisors[:max_options]] # has at least 1 element # big -> small order
return ns
def random_divisor(value: int, min_value: int, /, max_options: int = 1) -> int:
"""
Returns a random divisor of value that
x * min_value <= value
if max_options is 1, the behavior is deterministic
"""
ns = get_divisors(value, min_value, max_options=max_options) # get cached divisors
idx = RNG_INSTANCE.randint(0, len(ns) - 1)
return ns[idx]
def set_hypertile_seed(seed: int) -> None:
RNG_INSTANCE.seed(seed)
@cache
def largest_tile_size_available(width: int, height: int) -> int:
"""
Calculates the largest tile size available for a given width and height
Tile size is always a power of 2
"""
gcd = math.gcd(width, height)
largest_tile_size_available = 1
while gcd % (largest_tile_size_available * 2) == 0:
largest_tile_size_available *= 2
return largest_tile_size_available
def iterative_closest_divisors(hw:int, aspect_ratio:float) -> tuple[int, int]:
"""
Finds h and w such that h*w = hw and h/w = aspect_ratio
We check all possible divisors of hw and return the closest to the aspect ratio
"""
divisors = [i for i in range(2, hw + 1) if hw % i == 0] # all divisors of hw
pairs = [(i, hw // i) for i in divisors] # all pairs of divisors of hw
ratios = [w/h for h, w in pairs] # all ratios of pairs of divisors of hw
closest_ratio = min(ratios, key=lambda x: abs(x - aspect_ratio)) # closest ratio to aspect_ratio
closest_pair = pairs[ratios.index(closest_ratio)] # closest pair of divisors to aspect_ratio
return closest_pair
@cache
def find_hw_candidates(hw:int, aspect_ratio:float) -> tuple[int, int]:
"""
Finds h and w such that h*w = hw and h/w = aspect_ratio
"""
h, w = round(math.sqrt(hw * aspect_ratio)), round(math.sqrt(hw / aspect_ratio))
# find h and w such that h*w = hw and h/w = aspect_ratio
if h * w != hw:
w_candidate = hw / h
# check if w is an integer
if not w_candidate.is_integer():
h_candidate = hw / w
# check if h is an integer
if not h_candidate.is_integer():
return iterative_closest_divisors(hw, aspect_ratio)
else:
h = int(h_candidate)
else:
w = int(w_candidate)
return h, w
def self_attn_forward(params: HypertileParams, scale_depth=True) -> Callable:
@wraps(params.forward)
def wrapper(*args, **kwargs):
if not params.enabled:
return params.forward(*args, **kwargs)
latent_tile_size = max(128, params.tile_size) // 8
x = args[0]
# VAE
if x.ndim == 4:
b, c, h, w = x.shape
nh = random_divisor(h, latent_tile_size, params.swap_size)
nw = random_divisor(w, latent_tile_size, params.swap_size)
if nh * nw > 1:
x = rearrange(x, "b c (nh h) (nw w) -> (b nh nw) c h w", nh=nh, nw=nw) # split into nh * nw tiles
out = params.forward(x, *args[1:], **kwargs)
if nh * nw > 1:
out = rearrange(out, "(b nh nw) c h w -> b c (nh h) (nw w)", nh=nh, nw=nw)
# U-Net
else:
hw: int = x.size(1)
h, w = find_hw_candidates(hw, params.aspect_ratio)
assert h * w == hw, f"Invalid aspect ratio {params.aspect_ratio} for input of shape {x.shape}, hw={hw}, h={h}, w={w}"
factor = 2 ** params.depth if scale_depth else 1
nh = random_divisor(h, latent_tile_size * factor, params.swap_size)
nw = random_divisor(w, latent_tile_size * factor, params.swap_size)
if nh * nw > 1:
x = rearrange(x, "b (nh h nw w) c -> (b nh nw) (h w) c", h=h // nh, w=w // nw, nh=nh, nw=nw)
out = params.forward(x, *args[1:], **kwargs)
if nh * nw > 1:
out = rearrange(out, "(b nh nw) hw c -> b nh nw hw c", nh=nh, nw=nw)
out = rearrange(out, "b nh nw (h w) c -> b (nh h nw w) c", h=h // nh, w=w // nw)
return out
return wrapper
def hypertile_hook_model(model: nn.Module, width, height, *, enable=False, tile_size_max=128, swap_size=1, max_depth=3, is_sdxl=False):
hypertile_layers = getattr(model, "__webui_hypertile_layers", None)
if hypertile_layers is None:
if not enable:
return
hypertile_layers = {}
layers = DEPTH_LAYERS_XL if is_sdxl else DEPTH_LAYERS
for depth in range(4):
for layer_name, module in model.named_modules():
if any(layer_name.endswith(try_name) for try_name in layers[depth]):
params = HypertileParams()
module.__webui_hypertile_params = params
params.forward = module.forward
params.depth = depth
params.layer_name = layer_name
module.forward = self_attn_forward(params)
hypertile_layers[layer_name] = 1
model.__webui_hypertile_layers = hypertile_layers
aspect_ratio = width / height
tile_size = min(largest_tile_size_available(width, height), tile_size_max)
for layer_name, module in model.named_modules():
if layer_name in hypertile_layers:
params = module.__webui_hypertile_params
params.tile_size = tile_size
params.swap_size = swap_size
params.aspect_ratio = aspect_ratio
params.enabled = enable and params.depth <= max_depth

122
extensions-builtin/hypertile/scripts/hypertile_script.py Normal file
View File

@ -0,0 +1,122 @@
import hypertile
from modules import scripts, script_callbacks, shared
class ScriptHypertile(scripts.Script):
name = "Hypertile"
def title(self):
return self.name
def show(self, is_img2img):
return scripts.AlwaysVisible
def process(self, p, *args):
hypertile.set_hypertile_seed(p.all_seeds[0])
configure_hypertile(p.width, p.height, enable_unet=shared.opts.hypertile_enable_unet)
self.add_infotext(p)
def before_hr(self, p, *args):
enable = shared.opts.hypertile_enable_unet_secondpass or shared.opts.hypertile_enable_unet
# exclusive hypertile seed for the second pass
if enable:
hypertile.set_hypertile_seed(p.all_seeds[0])
configure_hypertile(p.hr_upscale_to_x, p.hr_upscale_to_y, enable_unet=enable)
if enable and not shared.opts.hypertile_enable_unet:
p.extra_generation_params["Hypertile U-Net second pass"] = True
self.add_infotext(p, add_unet_params=True)
def add_infotext(self, p, add_unet_params=False):
def option(name):
value = getattr(shared.opts, name)
default_value = shared.opts.get_default(name)
return None if value == default_value else value
if shared.opts.hypertile_enable_unet:
p.extra_generation_params["Hypertile U-Net"] = True
if shared.opts.hypertile_enable_unet or add_unet_params:
p.extra_generation_params["Hypertile U-Net max depth"] = option('hypertile_max_depth_unet')
p.extra_generation_params["Hypertile U-Net max tile size"] = option('hypertile_max_tile_unet')
p.extra_generation_params["Hypertile U-Net swap size"] = option('hypertile_swap_size_unet')
if shared.opts.hypertile_enable_vae:
p.extra_generation_params["Hypertile VAE"] = True
p.extra_generation_params["Hypertile VAE max depth"] = option('hypertile_max_depth_vae')
p.extra_generation_params["Hypertile VAE max tile size"] = option('hypertile_max_tile_vae')
p.extra_generation_params["Hypertile VAE swap size"] = option('hypertile_swap_size_vae')
def configure_hypertile(width, height, enable_unet=True):
hypertile.hypertile_hook_model(
shared.sd_model.first_stage_model,
width,
height,
swap_size=shared.opts.hypertile_swap_size_vae,
max_depth=shared.opts.hypertile_max_depth_vae,
tile_size_max=shared.opts.hypertile_max_tile_vae,
enable=shared.opts.hypertile_enable_vae,
)
hypertile.hypertile_hook_model(
shared.sd_model.model,
width,
height,
swap_size=shared.opts.hypertile_swap_size_unet,
max_depth=shared.opts.hypertile_max_depth_unet,
tile_size_max=shared.opts.hypertile_max_tile_unet,
enable=enable_unet,
is_sdxl=shared.sd_model.is_sdxl
)
def on_ui_settings():
import gradio as gr
options = {
"hypertile_explanation": shared.OptionHTML("""
<a href='https://github.com/tfernd/HyperTile'>Hypertile</a> optimizes the self-attention layer within U-Net and VAE models,
resulting in a reduction in computation time ranging from 1 to 4 times. The larger the generated image is, the greater the
benefit.
"""),
"hypertile_enable_unet": shared.OptionInfo(False, "Enable Hypertile U-Net", infotext="Hypertile U-Net").info("enables hypertile for all modes, including hires fix second pass; noticeable change in details of the generated picture"),
"hypertile_enable_unet_secondpass": shared.OptionInfo(False, "Enable Hypertile U-Net for hires fix second pass", infotext="Hypertile U-Net second pass").info("enables hypertile just for hires fix second pass - regardless of whether the above setting is enabled"),
"hypertile_max_depth_unet": shared.OptionInfo(3, "Hypertile U-Net max depth", gr.Slider, {"minimum": 0, "maximum": 3, "step": 1}, infotext="Hypertile U-Net max depth").info("larger = more neural network layers affected; minor effect on performance"),
"hypertile_max_tile_unet": shared.OptionInfo(256, "Hypertile U-Net max tile size", gr.Slider, {"minimum": 0, "maximum": 512, "step": 16}, infotext="Hypertile U-Net max tile size").info("larger = worse performance"),
"hypertile_swap_size_unet": shared.OptionInfo(3, "Hypertile U-Net swap size", gr.Slider, {"minimum": 0, "maximum": 64, "step": 1}, infotext="Hypertile U-Net swap size"),
"hypertile_enable_vae": shared.OptionInfo(False, "Enable Hypertile VAE", infotext="Hypertile VAE").info("minimal change in the generated picture"),
"hypertile_max_depth_vae": shared.OptionInfo(3, "Hypertile VAE max depth", gr.Slider, {"minimum": 0, "maximum": 3, "step": 1}, infotext="Hypertile VAE max depth"),
"hypertile_max_tile_vae": shared.OptionInfo(128, "Hypertile VAE max tile size", gr.Slider, {"minimum": 0, "maximum": 512, "step": 16}, infotext="Hypertile VAE max tile size"),
"hypertile_swap_size_vae": shared.OptionInfo(3, "Hypertile VAE swap size ", gr.Slider, {"minimum": 0, "maximum": 64, "step": 1}, infotext="Hypertile VAE swap size"),
}
for name, opt in options.items():
opt.section = ('hypertile', "Hypertile")
shared.opts.add_option(name, opt)
def add_axis_options():
xyz_grid = [x for x in scripts.scripts_data if x.script_class.__module__ == "xyz_grid.py"][0].module
xyz_grid.axis_options.extend([
xyz_grid.AxisOption("[Hypertile] Unet First pass Enabled", str, xyz_grid.apply_override('hypertile_enable_unet', boolean=True), choices=xyz_grid.boolean_choice(reverse=True)),
xyz_grid.AxisOption("[Hypertile] Unet Second pass Enabled", str, xyz_grid.apply_override('hypertile_enable_unet_secondpass', boolean=True), choices=xyz_grid.boolean_choice(reverse=True)),
xyz_grid.AxisOption("[Hypertile] Unet Max Depth", int, xyz_grid.apply_override("hypertile_max_depth_unet"), confirm=xyz_grid.confirm_range(0, 3, '[Hypertile] Unet Max Depth'), choices=lambda: [str(x) for x in range(4)]),
xyz_grid.AxisOption("[Hypertile] Unet Max Tile Size", int, xyz_grid.apply_override("hypertile_max_tile_unet"), confirm=xyz_grid.confirm_range(0, 512, '[Hypertile] Unet Max Tile Size')),
xyz_grid.AxisOption("[Hypertile] Unet Swap Size", int, xyz_grid.apply_override("hypertile_swap_size_unet"), confirm=xyz_grid.confirm_range(0, 64, '[Hypertile] Unet Swap Size')),
xyz_grid.AxisOption("[Hypertile] VAE Enabled", str, xyz_grid.apply_override('hypertile_enable_vae', boolean=True), choices=xyz_grid.boolean_choice(reverse=True)),
xyz_grid.AxisOption("[Hypertile] VAE Max Depth", int, xyz_grid.apply_override("hypertile_max_depth_vae"), confirm=xyz_grid.confirm_range(0, 3, '[Hypertile] VAE Max Depth'), choices=lambda: [str(x) for x in range(4)]),
xyz_grid.AxisOption("[Hypertile] VAE Max Tile Size", int, xyz_grid.apply_override("hypertile_max_tile_vae"), confirm=xyz_grid.confirm_range(0, 512, '[Hypertile] VAE Max Tile Size')),
xyz_grid.AxisOption("[Hypertile] VAE Swap Size", int, xyz_grid.apply_override("hypertile_swap_size_vae"), confirm=xyz_grid.confirm_range(0, 64, '[Hypertile] VAE Swap Size')),
])
script_callbacks.on_ui_settings(on_ui_settings)
script_callbacks.on_before_ui(add_axis_options)

34
extensions-builtin/mobile/javascript/mobile.js Normal file
View File

@ -0,0 +1,34 @@
var isSetupForMobile = false;
function isMobile() {
for (var tab of ["txt2img", "img2img"]) {
var imageTab = gradioApp().getElementById(tab + '_results');
if (imageTab && imageTab.offsetParent && imageTab.offsetLeft == 0) {
return true;
}
}
return false;
}
function reportWindowSize() {
if (gradioApp().querySelector('.toprow-compact-tools')) return; // not applicable for compact prompt layout
var currentlyMobile = isMobile();
if (currentlyMobile == isSetupForMobile) return;
isSetupForMobile = currentlyMobile;
for (var tab of ["txt2img", "img2img"]) {
var button = gradioApp().getElementById(tab + '_generate_box');
var target = gradioApp().getElementById(currentlyMobile ? tab + '_results' : tab + '_actions_column');
target.insertBefore(button, target.firstElementChild);
gradioApp().getElementById(tab + '_results').classList.toggle('mobile', currentlyMobile);
}
}
window.addEventListener("resize", reportWindowSize);
onUiLoaded(function() {
reportWindowSize();
});

64
extensions-builtin/postprocessing-for-training/scripts/postprocessing_autosized_crop.py Normal file
View File

@ -0,0 +1,64 @@
from PIL import Image
from modules import scripts_postprocessing, ui_components
import gradio as gr
def center_crop(image: Image, w: int, h: int):
iw, ih = image.size
if ih / h < iw / w:
sw = w * ih / h
box = (iw - sw) / 2, 0, iw - (iw - sw) / 2, ih
else:
sh = h * iw / w
box = 0, (ih - sh) / 2, iw, ih - (ih - sh) / 2
return image.resize((w, h), Image.Resampling.LANCZOS, box)
def multicrop_pic(image: Image, mindim, maxdim, minarea, maxarea, objective, threshold):
iw, ih = image.size
err = lambda w, h: 1 - (lambda x: x if x < 1 else 1 / x)(iw / ih / (w / h))
wh = max(((w, h) for w in range(mindim, maxdim + 1, 64) for h in range(mindim, maxdim + 1, 64)
if minarea <= w * h <= maxarea and err(w, h) <= threshold),
key=lambda wh: (wh[0] * wh[1], -err(*wh))[::1 if objective == 'Maximize area' else -1],
default=None
)
return wh and center_crop(image, *wh)
class ScriptPostprocessingAutosizedCrop(scripts_postprocessing.ScriptPostprocessing):
name = "Auto-sized crop"
order = 4020
def ui(self):
with ui_components.InputAccordion(False, label="Auto-sized crop") as enable:
gr.Markdown('Each image is center-cropped with an automatically chosen width and height.')
with gr.Row():
mindim = gr.Slider(minimum=64, maximum=2048, step=8, label="Dimension lower bound", value=384, elem_id="postprocess_multicrop_mindim")
maxdim = gr.Slider(minimum=64, maximum=2048, step=8, label="Dimension upper bound", value=768, elem_id="postprocess_multicrop_maxdim")
with gr.Row():
minarea = gr.Slider(minimum=64 * 64, maximum=2048 * 2048, step=1, label="Area lower bound", value=64 * 64, elem_id="postprocess_multicrop_minarea")
maxarea = gr.Slider(minimum=64 * 64, maximum=2048 * 2048, step=1, label="Area upper bound", value=640 * 640, elem_id="postprocess_multicrop_maxarea")
with gr.Row():
objective = gr.Radio(["Maximize area", "Minimize error"], value="Maximize area", label="Resizing objective", elem_id="postprocess_multicrop_objective")
threshold = gr.Slider(minimum=0, maximum=1, step=0.01, label="Error threshold", value=0.1, elem_id="postprocess_multicrop_threshold")
return {
"enable": enable,
"mindim": mindim,
"maxdim": maxdim,
"minarea": minarea,
"maxarea": maxarea,
"objective": objective,
"threshold": threshold,
}
def process(self, pp: scripts_postprocessing.PostprocessedImage, enable, mindim, maxdim, minarea, maxarea, objective, threshold):
if not enable:
return
cropped = multicrop_pic(pp.image, mindim, maxdim, minarea, maxarea, objective, threshold)
if cropped is not None:
pp.image = cropped
else:
print(f"skipped {pp.image.width}x{pp.image.height} image (can't find suitable size within error threshold)")

30
extensions-builtin/postprocessing-for-training/scripts/postprocessing_caption.py Normal file
View File

@ -0,0 +1,30 @@
from modules import scripts_postprocessing, ui_components, deepbooru, shared
import gradio as gr
class ScriptPostprocessingCeption(scripts_postprocessing.ScriptPostprocessing):
name = "Caption"
order = 4040
def ui(self):
with ui_components.InputAccordion(False, label="Caption") as enable:
option = gr.CheckboxGroup(value=["Deepbooru"], choices=["Deepbooru", "BLIP"], show_label=False)
return {
"enable": enable,
"option": option,
}
def process(self, pp: scripts_postprocessing.PostprocessedImage, enable, option):
if not enable:
return
captions = [pp.caption]
if "Deepbooru" in option:
captions.append(deepbooru.model.tag(pp.image))
if "BLIP" in option:
captions.append(shared.interrogator.interrogate(pp.image.convert("RGB")))
pp.caption = ", ".join([x for x in captions if x])

32
extensions-builtin/postprocessing-for-training/scripts/postprocessing_create_flipped_copies.py Normal file
View File

@ -0,0 +1,32 @@
from PIL import ImageOps, Image
from modules import scripts_postprocessing, ui_components
import gradio as gr
class ScriptPostprocessingCreateFlippedCopies(scripts_postprocessing.ScriptPostprocessing):
name = "Create flipped copies"
order = 4030
def ui(self):
with ui_components.InputAccordion(False, label="Create flipped copies") as enable:
with gr.Row():
option = gr.CheckboxGroup(value=["Horizontal"], choices=["Horizontal", "Vertical", "Both"], show_label=False)
return {
"enable": enable,
"option": option,
}
def process(self, pp: scripts_postprocessing.PostprocessedImage, enable, option):
if not enable:
return
if "Horizontal" in option:
pp.extra_images.append(ImageOps.mirror(pp.image))
if "Vertical" in option:
pp.extra_images.append(pp.image.transpose(Image.Transpose.FLIP_TOP_BOTTOM))
if "Both" in option:
pp.extra_images.append(pp.image.transpose(Image.Transpose.FLIP_TOP_BOTTOM).transpose(Image.Transpose.FLIP_LEFT_RIGHT))

54
extensions-builtin/postprocessing-for-training/scripts/postprocessing_focal_crop.py Normal file
View File

@ -0,0 +1,54 @@
from modules import scripts_postprocessing, ui_components, errors
import gradio as gr
from modules.textual_inversion import autocrop
class ScriptPostprocessingFocalCrop(scripts_postprocessing.ScriptPostprocessing):
name = "Auto focal point crop"
order = 4010
def ui(self):
with ui_components.InputAccordion(False, label="Auto focal point crop") as enable:
face_weight = gr.Slider(label='Focal point face weight', value=0.9, minimum=0.0, maximum=1.0, step=0.05, elem_id="postprocess_focal_crop_face_weight")
entropy_weight = gr.Slider(label='Focal point entropy weight', value=0.15, minimum=0.0, maximum=1.0, step=0.05, elem_id="postprocess_focal_crop_entropy_weight")
edges_weight = gr.Slider(label='Focal point edges weight', value=0.5, minimum=0.0, maximum=1.0, step=0.05, elem_id="postprocess_focal_crop_edges_weight")
debug = gr.Checkbox(label='Create debug image', elem_id="train_process_focal_crop_debug")
return {
"enable": enable,
"face_weight": face_weight,
"entropy_weight": entropy_weight,
"edges_weight": edges_weight,
"debug": debug,
}
def process(self, pp: scripts_postprocessing.PostprocessedImage, enable, face_weight, entropy_weight, edges_weight, debug):
if not enable:
return
if not pp.shared.target_width or not pp.shared.target_height:
return
dnn_model_path = None
try:
dnn_model_path = autocrop.download_and_cache_models()
except Exception:
errors.report("Unable to load face detection model for auto crop selection. Falling back to lower quality haar method.", exc_info=True)
autocrop_settings = autocrop.Settings(
crop_width=pp.shared.target_width,
crop_height=pp.shared.target_height,
face_points_weight=face_weight,
entropy_points_weight=entropy_weight,
corner_points_weight=edges_weight,
annotate_image=debug,
dnn_model_path=dnn_model_path,
)
result, *others = autocrop.crop_image(pp.image, autocrop_settings)
pp.image = result
pp.extra_images = [pp.create_copy(x, nametags=["focal-crop-debug"], disable_processing=True) for x in others]

71
extensions-builtin/postprocessing-for-training/scripts/postprocessing_split_oversized.py Normal file
View File

@ -0,0 +1,71 @@
import math
from modules import scripts_postprocessing, ui_components
import gradio as gr
def split_pic(image, inverse_xy, width, height, overlap_ratio):
if inverse_xy:
from_w, from_h = image.height, image.width
to_w, to_h = height, width
else:
from_w, from_h = image.width, image.height
to_w, to_h = width, height
h = from_h * to_w // from_w
if inverse_xy:
image = image.resize((h, to_w))
else:
image = image.resize((to_w, h))
split_count = math.ceil((h - to_h * overlap_ratio) / (to_h * (1.0 - overlap_ratio)))
y_step = (h - to_h) / (split_count - 1)
for i in range(split_count):
y = int(y_step * i)
if inverse_xy:
splitted = image.crop((y, 0, y + to_h, to_w))
else:
splitted = image.crop((0, y, to_w, y + to_h))
yield splitted
class ScriptPostprocessingSplitOversized(scripts_postprocessing.ScriptPostprocessing):
name = "Split oversized images"
order = 4000
def ui(self):
with ui_components.InputAccordion(False, label="Split oversized images") as enable:
with gr.Row():
split_threshold = gr.Slider(label='Threshold', value=0.5, minimum=0.0, maximum=1.0, step=0.05, elem_id="postprocess_split_threshold")
overlap_ratio = gr.Slider(label='Overlap ratio', value=0.2, minimum=0.0, maximum=0.9, step=0.05, elem_id="postprocess_overlap_ratio")
return {
"enable": enable,
"split_threshold": split_threshold,
"overlap_ratio": overlap_ratio,
}
def process(self, pp: scripts_postprocessing.PostprocessedImage, enable, split_threshold, overlap_ratio):
if not enable:
return
width = pp.shared.target_width
height = pp.shared.target_height
if not width or not height:
return
if pp.image.height > pp.image.width:
ratio = (pp.image.width * height) / (pp.image.height * width)
inverse_xy = False
else:
ratio = (pp.image.height * width) / (pp.image.width * height)
inverse_xy = True
if ratio >= 1.0 or ratio > split_threshold:
return
result, *others = split_pic(pp.image, inverse_xy, width, height, overlap_ratio)
pp.image = result
pp.extra_images = [pp.create_copy(x) for x in others]

42
extensions-builtin/prompt-bracket-checker/javascript/prompt-bracket-checker.js Normal file
View File

@ -0,0 +1,42 @@
// Stable Diffusion WebUI - Bracket checker
// By Hingashi no Florin/Bwin4L & @akx
// Counts open and closed brackets (round, square, curly) in the prompt and negative prompt text boxes in the txt2img and img2img tabs.
// If there's a mismatch, the keyword counter turns red and if you hover on it, a tooltip tells you what's wrong.
function checkBrackets(textArea, counterElt) {
var counts = {};
(textArea.value.match(/[(){}[\]]/g) || []).forEach(bracket => {
counts[bracket] = (counts[bracket] || 0) + 1;
});
var errors = [];
function checkPair(open, close, kind) {
if (counts[open] !== counts[close]) {
errors.push(
`${open}...${close} - Detected ${counts[open] || 0} opening and ${counts[close] || 0} closing ${kind}.`
);
}
}
checkPair('(', ')', 'round brackets');
checkPair('[', ']', 'square brackets');
checkPair('{', '}', 'curly brackets');
counterElt.title = errors.join('\n');
counterElt.classList.toggle('error', errors.length !== 0);
}
function setupBracketChecking(id_prompt, id_counter) {
var textarea = gradioApp().querySelector("#" + id_prompt + " > label > textarea");
var counter = gradioApp().getElementById(id_counter);
if (textarea && counter) {
textarea.addEventListener("input", () => checkBrackets(textarea, counter));
}
}
onUiLoaded(function() {
setupBracketChecking('txt2img_prompt', 'txt2img_token_counter');
setupBracketChecking('txt2img_neg_prompt', 'txt2img_negative_token_counter');
setupBracketChecking('img2img_prompt', 'img2img_token_counter');
setupBracketChecking('img2img_neg_prompt', 'img2img_negative_token_counter');
});

760
extensions-builtin/soft-inpainting/scripts/soft_inpainting.py Normal file
View File

@ -0,0 +1,760 @@
import numpy as np
import gradio as gr
import math
from modules.ui_components import InputAccordion
import modules.scripts as scripts
from modules.torch_utils import float64
class SoftInpaintingSettings:
def __init__(self,
mask_blend_power,
mask_blend_scale,
inpaint_detail_preservation,
composite_mask_influence,
composite_difference_threshold,
composite_difference_contrast):
self.mask_blend_power = mask_blend_power
self.mask_blend_scale = mask_blend_scale
self.inpaint_detail_preservation = inpaint_detail_preservation
self.composite_mask_influence = composite_mask_influence
self.composite_difference_threshold = composite_difference_threshold
self.composite_difference_contrast = composite_difference_contrast
def add_generation_params(self, dest):
dest[enabled_gen_param_label] = True
dest[gen_param_labels.mask_blend_power] = self.mask_blend_power
dest[gen_param_labels.mask_blend_scale] = self.mask_blend_scale
dest[gen_param_labels.inpaint_detail_preservation] = self.inpaint_detail_preservation
dest[gen_param_labels.composite_mask_influence] = self.composite_mask_influence
dest[gen_param_labels.composite_difference_threshold] = self.composite_difference_threshold
dest[gen_param_labels.composite_difference_contrast] = self.composite_difference_contrast
# ------------------- Methods -------------------
def processing_uses_inpainting(p):
# TODO: Figure out a better way to determine if inpainting is being used by p
if getattr(p, "image_mask", None) is not None:
return True
if getattr(p, "mask", None) is not None:
return True
if getattr(p, "nmask", None) is not None:
return True
return False
def latent_blend(settings, a, b, t):
"""
Interpolates two latent image representations according to the parameter t,
where the interpolated vectors' magnitudes are also interpolated separately.
The "detail_preservation" factor biases the magnitude interpolation towards
the larger of the two magnitudes.
"""
import torch
# NOTE: We use inplace operations wherever possible.
if len(t.shape) == 3:
# [4][w][h] to [1][4][w][h]
t2 = t.unsqueeze(0)
# [4][w][h] to [1][1][w][h] - the [4] seem redundant.
t3 = t[0].unsqueeze(0).unsqueeze(0)
else:
t2 = t
t3 = t[:, 0][:, None]
one_minus_t2 = 1 - t2
one_minus_t3 = 1 - t3
# Linearly interpolate the image vectors.
a_scaled = a * one_minus_t2
b_scaled = b * t2
image_interp = a_scaled
image_interp.add_(b_scaled)
result_type = image_interp.dtype
del a_scaled, b_scaled, t2, one_minus_t2
# Calculate the magnitude of the interpolated vectors. (We will remove this magnitude.)
# 64-bit operations are used here to allow large exponents.
current_magnitude = torch.norm(image_interp, p=2, dim=1, keepdim=True).to(float64(image_interp)).add_(0.00001)
# Interpolate the powered magnitudes, then un-power them (bring them back to a power of 1).
a_magnitude = torch.norm(a, p=2, dim=1, keepdim=True).to(float64(a)).pow_(settings.inpaint_detail_preservation) * one_minus_t3
b_magnitude = torch.norm(b, p=2, dim=1, keepdim=True).to(float64(b)).pow_(settings.inpaint_detail_preservation) * t3
desired_magnitude = a_magnitude
desired_magnitude.add_(b_magnitude).pow_(1 / settings.inpaint_detail_preservation)
del a_magnitude, b_magnitude, t3, one_minus_t3
# Change the linearly interpolated image vectors' magnitudes to the value we want.
# This is the last 64-bit operation.
image_interp_scaling_factor = desired_magnitude
image_interp_scaling_factor.div_(current_magnitude)
image_interp_scaling_factor = image_interp_scaling_factor.to(result_type)
image_interp_scaled = image_interp
image_interp_scaled.mul_(image_interp_scaling_factor)
del current_magnitude
del desired_magnitude
del image_interp
del image_interp_scaling_factor
del result_type
return image_interp_scaled
def get_modified_nmask(settings, nmask, sigma):
"""
Converts a negative mask representing the transparency of the original latent vectors being overlaid
to a mask that is scaled according to the denoising strength for this step.
Where:
0 = fully opaque, infinite density, fully masked
1 = fully transparent, zero density, fully unmasked
We bring this transparency to a power, as this allows one to simulate N number of blending operations
where N can be any positive real value. Using this one can control the balance of influence between
the denoiser and the original latents according to the sigma value.
NOTE: "mask" is not used
"""
import torch
return torch.pow(nmask, (sigma ** settings.mask_blend_power) * settings.mask_blend_scale)
def apply_adaptive_masks(
settings: SoftInpaintingSettings,
nmask,
latent_orig,
latent_processed,
overlay_images,
width, height,
paste_to):
import torch
import modules.processing as proc
import modules.images as images
from PIL import Image, ImageOps, ImageFilter
# TODO: Bias the blending according to the latent mask, add adjustable parameter for bias control.
if len(nmask.shape) == 3:
latent_mask = nmask[0].float()
else:
latent_mask = nmask[:, 0].float()
# convert the original mask into a form we use to scale distances for thresholding
mask_scalar = 1 - (torch.clamp(latent_mask, min=0, max=1) ** (settings.mask_blend_scale / 2))
mask_scalar = (0.5 * (1 - settings.composite_mask_influence)
+ mask_scalar * settings.composite_mask_influence)
mask_scalar = mask_scalar / (1.00001 - mask_scalar)
mask_scalar = mask_scalar.cpu().numpy()
latent_distance = torch.norm(latent_processed - latent_orig, p=2, dim=1)
kernel, kernel_center = get_gaussian_kernel(stddev_radius=1.5, max_radius=2)
masks_for_overlay = []
for i, (distance_map, overlay_image) in enumerate(zip(latent_distance, overlay_images)):
converted_mask = distance_map.float().cpu().numpy()
converted_mask = weighted_histogram_filter(converted_mask, kernel, kernel_center,
percentile_min=0.9, percentile_max=1, min_width=1)
converted_mask = weighted_histogram_filter(converted_mask, kernel, kernel_center,
percentile_min=0.25, percentile_max=0.75, min_width=1)
# The distance at which opacity of original decreases to 50%
if len(mask_scalar.shape) == 3:
if mask_scalar.shape[0] > i:
half_weighted_distance = settings.composite_difference_threshold * mask_scalar[i]
else:
half_weighted_distance = settings.composite_difference_threshold * mask_scalar[0]
else:
half_weighted_distance = settings.composite_difference_threshold * mask_scalar
converted_mask = converted_mask / half_weighted_distance
converted_mask = 1 / (1 + converted_mask ** settings.composite_difference_contrast)
converted_mask = smootherstep(converted_mask)
converted_mask = 1 - converted_mask
converted_mask = 255. * converted_mask
converted_mask = converted_mask.astype(np.uint8)
converted_mask = Image.fromarray(converted_mask)
converted_mask = images.resize_image(2, converted_mask, width, height)
converted_mask = proc.create_binary_mask(converted_mask, round=False)
# Remove aliasing artifacts using a gaussian blur.
converted_mask = converted_mask.filter(ImageFilter.GaussianBlur(radius=4))
# Expand the mask to fit the whole image if needed.
if paste_to is not None:
converted_mask = proc.uncrop(converted_mask,
(overlay_image.width, overlay_image.height),
paste_to)
masks_for_overlay.append(converted_mask)
image_masked = Image.new('RGBa', (overlay_image.width, overlay_image.height))
image_masked.paste(overlay_image.convert("RGBA").convert("RGBa"),
mask=ImageOps.invert(converted_mask.convert('L')))
overlay_images[i] = image_masked.convert('RGBA')
return masks_for_overlay
def apply_masks(
settings,
nmask,
overlay_images,
width, height,
paste_to):
import torch
import modules.processing as proc
import modules.images as images
from PIL import Image, ImageOps, ImageFilter
converted_mask = nmask[0].float()
converted_mask = torch.clamp(converted_mask, min=0, max=1).pow_(settings.mask_blend_scale / 2)
converted_mask = 255. * converted_mask
converted_mask = converted_mask.cpu().numpy().astype(np.uint8)
converted_mask = Image.fromarray(converted_mask)
converted_mask = images.resize_image(2, converted_mask, width, height)
converted_mask = proc.create_binary_mask(converted_mask, round=False)
# Remove aliasing artifacts using a gaussian blur.
converted_mask = converted_mask.filter(ImageFilter.GaussianBlur(radius=4))
# Expand the mask to fit the whole image if needed.
if paste_to is not None:
converted_mask = proc.uncrop(converted_mask,
(width, height),
paste_to)
masks_for_overlay = []
for i, overlay_image in enumerate(overlay_images):
masks_for_overlay[i] = converted_mask
image_masked = Image.new('RGBa', (overlay_image.width, overlay_image.height))
image_masked.paste(overlay_image.convert("RGBA").convert("RGBa"),
mask=ImageOps.invert(converted_mask.convert('L')))
overlay_images[i] = image_masked.convert('RGBA')
return masks_for_overlay
def weighted_histogram_filter(img, kernel, kernel_center, percentile_min=0.0, percentile_max=1.0, min_width=1.0):
"""
Generalization convolution filter capable of applying
weighted mean, median, maximum, and minimum filters
parametrically using an arbitrary kernel.
Args:
img (nparray):
The image, a 2-D array of floats, to which the filter is being applied.
kernel (nparray):
The kernel, a 2-D array of floats.
kernel_center (nparray):
The kernel center coordinate, a 1-D array with two elements.
percentile_min (float):
The lower bound of the histogram window used by the filter,
from 0 to 1.
percentile_max (float):
The upper bound of the histogram window used by the filter,
from 0 to 1.
min_width (float):
The minimum size of the histogram window bounds, in weight units.
Must be greater than 0.
Returns:
(nparray): A filtered copy of the input image "img", a 2-D array of floats.
"""
# Converts an index tuple into a vector.
def vec(x):
return np.array(x)
kernel_min = -kernel_center
kernel_max = vec(kernel.shape) - kernel_center
def weighted_histogram_filter_single(idx):
idx = vec(idx)
min_index = np.maximum(0, idx + kernel_min)
max_index = np.minimum(vec(img.shape), idx + kernel_max)
window_shape = max_index - min_index
class WeightedElement:
"""
An element of the histogram, its weight
and bounds.
"""
def __init__(self, value, weight):
self.value: float = value
self.weight: float = weight
self.window_min: float = 0.0
self.window_max: float = 1.0
# Collect the values in the image as WeightedElements,
# weighted by their corresponding kernel values.
values = []
for window_tup in np.ndindex(tuple(window_shape)):
window_index = vec(window_tup)
image_index = window_index + min_index
centered_kernel_index = image_index - idx
kernel_index = centered_kernel_index + kernel_center
element = WeightedElement(img[tuple(image_index)], kernel[tuple(kernel_index)])
values.append(element)
def sort_key(x: WeightedElement):
return x.value
values.sort(key=sort_key)
# Calculate the height of the stack (sum)
# and each sample's range they occupy in the stack
sum = 0
for i in range(len(values)):
values[i].window_min = sum
sum += values[i].weight
values[i].window_max = sum
# Calculate what range of this stack ("window")
# we want to get the weighted average across.
window_min = sum * percentile_min
window_max = sum * percentile_max
window_width = window_max - window_min
# Ensure the window is within the stack and at least a certain size.
if window_width < min_width:
window_center = (window_min + window_max) / 2
window_min = window_center - min_width / 2
window_max = window_center + min_width / 2
if window_max > sum:
window_max = sum
window_min = sum - min_width
if window_min < 0:
window_min = 0
window_max = min_width
value = 0
value_weight = 0
# Get the weighted average of all the samples
# that overlap with the window, weighted
# by the size of their overlap.
for i in range(len(values)):
if window_min >= values[i].window_max:
continue
if window_max <= values[i].window_min:
break
s = max(window_min, values[i].window_min)
e = min(window_max, values[i].window_max)
w = e - s
value += values[i].value * w
value_weight += w
return value / value_weight if value_weight != 0 else 0
img_out = img.copy()
# Apply the kernel operation over each pixel.
for index in np.ndindex(img.shape):
img_out[index] = weighted_histogram_filter_single(index)
return img_out
def smoothstep(x):
"""
The smoothstep function, input should be clamped to 0-1 range.
Turns a diagonal line (f(x) = x) into a sigmoid-like curve.
"""
return x * x * (3 - 2 * x)
def smootherstep(x):
"""
The smootherstep function, input should be clamped to 0-1 range.
Turns a diagonal line (f(x) = x) into a sigmoid-like curve.
"""
return x * x * x * (x * (6 * x - 15) + 10)
def get_gaussian_kernel(stddev_radius=1.0, max_radius=2):
"""
Creates a Gaussian kernel with thresholded edges.
Args:
stddev_radius (float):
Standard deviation of the gaussian kernel, in pixels.
max_radius (int):
The size of the filter kernel. The number of pixels is (max_radius*2+1) ** 2.
The kernel is thresholded so that any values one pixel beyond this radius
is weighted at 0.
Returns:
(nparray, nparray): A kernel array (shape: (N, N)), its center coordinate (shape: (2))
"""
# Evaluates a 0-1 normalized gaussian function for a given square distance from the mean.
def gaussian(sqr_mag):
return math.exp(-sqr_mag / (stddev_radius * stddev_radius))
# Helper function for converting a tuple to an array.
def vec(x):
return np.array(x)
"""
Since a gaussian is unbounded, we need to limit ourselves
to a finite range.
We taper the ends off at the end of that range so they equal zero
while preserving the maximum value of 1 at the mean.
"""
zero_radius = max_radius + 1.0
gauss_zero = gaussian(zero_radius * zero_radius)
gauss_kernel_scale = 1 / (1 - gauss_zero)
def gaussian_kernel_func(coordinate):
x = coordinate[0] ** 2.0 + coordinate[1] ** 2.0
x = gaussian(x)
x -= gauss_zero
x *= gauss_kernel_scale
x = max(0.0, x)
return x
size = max_radius * 2 + 1
kernel_center = max_radius
kernel = np.zeros((size, size))
for index in np.ndindex(kernel.shape):
kernel[index] = gaussian_kernel_func(vec(index) - kernel_center)
return kernel, kernel_center
# ------------------- Constants -------------------
default = SoftInpaintingSettings(1, 0.5, 4, 0, 0.5, 2)
enabled_ui_label = "Soft inpainting"
enabled_gen_param_label = "Soft inpainting enabled"
enabled_el_id = "soft_inpainting_enabled"
ui_labels = SoftInpaintingSettings(
"Schedule bias",
"Preservation strength",
"Transition contrast boost",
"Mask influence",
"Difference threshold",
"Difference contrast")
ui_info = SoftInpaintingSettings(
"Shifts when preservation of original content occurs during denoising.",
"How strongly partially masked content should be preserved.",
"Amplifies the contrast that may be lost in partially masked regions.",
"How strongly the original mask should bias the difference threshold.",
"How much an image region can change before the original pixels are not blended in anymore.",
"How sharp the transition should be between blended and not blended.")
gen_param_labels = SoftInpaintingSettings(
"Soft inpainting schedule bias",
"Soft inpainting preservation strength",
"Soft inpainting transition contrast boost",
"Soft inpainting mask influence",
"Soft inpainting difference threshold",
"Soft inpainting difference contrast")
el_ids = SoftInpaintingSettings(
"mask_blend_power",
"mask_blend_scale",
"inpaint_detail_preservation",
"composite_mask_influence",
"composite_difference_threshold",
"composite_difference_contrast")
# ------------------- Script -------------------
class Script(scripts.Script):
def __init__(self):
self.section = "inpaint"
self.masks_for_overlay = None
self.overlay_images = None
def title(self):
return "Soft Inpainting"
def show(self, is_img2img):
return scripts.AlwaysVisible if is_img2img else False
def ui(self, is_img2img):
if not is_img2img:
return
with InputAccordion(False, label=enabled_ui_label, elem_id=enabled_el_id) as soft_inpainting_enabled:
with gr.Group():
gr.Markdown(
"""
Soft inpainting allows you to **seamlessly blend original content with inpainted content** according to the mask opacity.
**High _Mask blur_** values are recommended!
""")
power = \
gr.Slider(label=ui_labels.mask_blend_power,
info=ui_info.mask_blend_power,
minimum=0,
maximum=8,
step=0.1,
value=default.mask_blend_power,
elem_id=el_ids.mask_blend_power)
scale = \
gr.Slider(label=ui_labels.mask_blend_scale,
info=ui_info.mask_blend_scale,
minimum=0,
maximum=8,
step=0.05,
value=default.mask_blend_scale,
elem_id=el_ids.mask_blend_scale)
detail = \
gr.Slider(label=ui_labels.inpaint_detail_preservation,
info=ui_info.inpaint_detail_preservation,
minimum=1,
maximum=32,
step=0.5,
value=default.inpaint_detail_preservation,
elem_id=el_ids.inpaint_detail_preservation)
gr.Markdown(
"""
### Pixel Composite Settings
""")
mask_inf = \
gr.Slider(label=ui_labels.composite_mask_influence,
info=ui_info.composite_mask_influence,
minimum=0,
maximum=1,
step=0.05,
value=default.composite_mask_influence,
elem_id=el_ids.composite_mask_influence)
dif_thresh = \
gr.Slider(label=ui_labels.composite_difference_threshold,
info=ui_info.composite_difference_threshold,
minimum=0,
maximum=8,
step=0.25,
value=default.composite_difference_threshold,
elem_id=el_ids.composite_difference_threshold)
dif_contr = \
gr.Slider(label=ui_labels.composite_difference_contrast,
info=ui_info.composite_difference_contrast,
minimum=0,
maximum=8,
step=0.25,
value=default.composite_difference_contrast,
elem_id=el_ids.composite_difference_contrast)
with gr.Accordion("Help", open=False):
gr.Markdown(
f"""
### {ui_labels.mask_blend_power}
The blending strength of original content is scaled proportionally with the decreasing noise level values at each step (sigmas).
This ensures that the influence of the denoiser and original content preservation is roughly balanced at each step.
This balance can be shifted using this parameter, controlling whether earlier or later steps have stronger preservation.
- **Below 1**: Stronger preservation near the end (with low sigma)
- **1**: Balanced (proportional to sigma)
- **Above 1**: Stronger preservation in the beginning (with high sigma)
""")
gr.Markdown(
f"""
### {ui_labels.mask_blend_scale}
Skews whether partially masked image regions should be more likely to preserve the original content or favor inpainted content.
This may need to be adjusted depending on the {ui_labels.mask_blend_power}, CFG Scale, prompt and Denoising strength.
- **Low values**: Favors generated content.
- **High values**: Favors original content.
""")
gr.Markdown(
f"""
### {ui_labels.inpaint_detail_preservation}
This parameter controls how the original latent vectors and denoised latent vectors are interpolated.
With higher values, the magnitude of the resulting blended vector will be closer to the maximum of the two interpolated vectors.
This can prevent the loss of contrast that occurs with linear interpolation.
- **Low values**: Softer blending, details may fade.
- **High values**: Stronger contrast, may over-saturate colors.
""")
gr.Markdown(
"""
## Pixel Composite Settings
Masks are generated based on how much a part of the image changed after denoising.
These masks are used to blend the original and final images together.
If the difference is low, the original pixels are used instead of the pixels returned by the inpainting process.
""")
gr.Markdown(
f"""
### {ui_labels.composite_mask_influence}
This parameter controls how much the mask should bias this sensitivity to difference.
- **0**: Ignore the mask, only consider differences in image content.
- **1**: Follow the mask closely despite image content changes.
""")
gr.Markdown(
f"""
### {ui_labels.composite_difference_threshold}
This value represents the difference at which the original pixels will have less than 50% opacity.
- **Low values**: Two images patches must be almost the same in order to retain original pixels.
- **High values**: Two images patches can be very different and still retain original pixels.
""")
gr.Markdown(
f"""
### {ui_labels.composite_difference_contrast}
This value represents the contrast between the opacity of the original and inpainted content.
- **Low values**: The blend will be more gradual and have longer transitions, but may cause ghosting.
- **High values**: Ghosting will be less common, but transitions may be very sudden.
""")
self.infotext_fields = [(soft_inpainting_enabled, enabled_gen_param_label),
(power, gen_param_labels.mask_blend_power),
(scale, gen_param_labels.mask_blend_scale),
(detail, gen_param_labels.inpaint_detail_preservation),
(mask_inf, gen_param_labels.composite_mask_influence),
(dif_thresh, gen_param_labels.composite_difference_threshold),
(dif_contr, gen_param_labels.composite_difference_contrast)]
self.paste_field_names = []
for _, field_name in self.infotext_fields:
self.paste_field_names.append(field_name)
return [soft_inpainting_enabled,
power,
scale,
detail,
mask_inf,
dif_thresh,
dif_contr]
def process(self, p, enabled, power, scale, detail_preservation, mask_inf, dif_thresh, dif_contr):
if not enabled:
return
if not processing_uses_inpainting(p):
return
# Shut off the rounding it normally does.
p.mask_round = False
settings = SoftInpaintingSettings(power, scale, detail_preservation, mask_inf, dif_thresh, dif_contr)
# p.extra_generation_params["Mask rounding"] = False
settings.add_generation_params(p.extra_generation_params)
def on_mask_blend(self, p, mba: scripts.MaskBlendArgs, enabled, power, scale, detail_preservation, mask_inf,
dif_thresh, dif_contr):
if not enabled:
return
if not processing_uses_inpainting(p):
return
if mba.is_final_blend:
mba.blended_latent = mba.current_latent
return
settings = SoftInpaintingSettings(power, scale, detail_preservation, mask_inf, dif_thresh, dif_contr)
# todo: Why is sigma 2D? Both values are the same.
mba.blended_latent = latent_blend(settings,
mba.init_latent,
mba.current_latent,
get_modified_nmask(settings, mba.nmask, mba.sigma[0]))
def post_sample(self, p, ps: scripts.PostSampleArgs, enabled, power, scale, detail_preservation, mask_inf,
dif_thresh, dif_contr):
if not enabled:
return
if not processing_uses_inpainting(p):
return
nmask = getattr(p, "nmask", None)
if nmask is None:
return
from modules import images
from modules.shared import opts
settings = SoftInpaintingSettings(power, scale, detail_preservation, mask_inf, dif_thresh, dif_contr)
# since the original code puts holes in the existing overlay images,
# we have to rebuild them.
self.overlay_images = []
for img in p.init_images:
image = images.flatten(img, opts.img2img_background_color)
if p.paste_to is None and p.resize_mode != 3:
image = images.resize_image(p.resize_mode, image, p.width, p.height)
self.overlay_images.append(image.convert('RGBA'))
if len(p.init_images) == 1:
self.overlay_images = self.overlay_images * p.batch_size
if getattr(ps.samples, 'already_decoded', False):
self.masks_for_overlay = apply_masks(settings=settings,
nmask=nmask,
overlay_images=self.overlay_images,
width=p.width,
height=p.height,
paste_to=p.paste_to)
else:
self.masks_for_overlay = apply_adaptive_masks(settings=settings,
nmask=nmask,
latent_orig=p.init_latent,
latent_processed=ps.samples,
overlay_images=self.overlay_images,
width=p.width,
height=p.height,
paste_to=p.paste_to)
def postprocess_maskoverlay(self, p, ppmo: scripts.PostProcessMaskOverlayArgs, enabled, power, scale,
detail_preservation, mask_inf, dif_thresh, dif_contr):
if not enabled:
return
if not processing_uses_inpainting(p):
return
if self.masks_for_overlay is None:
return
if self.overlay_images is None:
return
ppmo.mask_for_overlay = self.masks_for_overlay[ppmo.index]
ppmo.overlay_image = self.overlay_images[ppmo.index]

BIN
html/card-no-preview.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 82 KiB

9
html/extra-networks-card.html Normal file
View File

@ -0,0 +1,9 @@
<div class="card" style="{style}" onclick="{card_clicked}" data-name="{name}" {sort_keys}>
{background_image}
<div class="button-row">{copy_path_button}{metadata_button}{edit_button}</div>
<div class="actions">
<div class="additional">{search_terms}</div>
<span class="name">{name}</span>
<span class="description">{description}</span>
</div>
</div>

5
html/extra-networks-copy-path-button.html Normal file
View File

@ -0,0 +1,5 @@
<div class="copy-path-button card-button"
title="Copy path to clipboard"
onclick="extraNetworksCopyCardPath(event)"
data-clipboard-text="{filename}">
</div>

4
html/extra-networks-edit-item-button.html Normal file
View File

@ -0,0 +1,4 @@
<div class="edit-button card-button"
title="Edit metadata"
onclick="extraNetworksEditUserMetadata(event, '{tabname}', '{extra_networks_tabname}')">
</div>

4
html/extra-networks-metadata-button.html Normal file
View File

@ -0,0 +1,4 @@
<div class="metadata-button card-button"
title="Show internal metadata"
onclick="extraNetworksRequestMetadata(event, '{extra_networks_tabname}')">
</div>

8
html/extra-networks-no-cards.html Normal file
View File

@ -0,0 +1,8 @@
<div class='nocards'>
<h1>Nothing here. Add some content to the following directories:</h1>
<ul>
{dirs}
</ul>
</div>

8
html/extra-networks-pane-dirs.html Normal file
View File

@ -0,0 +1,8 @@
<div class="extra-network-pane-content-dirs">
<div id='{tabname}_{extra_networks_tabname}_dirs' class='extra-network-dirs'>
{dirs_html}
</div>
<div id='{tabname}_{extra_networks_tabname}_cards' class='extra-network-cards'>
{items_html}
</div>
</div>

8
html/extra-networks-pane-tree.html Normal file
View File

@ -0,0 +1,8 @@
<div class="extra-network-pane-content-tree resize-handle-row">
<div id='{tabname}_{extra_networks_tabname}_tree' class='extra-network-tree' style='flex-basis: {extra_networks_tree_view_default_width}px'>
{tree_html}
</div>
<div id='{tabname}_{extra_networks_tabname}_cards' class='extra-network-cards' style='flex-grow: 1;'>
{items_html}
</div>
</div>

81
html/extra-networks-pane.html Normal file
View File

@ -0,0 +1,81 @@
<div id='{tabname}_{extra_networks_tabname}_pane' class='extra-network-pane {tree_view_div_default_display_class}'>
<div class="extra-network-control" id="{tabname}_{extra_networks_tabname}_controls" style="display:none" >
<div class="extra-network-control--search">
<input
id="{tabname}_{extra_networks_tabname}_extra_search"
class="extra-network-control--search-text"
type="search"
placeholder="Search"
>
</div>
<small>Sort: </small>
<div
id="{tabname}_{extra_networks_tabname}_extra_sort_path"
class="extra-network-control--sort{sort_path_active}"
data-sortkey="default"
title="Sort by path"
onclick="extraNetworksControlSortOnClick(event, '{tabname}', '{extra_networks_tabname}');"
>
<i class="extra-network-control--icon extra-network-control--sort-icon"></i>
</div>
<div
id="{tabname}_{extra_networks_tabname}_extra_sort_name"
class="extra-network-control--sort{sort_name_active}"
data-sortkey="name"
title="Sort by name"
onclick="extraNetworksControlSortOnClick(event, '{tabname}', '{extra_networks_tabname}');"
>
<i class="extra-network-control--icon extra-network-control--sort-icon"></i>
</div>
<div
id="{tabname}_{extra_networks_tabname}_extra_sort_date_created"
class="extra-network-control--sort{sort_date_created_active}"
data-sortkey="date_created"
title="Sort by date created"
onclick="extraNetworksControlSortOnClick(event, '{tabname}', '{extra_networks_tabname}');"
>
<i class="extra-network-control--icon extra-network-control--sort-icon"></i>
</div>
<div
id="{tabname}_{extra_networks_tabname}_extra_sort_date_modified"
class="extra-network-control--sort{sort_date_modified_active}"
data-sortkey="date_modified"
title="Sort by date modified"
onclick="extraNetworksControlSortOnClick(event, '{tabname}', '{extra_networks_tabname}');"
>
<i class="extra-network-control--icon extra-network-control--sort-icon"></i>
</div>
<small> </small>
<div
id="{tabname}_{extra_networks_tabname}_extra_sort_dir"
class="extra-network-control--sort-dir"
data-sortdir="{data_sortdir}"
title="Sort ascending"
onclick="extraNetworksControlSortDirOnClick(event, '{tabname}', '{extra_networks_tabname}');"
>
<i class="extra-network-control--icon extra-network-control--sort-dir-icon"></i>
</div>
<small> </small>
<div
id="{tabname}_{extra_networks_tabname}_extra_tree_view"
class="extra-network-control--tree-view {tree_view_btn_extra_class}"
title="Enable Tree View"
onclick="extraNetworksControlTreeViewOnClick(event, '{tabname}', '{extra_networks_tabname}');"
>
<i class="extra-network-control--icon extra-network-control--tree-view-icon"></i>
</div>
<div
id="{tabname}_{extra_networks_tabname}_extra_refresh"
class="extra-network-control--refresh"
title="Refresh page"
onclick="extraNetworksControlRefreshOnClick(event, '{tabname}', '{extra_networks_tabname}');"
>
<i class="extra-network-control--icon extra-network-control--refresh-icon"></i>
</div>
</div>
{pane_content}
</div>

23
html/extra-networks-tree-button.html Normal file
View File

@ -0,0 +1,23 @@
<span data-filterable-item-text hidden>{search_terms}</span>
<div class="tree-list-content {subclass}"
type="button"
onclick="extraNetworksTreeOnClick(event, '{tabname}', '{extra_networks_tabname}');{onclick_extra}"
data-path="{data_path}"
data-hash="{data_hash}"
>
<span class='tree-list-item-action tree-list-item-action--leading'>
{action_list_item_action_leading}
</span>
<span class="tree-list-item-visual tree-list-item-visual--leading">
{action_list_item_visual_leading}
</span>
<span class="tree-list-item-label tree-list-item-label--truncate">
{action_list_item_label}
</span>
<span class="tree-list-item-visual tree-list-item-visual--trailing">
{action_list_item_visual_trailing}
</span>
<span class="tree-list-item-action tree-list-item-action--trailing">
{action_list_item_action_trailing}
</span>
</div>

15
html/footer.html Normal file
View File

@ -0,0 +1,15 @@
<div>
<a href="{api_docs}">API</a>
 • 
<a href="https://github.com/AUTOMATIC1111/stable-diffusion-webui">Github</a>
 • 
<a href="https://gradio.app">Gradio</a>
 • 
<a href="#" onclick="showProfile('./internal/profile-startup'); return false;">Startup profile</a>
 • 
<a href="/" onclick="javascript:gradioApp().getElementById('settings_restart_gradio').click(); return false">Reload UI</a>
</div>
<br />
<div class="versions">
{versions}
</div>

382
html/licenses.html Normal file
View File

@ -0,0 +1,382 @@
<style>
#licenses h2 {font-size: 1.2em; font-weight: bold; margin-bottom: 0.2em;}
#licenses small {font-size: 0.95em; opacity: 0.85;}
#licenses pre { margin: 1em 0 2em 0;}
</style>
<h2><a href="https://github.com/invoke-ai/InvokeAI/blob/main/LICENSE">InvokeAI</a></h2>
<small>Some code for compatibility with OSX is taken from lstein's repository.</small>
<pre>
MIT License
Copyright (c) 2022 InvokeAI Team
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
</pre>
<h2><a href="https://github.com/Hafiidz/latent-diffusion/blob/main/LICENSE">LDSR</a></h2>
<small>Code added by contirubtors, most likely copied from this repository.</small>
<pre>
MIT License
Copyright (c) 2022 Machine Vision and Learning Group, LMU Munich
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
</pre>
<h2><a href="https://github.com/pharmapsychotic/clip-interrogator/blob/main/LICENSE">CLIP Interrogator</a></h2>
<small>Some small amounts of code borrowed and reworked.</small>
<pre>
MIT License
Copyright (c) 2022 pharmapsychotic
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
</pre>
<h2><a href="https://github.com/AminRezaei0x443/memory-efficient-attention/blob/main/LICENSE">Memory Efficient Attention</a></h2>
<small>The sub-quadratic cross attention optimization uses modified code from the Memory Efficient Attention package that Alex Birch optimized for 3D tensors. This license is updated to reflect that.</small>
<pre>
MIT License
Copyright (c) 2023 Alex Birch
Copyright (c) 2023 Amin Rezaei
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
</pre>
<h2><a href="https://github.com/huggingface/diffusers/blob/c7da8fd23359a22d0df2741688b5b4f33c26df21/LICENSE">Scaled Dot Product Attention</a></h2>
<small>Some small amounts of code borrowed and reworked.</small>
<pre>
Copyright 2023 The HuggingFace Team. All rights reserved.
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
</pre>
<h2><a href="https://github.com/explosion/curated-transformers/blob/main/LICENSE">Curated transformers</a></h2>
<small>The MPS workaround for nn.Linear on macOS 13.2.X is based on the MPS workaround for nn.Linear created by danieldk for Curated transformers</small>
<pre>
The MIT License (MIT)
Copyright (C) 2021 ExplosionAI GmbH
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in
all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
THE SOFTWARE.
</pre>
<h2><a href="https://github.com/madebyollin/taesd/blob/main/LICENSE">TAESD</a></h2>
<small>Tiny AutoEncoder for Stable Diffusion option for live previews</small>
<pre>
MIT License
Copyright (c) 2023 Ollin Boer Bohan
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
</pre>

113
javascript/aspectRatioOverlay.js Normal file
View File

@ -0,0 +1,113 @@
let currentWidth = null;
let currentHeight = null;
let arFrameTimeout = setTimeout(function() {}, 0);
function dimensionChange(e, is_width, is_height) {
if (is_width) {
currentWidth = e.target.value * 1.0;
}
if (is_height) {
currentHeight = e.target.value * 1.0;
}
var inImg2img = gradioApp().querySelector("#tab_img2img").style.display == "block";
if (!inImg2img) {
return;
}
var targetElement = null;
var tabIndex = get_tab_index('mode_img2img');
if (tabIndex == 0) { // img2img
targetElement = gradioApp().querySelector('#img2img_image div[data-testid=image] img');
} else if (tabIndex == 1) { //Sketch
targetElement = gradioApp().querySelector('#img2img_sketch div[data-testid=image] img');
} else if (tabIndex == 2) { // Inpaint
targetElement = gradioApp().querySelector('#img2maskimg div[data-testid=image] img');
} else if (tabIndex == 3) { // Inpaint sketch
targetElement = gradioApp().querySelector('#inpaint_sketch div[data-testid=image] img');
}
if (targetElement) {
var arPreviewRect = gradioApp().querySelector('#imageARPreview');
if (!arPreviewRect) {
arPreviewRect = document.createElement('div');
arPreviewRect.id = "imageARPreview";
gradioApp().appendChild(arPreviewRect);
}
var viewportOffset = targetElement.getBoundingClientRect();
var viewportscale = Math.min(targetElement.clientWidth / targetElement.naturalWidth, targetElement.clientHeight / targetElement.naturalHeight);
var scaledx = targetElement.naturalWidth * viewportscale;
var scaledy = targetElement.naturalHeight * viewportscale;
var clientRectTop = (viewportOffset.top + window.scrollY);
var clientRectLeft = (viewportOffset.left + window.scrollX);
var clientRectCentreY = clientRectTop + (targetElement.clientHeight / 2);
var clientRectCentreX = clientRectLeft + (targetElement.clientWidth / 2);
var arscale = Math.min(scaledx / currentWidth, scaledy / currentHeight);
var arscaledx = currentWidth * arscale;
var arscaledy = currentHeight * arscale;
var arRectTop = clientRectCentreY - (arscaledy / 2);
var arRectLeft = clientRectCentreX - (arscaledx / 2);
var arRectWidth = arscaledx;
var arRectHeight = arscaledy;
arPreviewRect.style.top = arRectTop + 'px';
arPreviewRect.style.left = arRectLeft + 'px';
arPreviewRect.style.width = arRectWidth + 'px';
arPreviewRect.style.height = arRectHeight + 'px';
clearTimeout(arFrameTimeout);
arFrameTimeout = setTimeout(function() {
arPreviewRect.style.display = 'none';
}, 2000);
arPreviewRect.style.display = 'block';
}
}
onAfterUiUpdate(function() {
var arPreviewRect = gradioApp().querySelector('#imageARPreview');
if (arPreviewRect) {
arPreviewRect.style.display = 'none';
}
var tabImg2img = gradioApp().querySelector("#tab_img2img");
if (tabImg2img) {
var inImg2img = tabImg2img.style.display == "block";
if (inImg2img) {
let inputs = gradioApp().querySelectorAll('input');
inputs.forEach(function(e) {
var is_width = e.parentElement.id == "img2img_width";
var is_height = e.parentElement.id == "img2img_height";
if ((is_width || is_height) && !e.classList.contains('scrollwatch')) {
e.addEventListener('input', function(e) {
dimensionChange(e, is_width, is_height);
});
e.classList.add('scrollwatch');
}
if (is_width) {
currentWidth = e.value * 1.0;
}
if (is_height) {
currentHeight = e.value * 1.0;
}
});
}
}
});

163
javascript/contextMenus.js Normal file
View File

@ -0,0 +1,163 @@
var contextMenuInit = function() {
let eventListenerApplied = false;
let menuSpecs = new Map();
const uid = function() {
return Date.now().toString(36) + Math.random().toString(36).substring(2);
};
function showContextMenu(event, element, menuEntries) {
let oldMenu = gradioApp().querySelector('#context-menu');
if (oldMenu) {
oldMenu.remove();
}
let baseStyle = window.getComputedStyle(uiCurrentTab);
const contextMenu = document.createElement('nav');
contextMenu.id = "context-menu";
contextMenu.style.background = baseStyle.background;
contextMenu.style.color = baseStyle.color;
contextMenu.style.fontFamily = baseStyle.fontFamily;
contextMenu.style.top = event.pageY + 'px';
contextMenu.style.left = event.pageX + 'px';
const contextMenuList = document.createElement('ul');
contextMenuList.className = 'context-menu-items';
contextMenu.append(contextMenuList);
menuEntries.forEach(function(entry) {
let contextMenuEntry = document.createElement('a');
contextMenuEntry.innerHTML = entry['name'];
contextMenuEntry.addEventListener("click", function() {
entry['func']();
});
contextMenuList.append(contextMenuEntry);
});
gradioApp().appendChild(contextMenu);
}
function appendContextMenuOption(targetElementSelector, entryName, entryFunction) {
var currentItems = menuSpecs.get(targetElementSelector);
if (!currentItems) {
currentItems = [];
menuSpecs.set(targetElementSelector, currentItems);
}
let newItem = {
id: targetElementSelector + '_' + uid(),
name: entryName,
func: entryFunction,
isNew: true
};
currentItems.push(newItem);
return newItem['id'];
}
function removeContextMenuOption(uid) {
menuSpecs.forEach(function(v) {
let index = -1;
v.forEach(function(e, ei) {
if (e['id'] == uid) {
index = ei;
}
});
if (index >= 0) {
v.splice(index, 1);
}
});
}
function addContextMenuEventListener() {
if (eventListenerApplied) {
return;
}
gradioApp().addEventListener("click", function(e) {
if (!e.isTrusted) {
return;
}
let oldMenu = gradioApp().querySelector('#context-menu');
if (oldMenu) {
oldMenu.remove();
}
});
['contextmenu', 'touchstart'].forEach((eventType) => {
gradioApp().addEventListener(eventType, function(e) {
let ev = e;
if (eventType.startsWith('touch')) {
if (e.touches.length !== 2) return;
ev = e.touches[0];
}
let oldMenu = gradioApp().querySelector('#context-menu');
if (oldMenu) {
oldMenu.remove();
}
menuSpecs.forEach(function(v, k) {
if (e.composedPath()[0].matches(k)) {
showContextMenu(ev, e.composedPath()[0], v);
e.preventDefault();
}
});
});
});
eventListenerApplied = true;
}
return [appendContextMenuOption, removeContextMenuOption, addContextMenuEventListener];
};
var initResponse = contextMenuInit();
var appendContextMenuOption = initResponse[0];
var removeContextMenuOption = initResponse[1];
var addContextMenuEventListener = initResponse[2];
(function() {
//Start example Context Menu Items
let generateOnRepeat = function(genbuttonid, interruptbuttonid) {
let genbutton = gradioApp().querySelector(genbuttonid);
let interruptbutton = gradioApp().querySelector(interruptbuttonid);
if (!interruptbutton.offsetParent) {
genbutton.click();
}
clearInterval(window.generateOnRepeatInterval);
window.generateOnRepeatInterval = setInterval(function() {
if (!interruptbutton.offsetParent) {
genbutton.click();
}
},
500);
};
let generateOnRepeat_txt2img = function() {
generateOnRepeat('#txt2img_generate', '#txt2img_interrupt');
};
let generateOnRepeat_img2img = function() {
generateOnRepeat('#img2img_generate', '#img2img_interrupt');
};
appendContextMenuOption('#txt2img_generate', 'Generate forever', generateOnRepeat_txt2img);
appendContextMenuOption('#txt2img_interrupt', 'Generate forever', generateOnRepeat_txt2img);
appendContextMenuOption('#img2img_generate', 'Generate forever', generateOnRepeat_img2img);
appendContextMenuOption('#img2img_interrupt', 'Generate forever', generateOnRepeat_img2img);
let cancelGenerateForever = function() {
clearInterval(window.generateOnRepeatInterval);
};
appendContextMenuOption('#txt2img_interrupt', 'Cancel generate forever', cancelGenerateForever);
appendContextMenuOption('#txt2img_generate', 'Cancel generate forever', cancelGenerateForever);
appendContextMenuOption('#img2img_interrupt', 'Cancel generate forever', cancelGenerateForever);
appendContextMenuOption('#img2img_generate', 'Cancel generate forever', cancelGenerateForever);
})();
//End example Context Menu Items
onAfterUiUpdate(addContextMenuEventListener);

156
javascript/dragdrop.js vendored Normal file
View File

@ -0,0 +1,156 @@
// allows drag-dropping files into gradio image elements, and also pasting images from clipboard
function isValidImageList(files) {
return files && files?.length === 1 && ['image/png', 'image/gif', 'image/jpeg'].includes(files[0].type);
}
function dropReplaceImage(imgWrap, files) {
if (!isValidImageList(files)) {
return;
}
const tmpFile = files[0];
imgWrap.querySelector('.modify-upload button + button, .touch-none + div button + button')?.click();
const callback = () => {
const fileInput = imgWrap.querySelector('input[type="file"]');
if (fileInput) {
if (files.length === 0) {
files = new DataTransfer();
files.items.add(tmpFile);
fileInput.files = files.files;
} else {
fileInput.files = files;
}
fileInput.dispatchEvent(new Event('change'));
}
};
if (imgWrap.closest('#pnginfo_image')) {
// special treatment for PNG Info tab, wait for fetch request to finish
const oldFetch = window.fetch;
window.fetch = async(input, options) => {
const response = await oldFetch(input, options);
if ('api/predict/' === input) {
const content = await response.text();
window.fetch = oldFetch;
window.requestAnimationFrame(() => callback());
return new Response(content, {
status: response.status,
statusText: response.statusText,
headers: response.headers
});
}
return response;
};
} else {
window.requestAnimationFrame(() => callback());
}
}
function eventHasFiles(e) {
if (!e.dataTransfer || !e.dataTransfer.files) return false;
if (e.dataTransfer.files.length > 0) return true;
if (e.dataTransfer.items.length > 0 && e.dataTransfer.items[0].kind == "file") return true;
return false;
}
function isURL(url) {
try {
const _ = new URL(url);
return true;
} catch {
return false;
}
}
function dragDropTargetIsPrompt(target) {
if (target?.placeholder && target?.placeholder.indexOf("Prompt") >= 0) return true;
if (target?.parentNode?.parentNode?.className?.indexOf("prompt") > 0) return true;
return false;
}
window.document.addEventListener('dragover', e => {
const target = e.composedPath()[0];
if (!eventHasFiles(e)) return;
var targetImage = target.closest('[data-testid="image"]');
if (!dragDropTargetIsPrompt(target) && !targetImage) return;
e.stopPropagation();
e.preventDefault();
e.dataTransfer.dropEffect = 'copy';
});
window.document.addEventListener('drop', async e => {
const target = e.composedPath()[0];
const url = e.dataTransfer.getData('text/uri-list') || e.dataTransfer.getData('text/plain');
if (!eventHasFiles(e) && !isURL(url)) return;
if (dragDropTargetIsPrompt(target)) {
e.stopPropagation();
e.preventDefault();
const isImg2img = get_tab_index('tabs') == 1;
let prompt_image_target = isImg2img ? "img2img_prompt_image" : "txt2img_prompt_image";
const imgParent = gradioApp().getElementById(prompt_image_target);
const files = e.dataTransfer.files;
const fileInput = imgParent.querySelector('input[type="file"]');
if (eventHasFiles(e) && fileInput) {
fileInput.files = files;
fileInput.dispatchEvent(new Event('change'));
} else if (url) {
try {
const request = await fetch(url);
if (!request.ok) {
console.error('Error fetching URL:', url, request.status);
return;
}
const data = new DataTransfer();
data.items.add(new File([await request.blob()], 'image.png'));
fileInput.files = data.files;
fileInput.dispatchEvent(new Event('change'));
} catch (error) {
console.error('Error fetching URL:', url, error);
return;
}
}
}
var targetImage = target.closest('[data-testid="image"]');
if (targetImage) {
e.stopPropagation();
e.preventDefault();
const files = e.dataTransfer.files;
dropReplaceImage(targetImage, files);
return;
}
});
window.addEventListener('paste', e => {
const files = e.clipboardData.files;
if (!isValidImageList(files)) {
return;
}
const visibleImageFields = [...gradioApp().querySelectorAll('[data-testid="image"]')]
.filter(el => uiElementIsVisible(el))
.sort((a, b) => uiElementInSight(b) - uiElementInSight(a));
if (!visibleImageFields.length) {
return;
}
const firstFreeImageField = visibleImageFields
.filter(el => !el.querySelector('img'))?.[0];
dropReplaceImage(
firstFreeImageField ?
firstFreeImageField :
visibleImageFields[visibleImageFields.length - 1]
, files
);
});

156
javascript/edit-attention.js Normal file
View File

@ -0,0 +1,156 @@
function keyupEditAttention(event) {
let target = event.originalTarget || event.composedPath()[0];
if (!target.matches("*:is([id*='_toprow'] [id*='_prompt'], .prompt) textarea")) return;
if (!(event.metaKey || event.ctrlKey)) return;
let isPlus = event.key == "ArrowUp";
let isMinus = event.key == "ArrowDown";
if (!isPlus && !isMinus) return;
let selectionStart = target.selectionStart;
let selectionEnd = target.selectionEnd;
let text = target.value;
function selectCurrentParenthesisBlock(OPEN, CLOSE) {
if (selectionStart !== selectionEnd) return false;
// Find opening parenthesis around current cursor
const before = text.substring(0, selectionStart);
let beforeParen = before.lastIndexOf(OPEN);
if (beforeParen == -1) return false;
let beforeClosingParen = before.lastIndexOf(CLOSE);
if (beforeClosingParen != -1 && beforeClosingParen > beforeParen) return false;
// Find closing parenthesis around current cursor
const after = text.substring(selectionStart);
let afterParen = after.indexOf(CLOSE);
if (afterParen == -1) return false;
let afterOpeningParen = after.indexOf(OPEN);
if (afterOpeningParen != -1 && afterOpeningParen < afterParen) return false;
// Set the selection to the text between the parenthesis
const parenContent = text.substring(beforeParen + 1, selectionStart + afterParen);
if (/.*:-?[\d.]+/s.test(parenContent)) {
const lastColon = parenContent.lastIndexOf(":");
selectionStart = beforeParen + 1;
selectionEnd = selectionStart + lastColon;
} else {
selectionStart = beforeParen + 1;
selectionEnd = selectionStart + parenContent.length;
}
target.setSelectionRange(selectionStart, selectionEnd);
return true;
}
function selectCurrentWord() {
if (selectionStart !== selectionEnd) return false;
const whitespace_delimiters = {"Tab": "\t", "Carriage Return": "\r", "Line Feed": "\n"};
let delimiters = opts.keyedit_delimiters;
for (let i of opts.keyedit_delimiters_whitespace) {
delimiters += whitespace_delimiters[i];
}
// seek backward to find beginning
while (!delimiters.includes(text[selectionStart - 1]) && selectionStart > 0) {
selectionStart--;
}
// seek forward to find end
while (!delimiters.includes(text[selectionEnd]) && selectionEnd < text.length) {
selectionEnd++;
}
// deselect surrounding whitespace
while (text[selectionStart] == " " && selectionStart < selectionEnd) {
selectionStart++;
}
while (text[selectionEnd - 1] == " " && selectionEnd > selectionStart) {
selectionEnd--;
}
target.setSelectionRange(selectionStart, selectionEnd);
return true;
}
// If the user hasn't selected anything, let's select their current parenthesis block or word
if (!selectCurrentParenthesisBlock('<', '>') && !selectCurrentParenthesisBlock('(', ')') && !selectCurrentParenthesisBlock('[', ']')) {
selectCurrentWord();
}
event.preventDefault();
var closeCharacter = ')';
var delta = opts.keyedit_precision_attention;
var start = selectionStart > 0 ? text[selectionStart - 1] : "";
var end = text[selectionEnd];
if (start == '<') {
closeCharacter = '>';
delta = opts.keyedit_precision_extra;
} else if (start == '(' && end == ')' || start == '[' && end == ']') { // convert old-style (((emphasis)))
let numParen = 0;
while (text[selectionStart - numParen - 1] == start && text[selectionEnd + numParen] == end) {
numParen++;
}
if (start == "[") {
weight = (1 / 1.1) ** numParen;
} else {
weight = 1.1 ** numParen;
}
weight = Math.round(weight / opts.keyedit_precision_attention) * opts.keyedit_precision_attention;
text = text.slice(0, selectionStart - numParen) + "(" + text.slice(selectionStart, selectionEnd) + ":" + weight + ")" + text.slice(selectionEnd + numParen);
selectionStart -= numParen - 1;
selectionEnd -= numParen - 1;
} else if (start != '(') {
// do not include spaces at the end
while (selectionEnd > selectionStart && text[selectionEnd - 1] == ' ') {
selectionEnd--;
}
if (selectionStart == selectionEnd) {
return;
}
text = text.slice(0, selectionStart) + "(" + text.slice(selectionStart, selectionEnd) + ":1.0)" + text.slice(selectionEnd);
selectionStart++;
selectionEnd++;
}
if (text[selectionEnd] != ':') return;
var weightLength = text.slice(selectionEnd + 1).indexOf(closeCharacter) + 1;
var weight = parseFloat(text.slice(selectionEnd + 1, selectionEnd + weightLength));
if (isNaN(weight)) return;
weight += isPlus ? delta : -delta;
weight = parseFloat(weight.toPrecision(12));
if (Number.isInteger(weight)) weight += ".0";
if (closeCharacter == ')' && weight == 1) {
var endParenPos = text.substring(selectionEnd).indexOf(')');
text = text.slice(0, selectionStart - 1) + text.slice(selectionStart, selectionEnd) + text.slice(selectionEnd + endParenPos + 1);
selectionStart--;
selectionEnd--;
} else {
text = text.slice(0, selectionEnd + 1) + weight + text.slice(selectionEnd + weightLength);
}
target.focus();
target.value = text;
target.selectionStart = selectionStart;
target.selectionEnd = selectionEnd;
updateInput(target);
}
addEventListener('keydown', (event) => {
keyupEditAttention(event);
});

41
javascript/edit-order.js Normal file
View File

@ -0,0 +1,41 @@
/* alt+left/right moves text in prompt */
function keyupEditOrder(event) {
if (!opts.keyedit_move) return;
let target = event.originalTarget || event.composedPath()[0];
if (!target.matches("*:is([id*='_toprow'] [id*='_prompt'], .prompt) textarea")) return;
if (!event.altKey) return;
let isLeft = event.key == "ArrowLeft";
let isRight = event.key == "ArrowRight";
if (!isLeft && !isRight) return;
event.preventDefault();
let selectionStart = target.selectionStart;
let selectionEnd = target.selectionEnd;
let text = target.value;
let items = text.split(",");
let indexStart = (text.slice(0, selectionStart).match(/,/g) || []).length;
let indexEnd = (text.slice(0, selectionEnd).match(/,/g) || []).length;
let range = indexEnd - indexStart + 1;
if (isLeft && indexStart > 0) {
items.splice(indexStart - 1, 0, ...items.splice(indexStart, range));
target.value = items.join();
target.selectionStart = items.slice(0, indexStart - 1).join().length + (indexStart == 1 ? 0 : 1);
target.selectionEnd = items.slice(0, indexEnd).join().length;
} else if (isRight && indexEnd < items.length - 1) {
items.splice(indexStart + 1, 0, ...items.splice(indexStart, range));
target.value = items.join();
target.selectionStart = items.slice(0, indexStart + 1).join().length + 1;
target.selectionEnd = items.slice(0, indexEnd + 2).join().length;
}
event.preventDefault();
updateInput(target);
}
addEventListener('keydown', (event) => {
keyupEditOrder(event);
});

95
javascript/extensions.js Normal file
View File

@ -0,0 +1,95 @@
function extensions_apply(_disabled_list, _update_list, disable_all) {
var disable = [];
var update = [];
const extensions_input = gradioApp().querySelectorAll('#extensions input[type="checkbox"]');
if (extensions_input.length == 0) {
throw Error("Extensions page not yet loaded.");
}
extensions_input.forEach(function(x) {
if (x.name.startsWith("enable_") && !x.checked) {
disable.push(x.name.substring(7));
}
if (x.name.startsWith("update_") && x.checked) {
update.push(x.name.substring(7));
}
});
restart_reload();
return [JSON.stringify(disable), JSON.stringify(update), disable_all];
}
function extensions_check() {
var disable = [];
gradioApp().querySelectorAll('#extensions input[type="checkbox"]').forEach(function(x) {
if (x.name.startsWith("enable_") && !x.checked) {
disable.push(x.name.substring(7));
}
});
gradioApp().querySelectorAll('#extensions .extension_status').forEach(function(x) {
x.innerHTML = "Loading...";
});
var id = randomId();
requestProgress(id, gradioApp().getElementById('extensions_installed_html'), null, function() {
});
return [id, JSON.stringify(disable)];
}
function install_extension_from_index(button, url) {
button.disabled = "disabled";
button.value = "Installing...";
var textarea = gradioApp().querySelector('#extension_to_install textarea');
textarea.value = url;
updateInput(textarea);
gradioApp().querySelector('#install_extension_button').click();
}
function config_state_confirm_restore(_, config_state_name, config_restore_type) {
if (config_state_name == "Current") {
return [false, config_state_name, config_restore_type];
}
let restored = "";
if (config_restore_type == "extensions") {
restored = "all saved extension versions";
} else if (config_restore_type == "webui") {
restored = "the webui version";
} else {
restored = "the webui version and all saved extension versions";
}
let confirmed = confirm("Are you sure you want to restore from this state?\nThis will reset " + restored + ".");
if (confirmed) {
restart_reload();
gradioApp().querySelectorAll('#extensions .extension_status').forEach(function(x) {
x.innerHTML = "Loading...";
});
}
return [confirmed, config_state_name, config_restore_type];
}
function toggle_all_extensions(event) {
gradioApp().querySelectorAll('#extensions .extension_toggle').forEach(function(checkbox_el) {
checkbox_el.checked = event.target.checked;
});
}
function toggle_extension() {
let all_extensions_toggled = true;
for (const checkbox_el of gradioApp().querySelectorAll('#extensions .extension_toggle')) {
if (!checkbox_el.checked) {
all_extensions_toggled = false;
break;
}
}
gradioApp().querySelector('#extensions .all_extensions_toggle').checked = all_extensions_toggled;
}

712
javascript/extraNetworks.js Normal file
View File

@ -0,0 +1,712 @@
function toggleCss(key, css, enable) {
var style = document.getElementById(key);
if (enable && !style) {
style = document.createElement('style');
style.id = key;
style.type = 'text/css';
document.head.appendChild(style);
}
if (style && !enable) {
document.head.removeChild(style);
}
if (style) {
style.innerHTML == '';
style.appendChild(document.createTextNode(css));
}
}
function setupExtraNetworksForTab(tabname) {
function registerPrompt(tabname, id) {
var textarea = gradioApp().querySelector("#" + id + " > label > textarea");
if (!activePromptTextarea[tabname]) {
activePromptTextarea[tabname] = textarea;
}
textarea.addEventListener("focus", function() {
activePromptTextarea[tabname] = textarea;
});
}
var tabnav = gradioApp().querySelector('#' + tabname + '_extra_tabs > div.tab-nav');
var controlsDiv = document.createElement('DIV');
controlsDiv.classList.add('extra-networks-controls-div');
tabnav.appendChild(controlsDiv);
tabnav.insertBefore(controlsDiv, null);
var this_tab = gradioApp().querySelector('#' + tabname + '_extra_tabs');
this_tab.querySelectorAll(":scope > [id^='" + tabname + "_']").forEach(function(elem) {
// tabname_full = {tabname}_{extra_networks_tabname}
var tabname_full = elem.id;
var search = gradioApp().querySelector("#" + tabname_full + "_extra_search");
var sort_dir = gradioApp().querySelector("#" + tabname_full + "_extra_sort_dir");
var refresh = gradioApp().querySelector("#" + tabname_full + "_extra_refresh");
var currentSort = '';
// If any of the buttons above don't exist, we want to skip this iteration of the loop.
if (!search || !sort_dir || !refresh) {
return; // `return` is equivalent of `continue` but for forEach loops.
}
var applyFilter = function(force) {
var searchTerm = search.value.toLowerCase();
gradioApp().querySelectorAll('#' + tabname + '_extra_tabs div.card').forEach(function(elem) {
var searchOnly = elem.querySelector('.search_only');
var text = Array.prototype.map.call(elem.querySelectorAll('.search_terms, .description'), function(t) {
return t.textContent.toLowerCase();
}).join(" ");
var visible = text.indexOf(searchTerm) != -1;
if (searchOnly && searchTerm.length < 4) {
visible = false;
}
if (visible) {
elem.classList.remove("hidden");
} else {
elem.classList.add("hidden");
}
});
applySort(force);
};
var applySort = function(force) {
var cards = gradioApp().querySelectorAll('#' + tabname_full + ' div.card');
var parent = gradioApp().querySelector('#' + tabname_full + "_cards");
var reverse = sort_dir.dataset.sortdir == "Descending";
var activeSearchElem = gradioApp().querySelector('#' + tabname_full + "_controls .extra-network-control--sort.extra-network-control--enabled");
var sortKey = activeSearchElem ? activeSearchElem.dataset.sortkey : "default";
var sortKeyDataField = "sort" + sortKey.charAt(0).toUpperCase() + sortKey.slice(1);
var sortKeyStore = sortKey + "-" + sort_dir.dataset.sortdir + "-" + cards.length;
if (sortKeyStore == currentSort && !force) {
return;
}
currentSort = sortKeyStore;
var sortedCards = Array.from(cards);
sortedCards.sort(function(cardA, cardB) {
var a = cardA.dataset[sortKeyDataField];
var b = cardB.dataset[sortKeyDataField];
if (!isNaN(a) && !isNaN(b)) {
return parseInt(a) - parseInt(b);
}
return (a < b ? -1 : (a > b ? 1 : 0));
});
if (reverse) {
sortedCards.reverse();
}
parent.innerHTML = '';
var frag = document.createDocumentFragment();
sortedCards.forEach(function(card) {
frag.appendChild(card);
});
parent.appendChild(frag);
};
search.addEventListener("input", function() {
applyFilter();
});
applySort();
applyFilter();
extraNetworksApplySort[tabname_full] = applySort;
extraNetworksApplyFilter[tabname_full] = applyFilter;
var controls = gradioApp().querySelector("#" + tabname_full + "_controls");
controlsDiv.insertBefore(controls, null);
if (elem.style.display != "none") {
extraNetworksShowControlsForPage(tabname, tabname_full);
}
});
registerPrompt(tabname, tabname + "_prompt");
registerPrompt(tabname, tabname + "_neg_prompt");
}
function extraNetworksMovePromptToTab(tabname, id, showPrompt, showNegativePrompt) {
if (!gradioApp().querySelector('.toprow-compact-tools')) return; // only applicable for compact prompt layout
var promptContainer = gradioApp().getElementById(tabname + '_prompt_container');
var prompt = gradioApp().getElementById(tabname + '_prompt_row');
var negPrompt = gradioApp().getElementById(tabname + '_neg_prompt_row');
var elem = id ? gradioApp().getElementById(id) : null;
if (showNegativePrompt && elem) {
elem.insertBefore(negPrompt, elem.firstChild);
} else {
promptContainer.insertBefore(negPrompt, promptContainer.firstChild);
}
if (showPrompt && elem) {
elem.insertBefore(prompt, elem.firstChild);
} else {
promptContainer.insertBefore(prompt, promptContainer.firstChild);
}
if (elem) {
elem.classList.toggle('extra-page-prompts-active', showNegativePrompt || showPrompt);
}
}
function extraNetworksShowControlsForPage(tabname, tabname_full) {
gradioApp().querySelectorAll('#' + tabname + '_extra_tabs .extra-networks-controls-div > div').forEach(function(elem) {
var targetId = tabname_full + "_controls";
elem.style.display = elem.id == targetId ? "" : "none";
});
}
function extraNetworksUnrelatedTabSelected(tabname) { // called from python when user selects an unrelated tab (generate)
extraNetworksMovePromptToTab(tabname, '', false, false);
extraNetworksShowControlsForPage(tabname, null);
}
function extraNetworksTabSelected(tabname, id, showPrompt, showNegativePrompt, tabname_full) { // called from python when user selects an extra networks tab
extraNetworksMovePromptToTab(tabname, id, showPrompt, showNegativePrompt);
extraNetworksShowControlsForPage(tabname, tabname_full);
}
function applyExtraNetworkFilter(tabname_full) {
var doFilter = function() {
var applyFunction = extraNetworksApplyFilter[tabname_full];
if (applyFunction) {
applyFunction(true);
}
};
setTimeout(doFilter, 1);
}
function applyExtraNetworkSort(tabname_full) {
var doSort = function() {
extraNetworksApplySort[tabname_full](true);
};
setTimeout(doSort, 1);
}
var extraNetworksApplyFilter = {};
var extraNetworksApplySort = {};
var activePromptTextarea = {};
function setupExtraNetworks() {
setupExtraNetworksForTab('txt2img');
setupExtraNetworksForTab('img2img');
}
var re_extranet = /<([^:^>]+:[^:]+):[\d.]+>(.*)/;
var re_extranet_g = /<([^:^>]+:[^:]+):[\d.]+>/g;
var re_extranet_neg = /\(([^:^>]+:[\d.]+)\)/;
var re_extranet_g_neg = /\(([^:^>]+:[\d.]+)\)/g;
function tryToRemoveExtraNetworkFromPrompt(textarea, text, isNeg) {
var m = text.match(isNeg ? re_extranet_neg : re_extranet);
var replaced = false;
var newTextareaText;
var extraTextBeforeNet = opts.extra_networks_add_text_separator;
if (m) {
var extraTextAfterNet = m[2];
var partToSearch = m[1];
var foundAtPosition = -1;
newTextareaText = textarea.value.replaceAll(isNeg ? re_extranet_g_neg : re_extranet_g, function(found, net, pos) {
m = found.match(isNeg ? re_extranet_neg : re_extranet);
if (m[1] == partToSearch) {
replaced = true;
foundAtPosition = pos;
return "";
}
return found;
});
if (foundAtPosition >= 0) {
if (extraTextAfterNet && newTextareaText.substr(foundAtPosition, extraTextAfterNet.length) == extraTextAfterNet) {
newTextareaText = newTextareaText.substr(0, foundAtPosition) + newTextareaText.substr(foundAtPosition + extraTextAfterNet.length);
}
if (newTextareaText.substr(foundAtPosition - extraTextBeforeNet.length, extraTextBeforeNet.length) == extraTextBeforeNet) {
newTextareaText = newTextareaText.substr(0, foundAtPosition - extraTextBeforeNet.length) + newTextareaText.substr(foundAtPosition);
}
}
} else {
newTextareaText = textarea.value.replaceAll(new RegExp(`((?:${extraTextBeforeNet})?${text})`, "g"), "");
replaced = (newTextareaText != textarea.value);
}
if (replaced) {
textarea.value = newTextareaText;
return true;
}
return false;
}
function updatePromptArea(text, textArea, isNeg) {
if (!tryToRemoveExtraNetworkFromPrompt(textArea, text, isNeg)) {
textArea.value = textArea.value + opts.extra_networks_add_text_separator + text;
}
updateInput(textArea);
}
function cardClicked(tabname, textToAdd, textToAddNegative, allowNegativePrompt) {
if (textToAddNegative.length > 0) {
updatePromptArea(textToAdd, gradioApp().querySelector("#" + tabname + "_prompt > label > textarea"));
updatePromptArea(textToAddNegative, gradioApp().querySelector("#" + tabname + "_neg_prompt > label > textarea"), true);
} else {
var textarea = allowNegativePrompt ? activePromptTextarea[tabname] : gradioApp().querySelector("#" + tabname + "_prompt > label > textarea");
updatePromptArea(textToAdd, textarea);
}
}
function saveCardPreview(event, tabname, filename) {
var textarea = gradioApp().querySelector("#" + tabname + '_preview_filename > label > textarea');
var button = gradioApp().getElementById(tabname + '_save_preview');
textarea.value = filename;
updateInput(textarea);
button.click();
event.stopPropagation();
event.preventDefault();
}
function extraNetworksSearchButton(tabname, extra_networks_tabname, event) {
var searchTextarea = gradioApp().querySelector("#" + tabname + "_" + extra_networks_tabname + "_extra_search");
var button = event.target;
var text = button.classList.contains("search-all") ? "" : button.textContent.trim();
searchTextarea.value = text;
updateInput(searchTextarea);
}
function extraNetworksTreeProcessFileClick(event, btn, tabname, extra_networks_tabname) {
/**
* Processes `onclick` events when user clicks on files in tree.
*
* @param event The generated event.
* @param btn The clicked `tree-list-item` button.
* @param tabname The name of the active tab in the sd webui. Ex: txt2img, img2img, etc.
* @param extra_networks_tabname The id of the active extraNetworks tab. Ex: lora, checkpoints, etc.
*/
// NOTE: Currently unused.
return;
}
function extraNetworksTreeProcessDirectoryClick(event, btn, tabname, extra_networks_tabname) {
/**
* Processes `onclick` events when user clicks on directories in tree.
*
* Here is how the tree reacts to clicks for various states:
* unselected unopened directory: Directory is selected and expanded.
* unselected opened directory: Directory is selected.
* selected opened directory: Directory is collapsed and deselected.
* chevron is clicked: Directory is expanded or collapsed. Selected state unchanged.
*
* @param event The generated event.
* @param btn The clicked `tree-list-item` button.
* @param tabname The name of the active tab in the sd webui. Ex: txt2img, img2img, etc.
* @param extra_networks_tabname The id of the active extraNetworks tab. Ex: lora, checkpoints, etc.
*/
var ul = btn.nextElementSibling;
// This is the actual target that the user clicked on within the target button.
// We use this to detect if the chevron was clicked.
var true_targ = event.target;
function _expand_or_collapse(_ul, _btn) {
// Expands <ul> if it is collapsed, collapses otherwise. Updates button attributes.
if (_ul.hasAttribute("hidden")) {
_ul.removeAttribute("hidden");
_btn.dataset.expanded = "";
} else {
_ul.setAttribute("hidden", "");
delete _btn.dataset.expanded;
}
}
function _remove_selected_from_all() {
// Removes the `selected` attribute from all buttons.
var sels = document.querySelectorAll("div.tree-list-content");
[...sels].forEach(el => {
delete el.dataset.selected;
});
}
function _select_button(_btn) {
// Removes `data-selected` attribute from all buttons then adds to passed button.
_remove_selected_from_all();
_btn.dataset.selected = "";
}
function _update_search(_tabname, _extra_networks_tabname, _search_text) {
// Update search input with select button's path.
var search_input_elem = gradioApp().querySelector("#" + tabname + "_" + extra_networks_tabname + "_extra_search");
search_input_elem.value = _search_text;
updateInput(search_input_elem);
}
// If user clicks on the chevron, then we do not select the folder.
if (true_targ.matches(".tree-list-item-action--leading, .tree-list-item-action-chevron")) {
_expand_or_collapse(ul, btn);
} else {
// User clicked anywhere else on the button.
if ("selected" in btn.dataset && !(ul.hasAttribute("hidden"))) {
// If folder is select and open, collapse and deselect button.
_expand_or_collapse(ul, btn);
delete btn.dataset.selected;
_update_search(tabname, extra_networks_tabname, "");
} else if (!(!("selected" in btn.dataset) && !(ul.hasAttribute("hidden")))) {
// If folder is open and not selected, then we don't collapse; just select.
// NOTE: Double inversion sucks but it is the clearest way to show the branching here.
_expand_or_collapse(ul, btn);
_select_button(btn, tabname, extra_networks_tabname);
_update_search(tabname, extra_networks_tabname, btn.dataset.path);
} else {
// All other cases, just select the button.
_select_button(btn, tabname, extra_networks_tabname);
_update_search(tabname, extra_networks_tabname, btn.dataset.path);
}
}
}
function extraNetworksTreeOnClick(event, tabname, extra_networks_tabname) {
/**
* Handles `onclick` events for buttons within an `extra-network-tree .tree-list--tree`.
*
* Determines whether the clicked button in the tree is for a file entry or a directory
* then calls the appropriate function.
*
* @param event The generated event.
* @param tabname The name of the active tab in the sd webui. Ex: txt2img, img2img, etc.
* @param extra_networks_tabname The id of the active extraNetworks tab. Ex: lora, checkpoints, etc.
*/
var btn = event.currentTarget;
var par = btn.parentElement;
if (par.dataset.treeEntryType === "file") {
extraNetworksTreeProcessFileClick(event, btn, tabname, extra_networks_tabname);
} else {
extraNetworksTreeProcessDirectoryClick(event, btn, tabname, extra_networks_tabname);
}
}
function extraNetworksControlSortOnClick(event, tabname, extra_networks_tabname) {
/** Handles `onclick` events for Sort Mode buttons. */
var self = event.currentTarget;
var parent = event.currentTarget.parentElement;
parent.querySelectorAll('.extra-network-control--sort').forEach(function(x) {
x.classList.remove('extra-network-control--enabled');
});
self.classList.add('extra-network-control--enabled');
applyExtraNetworkSort(tabname + "_" + extra_networks_tabname);
}
function extraNetworksControlSortDirOnClick(event, tabname, extra_networks_tabname) {
/**
* Handles `onclick` events for the Sort Direction button.
*
* Modifies the data attributes of the Sort Direction button to cycle between
* ascending and descending sort directions.
*
* @param event The generated event.
* @param tabname The name of the active tab in the sd webui. Ex: txt2img, img2img, etc.
* @param extra_networks_tabname The id of the active extraNetworks tab. Ex: lora, checkpoints, etc.
*/
if (event.currentTarget.dataset.sortdir == "Ascending") {
event.currentTarget.dataset.sortdir = "Descending";
event.currentTarget.setAttribute("title", "Sort descending");
} else {
event.currentTarget.dataset.sortdir = "Ascending";
event.currentTarget.setAttribute("title", "Sort ascending");
}
applyExtraNetworkSort(tabname + "_" + extra_networks_tabname);
}
function extraNetworksControlTreeViewOnClick(event, tabname, extra_networks_tabname) {
/**
* Handles `onclick` events for the Tree View button.
*
* Toggles the tree view in the extra networks pane.
*
* @param event The generated event.
* @param tabname The name of the active tab in the sd webui. Ex: txt2img, img2img, etc.
* @param extra_networks_tabname The id of the active extraNetworks tab. Ex: lora, checkpoints, etc.
*/
var button = event.currentTarget;
button.classList.toggle("extra-network-control--enabled");
var show = !button.classList.contains("extra-network-control--enabled");
var pane = gradioApp().getElementById(tabname + "_" + extra_networks_tabname + "_pane");
pane.classList.toggle("extra-network-dirs-hidden", show);
}
function extraNetworksControlRefreshOnClick(event, tabname, extra_networks_tabname) {
/**
* Handles `onclick` events for the Refresh Page button.
*
* In order to actually call the python functions in `ui_extra_networks.py`
* to refresh the page, we created an empty gradio button in that file with an
* event handler that refreshes the page. So what this function here does
* is it manually raises a `click` event on that button.
*
* @param event The generated event.
* @param tabname The name of the active tab in the sd webui. Ex: txt2img, img2img, etc.
* @param extra_networks_tabname The id of the active extraNetworks tab. Ex: lora, checkpoints, etc.
*/
var btn_refresh_internal = gradioApp().getElementById(tabname + "_" + extra_networks_tabname + "_extra_refresh_internal");
btn_refresh_internal.dispatchEvent(new Event("click"));
}
var globalPopup = null;
var globalPopupInner = null;
function closePopup() {
if (!globalPopup) return;
globalPopup.style.display = "none";
}
function popup(contents) {
if (!globalPopup) {
globalPopup = document.createElement('div');
globalPopup.classList.add('global-popup');
var close = document.createElement('div');
close.classList.add('global-popup-close');
close.addEventListener("click", closePopup);
close.title = "Close";
globalPopup.appendChild(close);
globalPopupInner = document.createElement('div');
globalPopupInner.classList.add('global-popup-inner');
globalPopup.appendChild(globalPopupInner);
gradioApp().querySelector('.main').appendChild(globalPopup);
}
globalPopupInner.innerHTML = '';
globalPopupInner.appendChild(contents);
globalPopup.style.display = "flex";
}
var storedPopupIds = {};
function popupId(id) {
if (!storedPopupIds[id]) {
storedPopupIds[id] = gradioApp().getElementById(id);
}
popup(storedPopupIds[id]);
}
function extraNetworksFlattenMetadata(obj) {
const result = {};
// Convert any stringified JSON objects to actual objects
for (const key of Object.keys(obj)) {
if (typeof obj[key] === 'string') {
try {
const parsed = JSON.parse(obj[key]);
if (parsed && typeof parsed === 'object') {
obj[key] = parsed;
}
} catch (error) {
continue;
}
}
}
// Flatten the object
for (const key of Object.keys(obj)) {
if (typeof obj[key] === 'object' && obj[key] !== null) {
const nested = extraNetworksFlattenMetadata(obj[key]);
for (const nestedKey of Object.keys(nested)) {
result[`${key}/${nestedKey}`] = nested[nestedKey];
}
} else {
result[key] = obj[key];
}
}
// Special case for handling modelspec keys
for (const key of Object.keys(result)) {
if (key.startsWith("modelspec.")) {
result[key.replaceAll(".", "/")] = result[key];
delete result[key];
}
}
// Add empty keys to designate hierarchy
for (const key of Object.keys(result)) {
const parts = key.split("/");
for (let i = 1; i < parts.length; i++) {
const parent = parts.slice(0, i).join("/");
if (!result[parent]) {
result[parent] = "";
}
}
}
return result;
}
function extraNetworksShowMetadata(text) {
try {
let parsed = JSON.parse(text);
if (parsed && typeof parsed === 'object') {
parsed = extraNetworksFlattenMetadata(parsed);
const table = createVisualizationTable(parsed, 0);
popup(table);
return;
}
} catch (error) {
console.error(error);
}
var elem = document.createElement('pre');
elem.classList.add('popup-metadata');
elem.textContent = text;
popup(elem);
return;
}
function requestGet(url, data, handler, errorHandler) {
var xhr = new XMLHttpRequest();
var args = Object.keys(data).map(function(k) {
return encodeURIComponent(k) + '=' + encodeURIComponent(data[k]);
}).join('&');
xhr.open("GET", url + "?" + args, true);
xhr.onreadystatechange = function() {
if (xhr.readyState === 4) {
if (xhr.status === 200) {
try {
var js = JSON.parse(xhr.responseText);
handler(js);
} catch (error) {
console.error(error);
errorHandler();
}
} else {
errorHandler();
}
}
};
var js = JSON.stringify(data);
xhr.send(js);
}
function extraNetworksCopyCardPath(event) {
navigator.clipboard.writeText(event.target.getAttribute("data-clipboard-text"));
event.stopPropagation();
}
function extraNetworksRequestMetadata(event, extraPage) {
var showError = function() {
extraNetworksShowMetadata("there was an error getting metadata");
};
var cardName = event.target.parentElement.parentElement.getAttribute("data-name");
requestGet("./sd_extra_networks/metadata", {page: extraPage, item: cardName}, function(data) {
if (data && data.metadata) {
extraNetworksShowMetadata(data.metadata);
} else {
showError();
}
}, showError);
event.stopPropagation();
}
var extraPageUserMetadataEditors = {};
function extraNetworksEditUserMetadata(event, tabname, extraPage) {
var id = tabname + '_' + extraPage + '_edit_user_metadata';
var editor = extraPageUserMetadataEditors[id];
if (!editor) {
editor = {};
editor.page = gradioApp().getElementById(id);
editor.nameTextarea = gradioApp().querySelector("#" + id + "_name" + ' textarea');
editor.button = gradioApp().querySelector("#" + id + "_button");
extraPageUserMetadataEditors[id] = editor;
}
var cardName = event.target.parentElement.parentElement.getAttribute("data-name");
editor.nameTextarea.value = cardName;
updateInput(editor.nameTextarea);
editor.button.click();
popup(editor.page);
event.stopPropagation();
}
function extraNetworksRefreshSingleCard(page, tabname, name) {
requestGet("./sd_extra_networks/get-single-card", {page: page, tabname: tabname, name: name}, function(data) {
if (data && data.html) {
var card = gradioApp().querySelector(`#${tabname}_${page.replace(" ", "_")}_cards > .card[data-name="${name}"]`);
var newDiv = document.createElement('DIV');
newDiv.innerHTML = data.html;
var newCard = newDiv.firstElementChild;
newCard.style.display = '';
card.parentElement.insertBefore(newCard, card);
card.parentElement.removeChild(card);
}
});
}
window.addEventListener("keydown", function(event) {
if (event.key == "Escape") {
closePopup();
}
});
/**
* Setup custom loading for this script.
* We need to wait for all of our HTML to be generated in the extra networks tabs
* before we can actually run the `setupExtraNetworks` function.
* The `onUiLoaded` function actually runs before all of our extra network tabs are
* finished generating. Thus we needed this new method.
*
*/
var uiAfterScriptsCallbacks = [];
var uiAfterScriptsTimeout = null;
var executedAfterScripts = false;
function scheduleAfterScriptsCallbacks() {
clearTimeout(uiAfterScriptsTimeout);
uiAfterScriptsTimeout = setTimeout(function() {
executeCallbacks(uiAfterScriptsCallbacks);
}, 200);
}
onUiLoaded(function() {
var mutationObserver = new MutationObserver(function(m) {
let existingSearchfields = gradioApp().querySelectorAll("[id$='_extra_search']").length;
let neededSearchfields = gradioApp().querySelectorAll("[id$='_extra_tabs'] > .tab-nav > button").length - 2;
if (!executedAfterScripts && existingSearchfields >= neededSearchfields) {
mutationObserver.disconnect();
executedAfterScripts = true;
scheduleAfterScriptsCallbacks();
}
});
mutationObserver.observe(gradioApp(), {childList: true, subtree: true});
});
uiAfterScriptsCallbacks.push(setupExtraNetworks);

35
javascript/generationParams.js Normal file
View File

@ -0,0 +1,35 @@
// attaches listeners to the txt2img and img2img galleries to update displayed generation param text when the image changes
let txt2img_gallery, img2img_gallery, modal = undefined;
onAfterUiUpdate(function() {
if (!txt2img_gallery) {
txt2img_gallery = attachGalleryListeners("txt2img");
}
if (!img2img_gallery) {
img2img_gallery = attachGalleryListeners("img2img");
}
if (!modal) {
modal = gradioApp().getElementById('lightboxModal');
modalObserver.observe(modal, {attributes: true, attributeFilter: ['style']});
}
});
let modalObserver = new MutationObserver(function(mutations) {
mutations.forEach(function(mutationRecord) {
let selectedTab = gradioApp().querySelector('#tabs div button.selected')?.innerText;
if (mutationRecord.target.style.display === 'none' && (selectedTab === 'txt2img' || selectedTab === 'img2img')) {
gradioApp().getElementById(selectedTab + "_generation_info_button")?.click();
}
});
});
function attachGalleryListeners(tab_name) {
var gallery = gradioApp().querySelector('#' + tab_name + '_gallery');
gallery?.addEventListener('click', () => gradioApp().getElementById(tab_name + "_generation_info_button").click());
gallery?.addEventListener('keydown', (e) => {
if (e.keyCode == 37 || e.keyCode == 39) { // left or right arrow
gradioApp().getElementById(tab_name + "_generation_info_button").click();
}
});
return gallery;
}

203
javascript/hints.js Normal file
View File

@ -0,0 +1,203 @@
// mouseover tooltips for various UI elements
var titles = {
"Sampling steps": "How many times to improve the generated image iteratively; higher values take longer; very low values can produce bad results",
"Sampling method": "Which algorithm to use to produce the image",
"GFPGAN": "Restore low quality faces using GFPGAN neural network",
"Euler a": "Euler Ancestral - very creative, each can get a completely different picture depending on step count, setting steps higher than 30-40 does not help",
"DDIM": "Denoising Diffusion Implicit Models - best at inpainting",
"UniPC": "Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models",
"DPM adaptive": "Ignores step count - uses a number of steps determined by the CFG and resolution",
"\u{1F4D0}": "Auto detect size from img2img",
"Batch count": "How many batches of images to create (has no impact on generation performance or VRAM usage)",
"Batch size": "How many image to create in a single batch (increases generation performance at cost of higher VRAM usage)",
"CFG Scale": "Classifier Free Guidance Scale - how strongly the image should conform to prompt - lower values produce more creative results",
"Seed": "A value that determines the output of random number generator - if you create an image with same parameters and seed as another image, you'll get the same result",
"\u{1f3b2}\ufe0f": "Set seed to -1, which will cause a new random number to be used every time",
"\u267b\ufe0f": "Reuse seed from last generation, mostly useful if it was randomized",
"\u2199\ufe0f": "Read generation parameters from prompt or last generation if prompt is empty into user interface.",
"\u{1f4c2}": "Open images output directory",
"\u{1f4be}": "Save style",
"\u{1f5d1}\ufe0f": "Clear prompt",
"\u{1f4cb}": "Apply selected styles to current prompt",
"\u{1f4d2}": "Paste available values into the field",
"\u{1f3b4}": "Show/hide extra networks",
"\u{1f300}": "Restore progress",
"Inpaint a part of image": "Draw a mask over an image, and the script will regenerate the masked area with content according to prompt",
"SD upscale": "Upscale image normally, split result into tiles, improve each tile using img2img, merge whole image back",
"Just resize": "Resize image to target resolution. Unless height and width match, you will get incorrect aspect ratio.",
"Crop and resize": "Resize the image so that entirety of target resolution is filled with the image. Crop parts that stick out.",
"Resize and fill": "Resize the image so that entirety of image is inside target resolution. Fill empty space with image's colors.",
"Mask blur": "How much to blur the mask before processing, in pixels.",
"Masked content": "What to put inside the masked area before processing it with Stable Diffusion.",
"fill": "fill it with colors of the image",
"original": "keep whatever was there originally",
"latent noise": "fill it with latent space noise",
"latent nothing": "fill it with latent space zeroes",
"Inpaint at full resolution": "Upscale masked region to target resolution, do inpainting, downscale back and paste into original image",
"Denoising strength": "Determines how little respect the algorithm should have for image's content. At 0, nothing will change, and at 1 you'll get an unrelated image. With values below 1.0, processing will take less steps than the Sampling Steps slider specifies.",
"Skip": "Stop processing current image and continue processing.",
"Interrupt": "Stop processing images and return any results accumulated so far.",
"Save": "Write image to a directory (default - log/images) and generation parameters into csv file.",
"X values": "Separate values for X axis using commas.",
"Y values": "Separate values for Y axis using commas.",
"None": "Do not do anything special",
"Prompt matrix": "Separate prompts into parts using vertical pipe character (|) and the script will create a picture for every combination of them (except for the first part, which will be present in all combinations)",
"X/Y/Z plot": "Create grid(s) where images will have different parameters. Use inputs below to specify which parameters will be shared by columns and rows",
"Custom code": "Run Python code. Advanced user only. Must run program with --allow-code for this to work",
"Prompt S/R": "Separate a list of words with commas, and the first word will be used as a keyword: script will search for this word in the prompt, and replace it with others",
"Prompt order": "Separate a list of words with commas, and the script will make a variation of prompt with those words for their every possible order",
"Tiling": "Produce an image that can be tiled.",
"Tile overlap": "For SD upscale, how much overlap in pixels should there be between tiles. Tiles overlap so that when they are merged back into one picture, there is no clearly visible seam.",
"Variation seed": "Seed of a different picture to be mixed into the generation.",
"Variation strength": "How strong of a variation to produce. At 0, there will be no effect. At 1, you will get the complete picture with variation seed (except for ancestral samplers, where you will just get something).",
"Resize seed from height": "Make an attempt to produce a picture similar to what would have been produced with same seed at specified resolution",
"Resize seed from width": "Make an attempt to produce a picture similar to what would have been produced with same seed at specified resolution",
"Interrogate": "Reconstruct prompt from existing image and put it into the prompt field.",
"Images filename pattern": "Use tags like [seed] and [date] to define how filenames for images are chosen. Leave empty for default.",
"Directory name pattern": "Use tags like [seed] and [date] to define how subdirectories for images and grids are chosen. Leave empty for default.",
"Max prompt words": "Set the maximum number of words to be used in the [prompt_words] option; ATTENTION: If the words are too long, they may exceed the maximum length of the file path that the system can handle",
"Loopback": "Performs img2img processing multiple times. Output images are used as input for the next loop.",
"Loops": "How many times to process an image. Each output is used as the input of the next loop. If set to 1, behavior will be as if this script were not used.",
"Final denoising strength": "The denoising strength for the final loop of each image in the batch.",
"Denoising strength curve": "The denoising curve controls the rate of denoising strength change each loop. Aggressive: Most of the change will happen towards the start of the loops. Linear: Change will be constant through all loops. Lazy: Most of the change will happen towards the end of the loops.",
"Style 1": "Style to apply; styles have components for both positive and negative prompts and apply to both",
"Style 2": "Style to apply; styles have components for both positive and negative prompts and apply to both",
"Apply style": "Insert selected styles into prompt fields",
"Create style": "Save current prompts as a style. If you add the token {prompt} to the text, the style uses that as a placeholder for your prompt when you use the style in the future.",
"Checkpoint name": "Loads weights from checkpoint before making images. You can either use hash or a part of filename (as seen in settings) for checkpoint name. Recommended to use with Y axis for less switching.",
"Inpainting conditioning mask strength": "Only applies to inpainting models. Determines how strongly to mask off the original image for inpainting and img2img. 1.0 means fully masked, which is the default behaviour. 0.0 means a fully unmasked conditioning. Lower values will help preserve the overall composition of the image, but will struggle with large changes.",
"Eta noise seed delta": "If this values is non-zero, it will be added to seed and used to initialize RNG for noises when using samplers with Eta. You can use this to produce even more variation of images, or you can use this to match images of other software if you know what you are doing.",
"Filename word regex": "This regular expression will be used extract words from filename, and they will be joined using the option below into label text used for training. Leave empty to keep filename text as it is.",
"Filename join string": "This string will be used to join split words into a single line if the option above is enabled.",
"Quicksettings list": "List of setting names, separated by commas, for settings that should go to the quick access bar at the top, rather than the usual setting tab. See modules/shared.py for setting names. Requires restarting to apply.",
"Weighted sum": "Result = A * (1 - M) + B * M",
"Add difference": "Result = A + (B - C) * M",
"No interpolation": "Result = A",
"Initialization text": "If the number of tokens is more than the number of vectors, some may be skipped.\nLeave the textbox empty to start with zeroed out vectors",
"Learning rate": "How fast should training go. Low values will take longer to train, high values may fail to converge (not generate accurate results) and/or may break the embedding (This has happened if you see Loss: nan in the training info textbox. If this happens, you need to manually restore your embedding from an older not-broken backup).\n\nYou can set a single numeric value, or multiple learning rates using the syntax:\n\n rate_1:max_steps_1, rate_2:max_steps_2, ...\n\nEG: 0.005:100, 1e-3:1000, 1e-5\n\nWill train with rate of 0.005 for first 100 steps, then 1e-3 until 1000 steps, then 1e-5 for all remaining steps.",
"Clip skip": "Early stopping parameter for CLIP model; 1 is stop at last layer as usual, 2 is stop at penultimate layer, etc.",
"Approx NN": "Cheap neural network approximation. Very fast compared to VAE, but produces pictures with 4 times smaller horizontal/vertical resolution and lower quality.",
"Approx cheap": "Very cheap approximation. Very fast compared to VAE, but produces pictures with 8 times smaller horizontal/vertical resolution and extremely low quality.",
"Hires. fix": "Use a two step process to partially create an image at smaller resolution, upscale, and then improve details in it without changing composition",
"Hires steps": "Number of sampling steps for upscaled picture. If 0, uses same as for original.",
"Upscale by": "Adjusts the size of the image by multiplying the original width and height by the selected value. Ignored if either Resize width to or Resize height to are non-zero.",
"Resize width to": "Resizes image to this width. If 0, width is inferred from either of two nearby sliders.",
"Resize height to": "Resizes image to this height. If 0, height is inferred from either of two nearby sliders.",
"Discard weights with matching name": "Regular expression; if weights's name matches it, the weights is not written to the resulting checkpoint. Use ^model_ema to discard EMA weights.",
"Extra networks tab order": "Comma-separated list of tab names; tabs listed here will appear in the extra networks UI first and in order listed.",
"Negative Guidance minimum sigma": "Skip negative prompt for steps where image is already mostly denoised; the higher this value, the more skips there will be; provides increased performance in exchange for minor quality reduction."
};
function updateTooltip(element) {
if (element.title) return; // already has a title
let text = element.textContent;
let tooltip = localization[titles[text]] || titles[text];
if (!tooltip) {
let value = element.value;
if (value) tooltip = localization[titles[value]] || titles[value];
}
if (!tooltip) {
// Gradio dropdown options have `data-value`.
let dataValue = element.dataset.value;
if (dataValue) tooltip = localization[titles[dataValue]] || titles[dataValue];
}
if (!tooltip) {
for (const c of element.classList) {
if (c in titles) {
tooltip = localization[titles[c]] || titles[c];
break;
}
}
}
if (tooltip) {
element.title = tooltip;
}
}
// Nodes to check for adding tooltips.
const tooltipCheckNodes = new Set();
// Timer for debouncing tooltip check.
let tooltipCheckTimer = null;
function processTooltipCheckNodes() {
for (const node of tooltipCheckNodes) {
updateTooltip(node);
}
tooltipCheckNodes.clear();
}
onUiUpdate(function(mutationRecords) {
for (const record of mutationRecords) {
if (record.type === "childList" && record.target.classList.contains("options")) {
// This smells like a Gradio dropdown menu having changed,
// so let's enqueue an update for the input element that shows the current value.
let wrap = record.target.parentNode;
let input = wrap?.querySelector("input");
if (input) {
input.title = ""; // So we'll even have a chance to update it.
tooltipCheckNodes.add(input);
}
}
for (const node of record.addedNodes) {
if (node.nodeType === Node.ELEMENT_NODE && !node.classList.contains("hide")) {
if (!node.title) {
if (
node.tagName === "SPAN" ||
node.tagName === "BUTTON" ||
node.tagName === "P" ||
node.tagName === "INPUT" ||
(node.tagName === "LI" && node.classList.contains("item")) // Gradio dropdown item
) {
tooltipCheckNodes.add(node);
}
}
node.querySelectorAll('span, button, p').forEach(n => tooltipCheckNodes.add(n));
}
}
}
if (tooltipCheckNodes.size) {
clearTimeout(tooltipCheckTimer);
tooltipCheckTimer = setTimeout(processTooltipCheckNodes, 1000);
}
});
onUiLoaded(function() {
for (var comp of window.gradio_config.components) {
if (comp.props.webui_tooltip && comp.props.elem_id) {
var elem = gradioApp().getElementById(comp.props.elem_id);
if (elem) {
elem.title = comp.props.webui_tooltip;
}
}
}
});

18
javascript/hires_fix.js Normal file
View File

@ -0,0 +1,18 @@
function onCalcResolutionHires(enable, width, height, hr_scale, hr_resize_x, hr_resize_y) {
function setInactive(elem, inactive) {
elem.classList.toggle('inactive', !!inactive);
}
var hrUpscaleBy = gradioApp().getElementById('txt2img_hr_scale');
var hrResizeX = gradioApp().getElementById('txt2img_hr_resize_x');
var hrResizeY = gradioApp().getElementById('txt2img_hr_resize_y');
gradioApp().getElementById('txt2img_hires_fix_row2').style.display = opts.use_old_hires_fix_width_height ? "none" : "";
setInactive(hrUpscaleBy, opts.use_old_hires_fix_width_height || hr_resize_x > 0 || hr_resize_y > 0);
setInactive(hrResizeX, opts.use_old_hires_fix_width_height || hr_resize_x == 0);
setInactive(hrResizeY, opts.use_old_hires_fix_width_height || hr_resize_y == 0);
return [enable, width, height, hr_scale, hr_resize_x, hr_resize_y];
}

43
javascript/imageMaskFix.js Normal file
View File

@ -0,0 +1,43 @@
/**
* temporary fix for https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/668
* @see https://github.com/gradio-app/gradio/issues/1721
*/
function imageMaskResize() {
const canvases = gradioApp().querySelectorAll('#img2maskimg .touch-none canvas');
if (!canvases.length) {
window.removeEventListener('resize', imageMaskResize);
return;
}
const wrapper = canvases[0].closest('.touch-none');
const previewImage = wrapper.previousElementSibling;
if (!previewImage.complete) {
previewImage.addEventListener('load', imageMaskResize);
return;
}
const w = previewImage.width;
const h = previewImage.height;
const nw = previewImage.naturalWidth;
const nh = previewImage.naturalHeight;
const portrait = nh > nw;
const wW = Math.min(w, portrait ? h / nh * nw : w / nw * nw);
const wH = Math.min(h, portrait ? h / nh * nh : w / nw * nh);
wrapper.style.width = `${wW}px`;
wrapper.style.height = `${wH}px`;
wrapper.style.left = `0px`;
wrapper.style.top = `0px`;
canvases.forEach(c => {
c.style.width = c.style.height = '';
c.style.maxWidth = '100%';
c.style.maxHeight = '100%';
c.style.objectFit = 'contain';
});
}
onAfterUiUpdate(imageMaskResize);
window.addEventListener('resize', imageMaskResize);

268
javascript/imageviewer.js Normal file
View File

@ -0,0 +1,268 @@
// A full size 'lightbox' preview modal shown when left clicking on gallery previews
function closeModal() {
gradioApp().getElementById("lightboxModal").style.display = "none";
}
function showModal(event) {
const source = event.target || event.srcElement;
const modalImage = gradioApp().getElementById("modalImage");
const modalToggleLivePreviewBtn = gradioApp().getElementById("modal_toggle_live_preview");
modalToggleLivePreviewBtn.innerHTML = opts.js_live_preview_in_modal_lightbox ? "&#x1F5C7;" : "&#x1F5C6;";
const lb = gradioApp().getElementById("lightboxModal");
modalImage.src = source.src;
if (modalImage.style.display === 'none') {
lb.style.setProperty('background-image', 'url(' + source.src + ')');
}
lb.style.display = "flex";
lb.focus();
const tabTxt2Img = gradioApp().getElementById("tab_txt2img");
const tabImg2Img = gradioApp().getElementById("tab_img2img");
// show the save button in modal only on txt2img or img2img tabs
if (tabTxt2Img.style.display != "none" || tabImg2Img.style.display != "none") {
gradioApp().getElementById("modal_save").style.display = "inline";
} else {
gradioApp().getElementById("modal_save").style.display = "none";
}
event.stopPropagation();
}
function negmod(n, m) {
return ((n % m) + m) % m;
}
function updateOnBackgroundChange() {
const modalImage = gradioApp().getElementById("modalImage");
if (modalImage && modalImage.offsetParent) {
let currentButton = selected_gallery_button();
let preview = gradioApp().querySelectorAll('.livePreview > img');
if (opts.js_live_preview_in_modal_lightbox && preview.length > 0) {
// show preview image if available
modalImage.src = preview[preview.length - 1].src;
} else if (currentButton?.children?.length > 0 && modalImage.src != currentButton.children[0].src) {
modalImage.src = currentButton.children[0].src;
if (modalImage.style.display === 'none') {
const modal = gradioApp().getElementById("lightboxModal");
modal.style.setProperty('background-image', `url(${modalImage.src})`);
}
}
}
}
function modalImageSwitch(offset) {
var galleryButtons = all_gallery_buttons();
if (galleryButtons.length > 1) {
var result = selected_gallery_index();
if (result != -1) {
var nextButton = galleryButtons[negmod((result + offset), galleryButtons.length)];
nextButton.click();
const modalImage = gradioApp().getElementById("modalImage");
const modal = gradioApp().getElementById("lightboxModal");
modalImage.src = nextButton.children[0].src;
if (modalImage.style.display === 'none') {
modal.style.setProperty('background-image', `url(${modalImage.src})`);
}
setTimeout(function() {
modal.focus();
}, 10);
}
}
}
function saveImage() {
const tabTxt2Img = gradioApp().getElementById("tab_txt2img");
const tabImg2Img = gradioApp().getElementById("tab_img2img");
const saveTxt2Img = "save_txt2img";
const saveImg2Img = "save_img2img";
if (tabTxt2Img.style.display != "none") {
gradioApp().getElementById(saveTxt2Img).click();
} else if (tabImg2Img.style.display != "none") {
gradioApp().getElementById(saveImg2Img).click();
} else {
console.error("missing implementation for saving modal of this type");
}
}
function modalSaveImage(event) {
saveImage();
event.stopPropagation();
}
function modalNextImage(event) {
modalImageSwitch(1);
event.stopPropagation();
}
function modalPrevImage(event) {
modalImageSwitch(-1);
event.stopPropagation();
}
function modalKeyHandler(event) {
switch (event.key) {
case "s":
saveImage();
break;
case "ArrowLeft":
modalPrevImage(event);
break;
case "ArrowRight":
modalNextImage(event);
break;
case "Escape":
closeModal();
break;
}
}
function setupImageForLightbox(e) {
if (e.dataset.modded) {
return;
}
e.dataset.modded = true;
e.style.cursor = 'pointer';
e.style.userSelect = 'none';
e.addEventListener('mousedown', function(evt) {
if (evt.button == 1) {
open(evt.target.src);
evt.preventDefault();
return;
}
}, true);
e.addEventListener('click', function(evt) {
if (!opts.js_modal_lightbox || evt.button != 0) return;
modalZoomSet(gradioApp().getElementById('modalImage'), opts.js_modal_lightbox_initially_zoomed);
evt.preventDefault();
showModal(evt);
}, true);
}
function modalZoomSet(modalImage, enable) {
if (modalImage) modalImage.classList.toggle('modalImageFullscreen', !!enable);
}
function modalZoomToggle(event) {
var modalImage = gradioApp().getElementById("modalImage");
modalZoomSet(modalImage, !modalImage.classList.contains('modalImageFullscreen'));
event.stopPropagation();
}
function modalLivePreviewToggle(event) {
const modalToggleLivePreview = gradioApp().getElementById("modal_toggle_live_preview");
opts.js_live_preview_in_modal_lightbox = !opts.js_live_preview_in_modal_lightbox;
modalToggleLivePreview.innerHTML = opts.js_live_preview_in_modal_lightbox ? "&#x1F5C7;" : "&#x1F5C6;";
event.stopPropagation();
}
function modalTileImageToggle(event) {
const modalImage = gradioApp().getElementById("modalImage");
const modal = gradioApp().getElementById("lightboxModal");
const isTiling = modalImage.style.display === 'none';
if (isTiling) {
modalImage.style.display = 'block';
modal.style.setProperty('background-image', 'none');
} else {
modalImage.style.display = 'none';
modal.style.setProperty('background-image', `url(${modalImage.src})`);
}
event.stopPropagation();
}
onAfterUiUpdate(function() {
var fullImg_preview = gradioApp().querySelectorAll('.gradio-gallery > div > img');
if (fullImg_preview != null) {
fullImg_preview.forEach(setupImageForLightbox);
}
updateOnBackgroundChange();
});
document.addEventListener("DOMContentLoaded", function() {
//const modalFragment = document.createDocumentFragment();
const modal = document.createElement('div');
modal.onclick = closeModal;
modal.id = "lightboxModal";
modal.tabIndex = 0;
modal.addEventListener('keydown', modalKeyHandler, true);
const modalControls = document.createElement('div');
modalControls.className = 'modalControls gradio-container';
modal.append(modalControls);
const modalZoom = document.createElement('span');
modalZoom.className = 'modalZoom cursor';
modalZoom.innerHTML = '&#10529;';
modalZoom.addEventListener('click', modalZoomToggle, true);
modalZoom.title = "Toggle zoomed view";
modalControls.appendChild(modalZoom);
const modalTileImage = document.createElement('span');
modalTileImage.className = 'modalTileImage cursor';
modalTileImage.innerHTML = '&#8862;';
modalTileImage.addEventListener('click', modalTileImageToggle, true);
modalTileImage.title = "Preview tiling";
modalControls.appendChild(modalTileImage);
const modalSave = document.createElement("span");
modalSave.className = "modalSave cursor";
modalSave.id = "modal_save";
modalSave.innerHTML = "&#x1F5AB;";
modalSave.addEventListener("click", modalSaveImage, true);
modalSave.title = "Save Image(s)";
modalControls.appendChild(modalSave);
const modalToggleLivePreview = document.createElement('span');
modalToggleLivePreview.className = 'modalToggleLivePreview cursor';
modalToggleLivePreview.id = "modal_toggle_live_preview";
modalToggleLivePreview.innerHTML = "&#x1F5C6;";
modalToggleLivePreview.onclick = modalLivePreviewToggle;
modalToggleLivePreview.title = "Toggle live preview";
modalControls.appendChild(modalToggleLivePreview);
const modalClose = document.createElement('span');
modalClose.className = 'modalClose cursor';
modalClose.innerHTML = '&times;';
modalClose.onclick = closeModal;
modalClose.title = "Close image viewer";
modalControls.appendChild(modalClose);
const modalImage = document.createElement('img');
modalImage.id = 'modalImage';
modalImage.onclick = closeModal;
modalImage.tabIndex = 0;
modalImage.addEventListener('keydown', modalKeyHandler, true);
modal.appendChild(modalImage);
const modalPrev = document.createElement('a');
modalPrev.className = 'modalPrev';
modalPrev.innerHTML = '&#10094;';
modalPrev.tabIndex = 0;
modalPrev.addEventListener('click', modalPrevImage, true);
modalPrev.addEventListener('keydown', modalKeyHandler, true);
modal.appendChild(modalPrev);
const modalNext = document.createElement('a');
modalNext.className = 'modalNext';
modalNext.innerHTML = '&#10095;';
modalNext.tabIndex = 0;
modalNext.addEventListener('click', modalNextImage, true);
modalNext.addEventListener('keydown', modalKeyHandler, true);
modal.appendChild(modalNext);
try {
gradioApp().appendChild(modal);
} catch (e) {
gradioApp().body.appendChild(modal);
}
document.body.appendChild(modal);
});

63
javascript/imageviewerGamepad.js Normal file
View File

@ -0,0 +1,63 @@
let gamepads = [];
window.addEventListener('gamepadconnected', (e) => {
const index = e.gamepad.index;
let isWaiting = false;
gamepads[index] = setInterval(async() => {
if (!opts.js_modal_lightbox_gamepad || isWaiting) return;
const gamepad = navigator.getGamepads()[index];
const xValue = gamepad.axes[0];
if (xValue <= -0.3) {
modalPrevImage(e);
isWaiting = true;
} else if (xValue >= 0.3) {
modalNextImage(e);
isWaiting = true;
}
if (isWaiting) {
await sleepUntil(() => {
const xValue = navigator.getGamepads()[index].axes[0];
if (xValue < 0.3 && xValue > -0.3) {
return true;
}
}, opts.js_modal_lightbox_gamepad_repeat);
isWaiting = false;
}
}, 10);
});
window.addEventListener('gamepaddisconnected', (e) => {
clearInterval(gamepads[e.gamepad.index]);
});
/*
Primarily for vr controller type pointer devices.
I use the wheel event because there's currently no way to do it properly with web xr.
*/
let isScrolling = false;
window.addEventListener('wheel', (e) => {
if (!opts.js_modal_lightbox_gamepad || isScrolling) return;
isScrolling = true;
if (e.deltaX <= -0.6) {
modalPrevImage(e);
} else if (e.deltaX >= 0.6) {
modalNextImage(e);
}
setTimeout(() => {
isScrolling = false;
}, opts.js_modal_lightbox_gamepad_repeat);
});
function sleepUntil(f, timeout) {
return new Promise((resolve) => {
const timeStart = new Date();
const wait = setInterval(function() {
if (f() || new Date() - timeStart > timeout) {
clearInterval(wait);
resolve();
}
}, 20);
});
}

68
javascript/inputAccordion.js Normal file
View File

@ -0,0 +1,68 @@
function inputAccordionChecked(id, checked) {
var accordion = gradioApp().getElementById(id);
accordion.visibleCheckbox.checked = checked;
accordion.onVisibleCheckboxChange();
}
function setupAccordion(accordion) {
var labelWrap = accordion.querySelector('.label-wrap');
var gradioCheckbox = gradioApp().querySelector('#' + accordion.id + "-checkbox input");
var extra = gradioApp().querySelector('#' + accordion.id + "-extra");
var span = labelWrap.querySelector('span');
var linked = true;
var isOpen = function() {
return labelWrap.classList.contains('open');
};
var observerAccordionOpen = new MutationObserver(function(mutations) {
mutations.forEach(function(mutationRecord) {
accordion.classList.toggle('input-accordion-open', isOpen());
if (linked) {
accordion.visibleCheckbox.checked = isOpen();
accordion.onVisibleCheckboxChange();
}
});
});
observerAccordionOpen.observe(labelWrap, {attributes: true, attributeFilter: ['class']});
if (extra) {
labelWrap.insertBefore(extra, labelWrap.lastElementChild);
}
accordion.onChecked = function(checked) {
if (isOpen() != checked) {
labelWrap.click();
}
};
var visibleCheckbox = document.createElement('INPUT');
visibleCheckbox.type = 'checkbox';
visibleCheckbox.checked = isOpen();
visibleCheckbox.id = accordion.id + "-visible-checkbox";
visibleCheckbox.className = gradioCheckbox.className + " input-accordion-checkbox";
span.insertBefore(visibleCheckbox, span.firstChild);
accordion.visibleCheckbox = visibleCheckbox;
accordion.onVisibleCheckboxChange = function() {
if (linked && isOpen() != visibleCheckbox.checked) {
labelWrap.click();
}
gradioCheckbox.checked = visibleCheckbox.checked;
updateInput(gradioCheckbox);
};
visibleCheckbox.addEventListener('click', function(event) {
linked = false;
event.stopPropagation();
});
visibleCheckbox.addEventListener('input', accordion.onVisibleCheckboxChange);
}
onUiLoaded(function() {
for (var accordion of gradioApp().querySelectorAll('.input-accordion')) {
setupAccordion(accordion);
}
});

26
javascript/localStorage.js Normal file
View File

@ -0,0 +1,26 @@
function localSet(k, v) {
try {
localStorage.setItem(k, v);
} catch (e) {
console.warn(`Failed to save ${k} to localStorage: ${e}`);
}
}
function localGet(k, def) {
try {
return localStorage.getItem(k);
} catch (e) {
console.warn(`Failed to load ${k} from localStorage: ${e}`);
}
return def;
}
function localRemove(k) {
try {
return localStorage.removeItem(k);
} catch (e) {
console.warn(`Failed to remove ${k} from localStorage: ${e}`);
}
}

205
javascript/localization.js Normal file
View File

@ -0,0 +1,205 @@
// localization = {} -- the dict with translations is created by the backend
var ignore_ids_for_localization = {
setting_sd_hypernetwork: 'OPTION',
setting_sd_model_checkpoint: 'OPTION',
modelmerger_primary_model_name: 'OPTION',
modelmerger_secondary_model_name: 'OPTION',
modelmerger_tertiary_model_name: 'OPTION',
train_embedding: 'OPTION',
train_hypernetwork: 'OPTION',
txt2img_styles: 'OPTION',
img2img_styles: 'OPTION',
setting_random_artist_categories: 'OPTION',
setting_face_restoration_model: 'OPTION',
setting_realesrgan_enabled_models: 'OPTION',
extras_upscaler_1: 'OPTION',
extras_upscaler_2: 'OPTION',
};
var re_num = /^[.\d]+$/;
var re_emoji = /[\p{Extended_Pictographic}\u{1F3FB}-\u{1F3FF}\u{1F9B0}-\u{1F9B3}]/u;
var original_lines = {};
var translated_lines = {};
function hasLocalization() {
return window.localization && Object.keys(window.localization).length > 0;
}
function textNodesUnder(el) {
var n, a = [], walk = document.createTreeWalker(el, NodeFilter.SHOW_TEXT, null, false);
while ((n = walk.nextNode())) a.push(n);
return a;
}
function canBeTranslated(node, text) {
if (!text) return false;
if (!node.parentElement) return false;
var parentType = node.parentElement.nodeName;
if (parentType == 'SCRIPT' || parentType == 'STYLE' || parentType == 'TEXTAREA') return false;
if (parentType == 'OPTION' || parentType == 'SPAN') {
var pnode = node;
for (var level = 0; level < 4; level++) {
pnode = pnode.parentElement;
if (!pnode) break;
if (ignore_ids_for_localization[pnode.id] == parentType) return false;
}
}
if (re_num.test(text)) return false;
if (re_emoji.test(text)) return false;
return true;
}
function getTranslation(text) {
if (!text) return undefined;
if (translated_lines[text] === undefined) {
original_lines[text] = 1;
}
var tl = localization[text];
if (tl !== undefined) {
translated_lines[tl] = 1;
}
return tl;
}
function processTextNode(node) {
var text = node.textContent.trim();
if (!canBeTranslated(node, text)) return;
var tl = getTranslation(text);
if (tl !== undefined) {
node.textContent = tl;
}
}
function processNode(node) {
if (node.nodeType == 3) {
processTextNode(node);
return;
}
if (node.title) {
let tl = getTranslation(node.title);
if (tl !== undefined) {
node.title = tl;
}
}
if (node.placeholder) {
let tl = getTranslation(node.placeholder);
if (tl !== undefined) {
node.placeholder = tl;
}
}
textNodesUnder(node).forEach(function(node) {
processTextNode(node);
});
}
function localizeWholePage() {
processNode(gradioApp());
function elem(comp) {
var elem_id = comp.props.elem_id ? comp.props.elem_id : "component-" + comp.id;
return gradioApp().getElementById(elem_id);
}
for (var comp of window.gradio_config.components) {
if (comp.props.webui_tooltip) {
let e = elem(comp);
let tl = e ? getTranslation(e.title) : undefined;
if (tl !== undefined) {
e.title = tl;
}
}
if (comp.props.placeholder) {
let e = elem(comp);
let textbox = e ? e.querySelector('[placeholder]') : null;
let tl = textbox ? getTranslation(textbox.placeholder) : undefined;
if (tl !== undefined) {
textbox.placeholder = tl;
}
}
}
}
function dumpTranslations() {
if (!hasLocalization()) {
// If we don't have any localization,
// we will not have traversed the app to find
// original_lines, so do that now.
localizeWholePage();
}
var dumped = {};
if (localization.rtl) {
dumped.rtl = true;
}
for (const text in original_lines) {
if (dumped[text] !== undefined) continue;
dumped[text] = localization[text] || text;
}
return dumped;
}
function download_localization() {
var text = JSON.stringify(dumpTranslations(), null, 4);
var element = document.createElement('a');
element.setAttribute('href', 'data:text/plain;charset=utf-8,' + encodeURIComponent(text));
element.setAttribute('download', "localization.json");
element.style.display = 'none';
document.body.appendChild(element);
element.click();
document.body.removeChild(element);
}
document.addEventListener("DOMContentLoaded", function() {
if (!hasLocalization()) {
return;
}
onUiUpdate(function(m) {
m.forEach(function(mutation) {
mutation.addedNodes.forEach(function(node) {
processNode(node);
});
});
});
localizeWholePage();
if (localization.rtl) { // if the language is from right to left,
(new MutationObserver((mutations, observer) => { // wait for the style to load
mutations.forEach(mutation => {
mutation.addedNodes.forEach(node => {
if (node.tagName === 'STYLE') {
observer.disconnect();
for (const x of node.sheet.rules) { // find all rtl media rules
if (Array.from(x.media || []).includes('rtl')) {
x.media.appendMedium('all'); // enable them
}
}
}
});
});
})).observe(gradioApp(), {childList: true});
}
});

53
javascript/notification.js Normal file
View File

@ -0,0 +1,53 @@
// Monitors the gallery and sends a browser notification when the leading image is new.
let lastHeadImg = null;
let notificationButton = null;
onAfterUiUpdate(function() {
if (notificationButton == null) {
notificationButton = gradioApp().getElementById('request_notifications');
if (notificationButton != null) {
notificationButton.addEventListener('click', () => {
void Notification.requestPermission();
}, true);
}
}
const galleryPreviews = gradioApp().querySelectorAll('div[id^="tab_"] div[id$="_results"] .thumbnail-item > img');
if (galleryPreviews == null) return;
const headImg = galleryPreviews[0]?.src;
if (headImg == null || headImg == lastHeadImg) return;
lastHeadImg = headImg;
// play notification sound if available
const notificationAudio = gradioApp().querySelector('#audio_notification audio');
if (notificationAudio) {
notificationAudio.volume = opts.notification_volume / 100.0 || 1.0;
notificationAudio.play();
}
if (document.hasFocus()) return;
// Multiple copies of the images are in the DOM when one is selected. Dedup with a Set to get the real number generated.
const imgs = new Set(Array.from(galleryPreviews).map(img => img.src));
const notification = new Notification(
'Stable Diffusion',
{
body: `Generated ${imgs.size > 1 ? imgs.size - opts.return_grid : 1} image${imgs.size > 1 ? 's' : ''}`,
icon: headImg,
image: headImg,
}
);
notification.onclick = function(_) {
parent.focus();
this.close();
};
});

174
javascript/profilerVisualization.js Normal file
View File

@ -0,0 +1,174 @@
function createRow(table, cellName, items) {
var tr = document.createElement('tr');
var res = [];
items.forEach(function(x, i) {
if (x === undefined) {
res.push(null);
return;
}
var td = document.createElement(cellName);
td.textContent = x;
tr.appendChild(td);
res.push(td);
var colspan = 1;
for (var n = i + 1; n < items.length; n++) {
if (items[n] !== undefined) {
break;
}
colspan += 1;
}
if (colspan > 1) {
td.colSpan = colspan;
}
});
table.appendChild(tr);
return res;
}
function createVisualizationTable(data, cutoff = 0, sort = "") {
var table = document.createElement('table');
table.className = 'popup-table';
var keys = Object.keys(data);
if (sort === "number") {
keys = keys.sort(function(a, b) {
return data[b] - data[a];
});
} else {
keys = keys.sort();
}
var items = keys.map(function(x) {
return {key: x, parts: x.split('/'), value: data[x]};
});
var maxLength = items.reduce(function(a, b) {
return Math.max(a, b.parts.length);
}, 0);
var cols = createRow(
table,
'th',
[
cutoff === 0 ? 'key' : 'record',
cutoff === 0 ? 'value' : 'seconds'
]
);
cols[0].colSpan = maxLength;
function arraysEqual(a, b) {
return !(a < b || b < a);
}
var addLevel = function(level, parent, hide) {
var matching = items.filter(function(x) {
return x.parts[level] && !x.parts[level + 1] && arraysEqual(x.parts.slice(0, level), parent);
});
if (sort === "number") {
matching = matching.sort(function(a, b) {
return b.value - a.value;
});
} else {
matching = matching.sort();
}
var othersTime = 0;
var othersList = [];
var othersRows = [];
var childrenRows = [];
matching.forEach(function(x) {
var visible = (cutoff === 0 && !hide) || (x.value >= cutoff && !hide);
var cells = [];
for (var i = 0; i < maxLength; i++) {
cells.push(x.parts[i]);
}
cells.push(cutoff === 0 ? x.value : x.value.toFixed(3));
var cols = createRow(table, 'td', cells);
for (i = 0; i < level; i++) {
cols[i].className = 'muted';
}
var tr = cols[0].parentNode;
if (!visible) {
tr.classList.add("hidden");
}
if (cutoff === 0 || x.value >= cutoff) {
childrenRows.push(tr);
} else {
othersTime += x.value;
othersList.push(x.parts[level]);
othersRows.push(tr);
}
var children = addLevel(level + 1, parent.concat([x.parts[level]]), true);
if (children.length > 0) {
var cell = cols[level];
var onclick = function() {
cell.classList.remove("link");
cell.removeEventListener("click", onclick);
children.forEach(function(x) {
x.classList.remove("hidden");
});
};
cell.classList.add("link");
cell.addEventListener("click", onclick);
}
});
if (othersTime > 0) {
var cells = [];
for (var i = 0; i < maxLength; i++) {
cells.push(parent[i]);
}
cells.push(othersTime.toFixed(3));
cells[level] = 'others';
var cols = createRow(table, 'td', cells);
for (i = 0; i < level; i++) {
cols[i].className = 'muted';
}
var cell = cols[level];
var tr = cell.parentNode;
var onclick = function() {
tr.classList.add("hidden");
cell.classList.remove("link");
cell.removeEventListener("click", onclick);
othersRows.forEach(function(x) {
x.classList.remove("hidden");
});
};
cell.title = othersList.join(", ");
cell.classList.add("link");
cell.addEventListener("click", onclick);
if (hide) {
tr.classList.add("hidden");
}
childrenRows.push(tr);
}
return childrenRows;
};
addLevel(0, []);
return table;
}
function showProfile(path, cutoff = 0.05) {
requestGet(path, {}, function(data) {
data.records['total'] = data.total;
const table = createVisualizationTable(data.records, cutoff, "number");
popup(table);
});
}

215
javascript/progressbar.js Normal file
View File

@ -0,0 +1,215 @@
// code related to showing and updating progressbar shown as the image is being made
function rememberGallerySelection() {
}
function getGallerySelectedIndex() {
}
function request(url, data, handler, errorHandler) {
var xhr = new XMLHttpRequest();
xhr.open("POST", url, true);
xhr.setRequestHeader("Content-Type", "application/json");
xhr.onreadystatechange = function() {
if (xhr.readyState === 4) {
if (xhr.status === 200) {
try {
var js = JSON.parse(xhr.responseText);
handler(js);
} catch (error) {
console.error(error);
errorHandler();
}
} else {
errorHandler();
}
}
};
var js = JSON.stringify(data);
xhr.send(js);
}
function pad2(x) {
return x < 10 ? '0' + x : x;
}
function formatTime(secs) {
if (secs > 3600) {
return pad2(Math.floor(secs / 60 / 60)) + ":" + pad2(Math.floor(secs / 60) % 60) + ":" + pad2(Math.floor(secs) % 60);
} else if (secs > 60) {
return pad2(Math.floor(secs / 60)) + ":" + pad2(Math.floor(secs) % 60);
} else {
return Math.floor(secs) + "s";
}
}
var originalAppTitle = undefined;
onUiLoaded(function() {
originalAppTitle = document.title;
});
function setTitle(progress) {
var title = originalAppTitle;
if (opts.show_progress_in_title && progress) {
title = '[' + progress.trim() + '] ' + title;
}
if (document.title != title) {
document.title = title;
}
}
function randomId() {
return "task(" + Math.random().toString(36).slice(2, 7) + Math.random().toString(36).slice(2, 7) + Math.random().toString(36).slice(2, 7) + ")";
}
// starts sending progress requests to "/internal/progress" uri, creating progressbar above progressbarContainer element and
// preview inside gallery element. Cleans up all created stuff when the task is over and calls atEnd.
// calls onProgress every time there is a progress update
function requestProgress(id_task, progressbarContainer, gallery, atEnd, onProgress, inactivityTimeout = 40) {
var dateStart = new Date();
var wasEverActive = false;
var parentProgressbar = progressbarContainer.parentNode;
var wakeLock = null;
var requestWakeLock = async function() {
if (!opts.prevent_screen_sleep_during_generation || wakeLock) return;
try {
wakeLock = await navigator.wakeLock.request('screen');
} catch (err) {
console.error('Wake Lock is not supported.');
}
};
var releaseWakeLock = async function() {
if (!opts.prevent_screen_sleep_during_generation || !wakeLock) return;
try {
await wakeLock.release();
wakeLock = null;
} catch (err) {
console.error('Wake Lock release failed', err);
}
};
var divProgress = document.createElement('div');
divProgress.className = 'progressDiv';
divProgress.style.display = opts.show_progressbar ? "block" : "none";
var divInner = document.createElement('div');
divInner.className = 'progress';
divProgress.appendChild(divInner);
parentProgressbar.insertBefore(divProgress, progressbarContainer);
var livePreview = null;
var removeProgressBar = function() {
releaseWakeLock();
if (!divProgress) return;
setTitle("");
parentProgressbar.removeChild(divProgress);
if (gallery && livePreview) gallery.removeChild(livePreview);
atEnd();
divProgress = null;
};
var funProgress = function(id_task) {
requestWakeLock();
request("./internal/progress", {id_task: id_task, live_preview: false}, function(res) {
if (res.completed) {
removeProgressBar();
return;
}
let progressText = "";
divInner.style.width = ((res.progress || 0) * 100.0) + '%';
divInner.style.background = res.progress ? "" : "transparent";
if (res.progress > 0) {
progressText = ((res.progress || 0) * 100.0).toFixed(0) + '%';
}
if (res.eta) {
progressText += " ETA: " + formatTime(res.eta);
}
setTitle(progressText);
if (res.textinfo && res.textinfo.indexOf("\n") == -1) {
progressText = res.textinfo + " " + progressText;
}
divInner.textContent = progressText;
var elapsedFromStart = (new Date() - dateStart) / 1000;
if (res.active) wasEverActive = true;
if (!res.active && wasEverActive) {
removeProgressBar();
return;
}
if (elapsedFromStart > inactivityTimeout && !res.queued && !res.active) {
removeProgressBar();
return;
}
if (onProgress) {
onProgress(res);
}
setTimeout(() => {
funProgress(id_task, res.id_live_preview);
}, opts.live_preview_refresh_period || 500);
}, function() {
removeProgressBar();
});
};
var funLivePreview = function(id_task, id_live_preview) {
request("./internal/progress", {id_task: id_task, id_live_preview: id_live_preview}, function(res) {
if (!divProgress) {
return;
}
if (res.live_preview && gallery) {
var img = new Image();
img.onload = function() {
if (!livePreview) {
livePreview = document.createElement('div');
livePreview.className = 'livePreview';
gallery.insertBefore(livePreview, gallery.firstElementChild);
}
livePreview.appendChild(img);
if (livePreview.childElementCount > 2) {
livePreview.removeChild(livePreview.firstElementChild);
}
};
img.src = res.live_preview;
}
setTimeout(() => {
funLivePreview(id_task, res.id_live_preview);
}, opts.live_preview_refresh_period || 500);
}, function() {
removeProgressBar();
});
};
funProgress(id_task, 0);
if (gallery) {
funLivePreview(id_task, 0);
}
}

Some files were not shown because too many files have changed in this diff Show More