Merge branch 'master' into xygrid_infotext_improvements

.github/ISSUE_TEMPLATE/bug_report.md

----
-name: Bug report
-about: Create a report to help us improve
-title: ''
-labels: bug-report
-assignees: ''
-
----
-
-**Describe the bug**
-A clear and concise description of what the bug is.
-
-**To Reproduce**
-Steps to reproduce the behavior:
-1. Go to '...'
-2. Click on '....'
-3. Scroll down to '....'
-4. See error
-
-**Expected behavior**
-A clear and concise description of what you expected to happen.
-
-**Screenshots**
-If applicable, add screenshots to help explain your problem.
-
-**Desktop (please complete the following information):**
- - OS: [e.g. Windows, Linux]
- - Browser [e.g. chrome, safari]
- - Commit revision [looks like this: e68484500f76a33ba477d5a99340ab30451e557b; can be seen when launching webui.bat, or obtained manually by running `git rev-parse HEAD`]
-
-**Additional context**
-Add any other context about the problem here.

.github/ISSUE_TEMPLATE/bug_report.yml

+name: Bug Report
+description: You think somethings is broken in the UI
+title: "[Bug]: "
+labels: ["bug-report"]
+
+body:
+  - type: checkboxes
+    attributes:
+      label: Is there an existing issue for this?
+      description: Please search to see if an issue already exists for the bug you encountered, and that it hasn't been fixed 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, don't forget to fill "What OS..." 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
+    validations:
+      required: true
+  - type: textarea
+    id: steps
+    attributes:
+      label: Steps to reproduce the problem
+      description: Please provide us with precise step by step information on how to reproduce the bug
+      value: |
+        1. Go to .... 
+        2. Press ....
+        3. ...
+    validations:
+      required: true
+  - type: textarea
+    id: what-should
+    attributes:
+      label: What should have happened?
+      description: tell what you think the normal behavior should be
+    validations:
+      required: true
+  - type: input
+    id: commit
+    attributes:
+      label: Commit where the problem happens
+      description: Which commit are you running ? (Do not write *Latest version/repo/commit*, as this means nothing and will have changed by the time we read your issue. Rather, copy the **Commit hash** shown in the cmd/terminal when you launch the UI)
+    validations:
+      required: true
+  - type: dropdown
+    id: platforms
+    attributes:
+      label: What platforms do you use to access UI ?
+      multiple: true
+      options:
+        - Windows
+        - Linux
+        - MacOS
+        - iOS
+        - Android
+        - Other/Cloud
+  - 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
+  - type: textarea
+    id: cmdargs
+    attributes:
+      label: Command Line Arguments
+      description: Are you using any launching parameters/command line arguments (modified webui-user.py) ? If yes, please write them below
+      render: Shell
+  - type: textarea
+    id: misc
+    attributes:
+      label: Additional information, context and logs
+      description: Please provide us with any relevant additional info, context or log output.

.github/ISSUE_TEMPLATE/config.yml

+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.

.github/ISSUE_TEMPLATE/feature_request.md

----
-name: Feature request
-about: Suggest an idea for this project
-title: ''
-labels: ''
-assignees: ''
-
----
-
-**Is your feature request related to a problem? Please describe.**
-A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
-
-**Describe the solution you'd like**
-A clear and concise description of what you want to happen.
-
-**Describe alternatives you've considered**
-A clear and concise description of any alternative solutions or features you've considered.
-
-**Additional context**
-Add any other context or screenshots about the feature request here.

.github/ISSUE_TEMPLATE/feature_request.yml

+name: Feature request
+description: Suggest an idea for this project
+title: "[Feature Request]: "
+labels: ["suggestion"]
+
+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.

.github/PULL_REQUEST_TEMPLATE/pull_request_template.md

+# Please read the [contributing wiki page](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Contributing) before submitting a pull request!
+
+If you have a large change, pay special attention to this paragraph:
+
+> Before making changes, if you think that your feature will result in more than 100 lines changing, find me and talk to me about the feature you are proposing. It pains me to reject the hard work someone else did, but I won't add everything to the repo, and it's better if the rejection happens before you have to waste time working on the feature.
+
+Otherwise, after making sure you're following the rules described in wiki page, remove this section and continue on.
+
+**Describe what this pull request is trying to achieve.**
+
+A clear and concise description of what you're trying to accomplish with this, so your intent doesn't have to be extracted from your code.
+
+**Additional notes and description of your changes**
+
+More technical discussion about your changes go here, plus anything that a maintainer might have to specifically take a look at, or be wary of.
+
+**Environment this was tested in**
+
+List the environment you have developed / tested this on. As per the contributing page, changes should be able to work on Windows out of the box.
+ - OS: [e.g. Windows, Linux]
+ - Browser [e.g. chrome, safari]
+ - Graphics card [e.g. NVIDIA RTX 2080 8GB, AMD RX 6600 8GB]
+
+**Screenshots or videos of your changes**
+
+If applicable, screenshots or a video showing off your changes. If it edits an existing UI, it should ideally contain a comparison of what used to be there, before your changes were made.
+
+This is **required** for anything that touches the user interface.
\ No newline at end of file

.github/workflows/on_pull_request.yaml

+# See https://github.com/actions/starter-workflows/blob/1067f16ad8a1eac328834e4b0ae24f7d206f810d/ci/pylint.yml for original reference file
+name: Run Linting/Formatting on Pull Requests
+
+on:
+  - push
+  - pull_request
+  # See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#onpull_requestpull_request_targetbranchesbranches-ignore for syntax docs
+  # if you want to filter out branches, delete the `- pull_request` and uncomment these lines :
+  # pull_request:  
+  #  branches:
+  #    - master
+  #  branches-ignore:
+  #    - development
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout Code
+        uses: actions/checkout@v3
+      - name: Set up Python 3.10
+        uses: actions/setup-python@v3
+        with:
+          python-version: 3.10.6
+      - uses: actions/cache@v2
+        with:
+          path: ~/.cache/pip
+          key: ${{ runner.os }}-pip-${{ hashFiles('**/requirements.txt') }}
+          restore-keys: |
+            ${{ runner.os }}-pip-
+      - name: Install PyLint
+        run: | 
+          python -m pip install --upgrade pip
+          pip install pylint
+      # This lets PyLint check to see if it can resolve imports
+      - name: Install dependencies
+        run : |
+          export COMMANDLINE_ARGS="--skip-torch-cuda-test --exit"
+          python launch.py
+      - name: Analysing the code with pylint
+        run: |
+          pylint $(git ls-files '*.py')

.github/workflows/run_tests.yaml

+name: Run basic features tests on CPU with empty SD model
+
+on:
+  - push
+  - pull_request
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout Code
+        uses: actions/checkout@v3
+      - name: Set up Python 3.10
+        uses: actions/setup-python@v4
+        with:
+          python-version: 3.10.6
+      - uses: actions/cache@v3
+        with:
+          path: ~/.cache/pip
+          key: ${{ runner.os }}-pip-${{ hashFiles('**/requirements.txt') }}
+          restore-keys: ${{ runner.os }}-pip-
+      - name: Run tests
+        run: python launch.py --tests basic_features --no-half --disable-opt-split-attention --use-cpu all --skip-torch-cuda-test
+      - name: Upload main app stdout-stderr
+        uses: actions/upload-artifact@v3
+        if: always()
+        with:
+          name: stdout-stderr
+          path: |
+            test/stdout.txt
+            test/stderr.txt

.gitignore

 __pycache__
 *.ckpt
+*.safetensors
 *.pth
 /ESRGAN/*
 /SwinIR/*
@@ -17,6 +18,7 @@ __pycache__
 /webui.settings.bat
 /embeddings
 /styles.csv
+/params.txt
 /styles.csv.bak
 /webui-user.bat
 /webui-user.sh
@@ -25,3 +27,8 @@ __pycache__
 /.idea
 notification.mp3
 /SwinIR
+/textual_inversion
+.vscode
+/extensions
+/test/stdout.txt
+/test/stderr.txt

.pylintrc

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

CODEOWNERS

+*       @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.
+
+

README.md

@@ -11,39 +11,44 @@ Check the [custom scripts](https://github.com/AUTOMATIC1111/stable-diffusion-web
 - One click install and run script (but you still must install python and git)
 - Outpainting
 - Inpainting
-- Prompt
-- Stable Diffusion upscale
+- Color Sketch
+- Prompt Matrix
+- Stable Diffusion Upscale
 - Attention, specify parts of text that the model should pay more attention to
-    - a man in a ((txuedo)) - will pay more attentinoto tuxedo
-    - a man in a (txuedo:1.21) - alternative syntax
-- Loopback, run img2img procvessing multiple times
+    - 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 to automatically adjust attention to selected text (code contributed by anonymous user)
+- Loopback, run img2img processing multiple times
 - X/Y plot, a way to draw a 2 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, neural network upscaler
+    - 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 
-- Prompt length validation
-     - get length of prompt in tokensas you type
-     - get a warning after geenration if some text was truncated
+- 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 commandline flag to enable)
+- 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
 - Random artist button
@@ -56,19 +61,37 @@ Check the [custom scripts](https://github.com/AUTOMATIC1111/stable-diffusion-web
 - 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
+- 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 two checkpoints into one
+- 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
+- Use Hypernetworks
+- Use VAEs
+- 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
 
 ## 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 both [NVidia](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-NVidia-GPUs) (recommended) and [AMD](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-AMD-GPUs) GPUs.
 
-Alternatively, use Google Colab:
+Alternatively, use online services (like Google Colab):
 
-- [Colab, maintained by Akaibu](https://colab.research.google.com/drive/1kw3egmSn-KgWsikYvOMjJkVDsPLjEMzl)
-- [Colab, original by me, outdated](https://colab.research.google.com/drive/1Iy-xW9t1-OQWhb0hNxueGij8phCyluOh).
+- [List of Online Services](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Online-Services)
 
 ### Automatic Installation on Windows
 1. Install [Python 3.10.6](https://www.python.org/downloads/windows/), checking "Add Python to PATH"
@@ -104,17 +127,27 @@ Here's how to add code to this repo: [Contributing](https://github.com/AUTOMATIC
 The documentation was moved from this README over to the project's [wiki](https://github.com/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/CompVis/stable-diffusion, https://github.com/CompVis/taming-transformers
 - k-diffusion - https://github.com/crowsonkb/k-diffusion.git
 - 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
-- Doggettx - Cross Attention layer optimization - https://github.com/Doggettx/stable-diffusion, original idea for prompt editing.
+- 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)
+- 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
+- Security advice - RyotaK
 - Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user.
 - (You)

artists.csv

@@ -523,7 +523,6 @@ Affandi,0.7170285,nudity
 Diane Arbus,0.655138,digipa-high-impact
 Joseph Ducreux,0.65247905,digipa-high-impact
 Berthe Morisot,0.7165984,fineart
-Hilma AF Klint,0.71643853,scribbles
 Hilma af Klint,0.71643853,scribbles
 Filippino Lippi,0.7163017,fineart
 Leonid Afremov,0.7163005,fineart
@@ -738,14 +737,12 @@ Abraham Mignon,0.60605425,fineart
 Albert Bloch,0.69573116,nudity
 Charles Dana Gibson,0.67155975,fineart
 Alexandre-Évariste Fragonard,0.6507174,fineart
-Alexandre-Évariste Fragonard,0.6507174,fineart
 Ernst Fuchs,0.6953538,nudity
 Alfredo Jaar,0.6952965,digipa-high-impact
 Judy Chicago,0.6952246,weird
 Frans van Mieris the Younger,0.6951849,fineart
 Aertgen van Leyden,0.6951305,fineart
 Emily Carr,0.69512105,fineart
-Frances Macdonald,0.6950408,scribbles
 Frances MacDonald,0.6950408,scribbles
 Hannah Höch,0.69495845,scribbles
 Gillis Rombouts,0.58770025,fineart
@@ -895,7 +892,6 @@ Richard McGuire,0.6820089,scribbles
 Anni Albers,0.65708244,digipa-high-impact
 Aleksey Savrasov,0.65207493,fineart
 Wayne Barlowe,0.6537874,fineart
-Giorgio De Chirico,0.6815907,fineart
 Giorgio de Chirico,0.6815907,fineart
 Ernest Procter,0.6815795,fineart
 Adriaen Brouwer,0.6815058,fineart
@@ -1045,7 +1041,6 @@ Bakemono Zukushi,0.67051035,anime
 Lucy Madox Brown,0.67032814,fineart
 Paul Wonner,0.6700563,scribbles
 Guido Borelli Da Caluso,0.66966087,digipa-high-impact
-Guido Borelli da Caluso,0.66966087,digipa-high-impact
 Emil Alzamora,0.5844039,nudity
 Heinrich Brocksieper,0.64469147,fineart
 Dan Smith,0.669563,digipa-high-impact
@@ -1242,7 +1237,6 @@ Betty Churcher,0.65387225,fineart
 Claes Corneliszoon Moeyaert,0.65386075,fineart
 David Bomberg,0.6537477,fineart
 Abraham Bosschaert,0.6535562,fineart
-Giuseppe De Nittis,0.65354455,fineart
 Giuseppe de Nittis,0.65354455,fineart
 John La Farge,0.65342575,fineart
 Frits Thaulow,0.65341854,fineart
@@ -1523,7 +1517,6 @@ Gertrude Harvey,0.5903887,fineart
 Grant Wood,0.6266253,fineart
 Fyodor Vasilyev,0.5234919,digipa-med-impact
 Cagnaccio di San Pietro,0.6261671,fineart
-Cagnaccio Di San Pietro,0.6261671,fineart
 Doris Boulton-Maude,0.62593174,fineart
 Adolf Hirémy-Hirschl,0.5946784,fineart
 Harold von Schmidt,0.6256755,fineart
@@ -2412,7 +2405,6 @@ Hermann Feierabend,0.5346168,digipa-high-impact
 Antonio Donghi,0.4610982,digipa-low-impact
 Adonna Khare,0.4858036,digipa-med-impact
 James Stokoe,0.5015107,digipa-med-impact
-Art & Language,0.5341332,digipa-high-impact
 Agustín Fernández,0.53403986,fineart
 Germán Londoño,0.5338712,fineart
 Emmanuelle Moureaux,0.5335641,digipa-high-impact

configs/alt-diffusion-inference.yaml

+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: True
+        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"
\ No newline at end of file

configs/v1-inference.yaml

+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: True
+        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

environment-wsl2.yaml

@@ -3,9 +3,9 @@ channels:
   - pytorch
   - defaults
 dependencies:
-  - python=3.8.5
-  - pip=20.3
+  - python=3.10
+  - pip=22.2.2
   - cudatoolkit=11.3
-  - pytorch=1.11.0
-  - torchvision=0.12.0
-  - numpy=1.19.2
+  - pytorch=1.12.1
+  - torchvision=0.13.1
+  - numpy=1.23.1
\ No newline at end of file

modules/ldsr_model_arch.py → extensions-builtin/LDSR/ldsr_model_arch.py

+import os
 import gc
 import time
 import warnings
@@ -8,27 +9,49 @@ 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
 
 warnings.filterwarnings("ignore", category=UserWarning)
 
+cached_ldsr_model: torch.nn.Module = None
+
 
 # Create LDSR Class
 class LDSR:
     def load_model_from_config(self, half_attention):
-        print(f"Loading model from {self.modelPath}")
-        pl_sd = torch.load(self.modelPath, map_location="cpu")
-        sd = pl_sd["state_dict"]
-        config = OmegaConf.load(self.yamlPath)
-        model = instantiate_from_config(config.model)
-        model.load_state_dict(sd, strict=False)
-        model.cuda()
-        if half_attention:
-            model = model.half()
-
-        model.eval()
+        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):
@@ -93,7 +116,8 @@ class LDSR:
         down_sample_method = 'Lanczos'
 
         gc.collect()
-        torch.cuda.empty_cache()
+        if torch.cuda.is_available:
+            torch.cuda.empty_cache()
 
         im_og = image
         width_og, height_og = im_og.size
@@ -101,8 +125,8 @@ class LDSR:
         down_sample_rate = target_scale / 4
         wd = width_og * down_sample_rate
         hd = height_og * down_sample_rate
-        width_downsampled_pre = int(wd)
-        height_downsampled_pre = int(hd)
+        width_downsampled_pre = int(np.ceil(wd))
+        height_downsampled_pre = int(np.ceil(hd))
 
         if down_sample_rate != 1:
             print(
@@ -110,7 +134,12 @@ class LDSR:
             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)")
-        logs = self.run(model["model"], im_og, diffusion_steps, eta)
+        
+        # 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()
@@ -120,9 +149,14 @@ class LDSR:
         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()
-        torch.cuda.empty_cache()
+        if torch.cuda.is_available:
+            torch.cuda.empty_cache()
+
         return a
 
 
@@ -137,7 +171,7 @@ def get_cond(selected_path):
     c = rearrange(c, '1 c h w -> 1 h w c')
     c = 2. * c - 1.
 
-    c = c.to(torch.device("cuda"))
+    c = c.to(shared.device)
     example["LR_image"] = c
     example["image"] = c_up
 

extensions-builtin/LDSR/preload.py

+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'))

modules/ldsr_model.py → extensions-builtin/LDSR/scripts/ldsr_model.py

@@ -5,15 +5,14 @@ import traceback
 from basicsr.utils.download_util import load_file_from_url
 
 from modules.upscaler import Upscaler, UpscalerData
-from modules.ldsr_model_arch import LDSR
-from modules import shared
-from modules.paths import models_path
+from ldsr_model_arch import LDSR
+from modules import shared, script_callbacks
+import sd_hijack_autoencoder, sd_hijack_ddpm_v1
 
 
 class UpscalerLDSR(Upscaler):
     def __init__(self, user_path):
         self.name = "LDSR"
-        self.model_path = os.path.join(models_path, self.name)
         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"
@@ -26,6 +25,7 @@ class UpscalerLDSR(Upscaler):
         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")
+        safetensors_model_path = os.path.join(self.model_path, "model.safetensors")
         if os.path.exists(yaml_path):
             statinfo = os.stat(yaml_path)
             if statinfo.st_size >= 10485760:
@@ -34,8 +34,11 @@ class UpscalerLDSR(Upscaler):
         if os.path.exists(old_model_path):
             print("Renaming model from model.pth to model.ckpt")
             os.rename(old_model_path, new_model_path)
-        model = load_file_from_url(url=self.model_url, model_dir=self.model_path,
-                                   file_name="model.ckpt", progress=True)
+        if os.path.exists(safetensors_model_path):
+            model = safetensors_model_path
+        else:
+            model = load_file_from_url(url=self.model_url, model_dir=self.model_path,
+                                       file_name="model.ckpt", progress=True)
         yaml = load_file_from_url(url=self.yaml_url, model_dir=self.model_path,
                                   file_name="project.yaml", progress=True)
 
@@ -54,3 +57,13 @@ class UpscalerLDSR(Upscaler):
             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)

extensions-builtin/LDSR/sd_hijack_autoencoder.py

+# 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 torch
+import pytorch_lightning as pl
+import torch.nn.functional as F
+from contextlib import contextmanager
+from taming.modules.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
+
+class VQModel(pl.LightningModule):
+    def __init__(self,
+                 ddconfig,
+                 lossconfig,
+                 n_embed,
+                 embed_dim,
+                 ckpt_path=None,
+                 ignore_keys=[],
+                 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)
+        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=list()):
+        sd = torch.load(path, map_location="cpu")["state_dict"]
+        keys = list(sd.keys())
+        for k in keys:
+            for ik in ignore_keys:
+                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 len(missing) > 0:
+            print(f"Missing Keys: {missing}")
+            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():
+            log_dict_ema = 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 = dict()
+        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__(embed_dim=embed_dim, *args, **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
+
+setattr(ldm.models.autoencoder, "VQModel", VQModel)
+setattr(ldm.models.autoencoder, "VQModelInterface", VQModelInterface)

extensions-builtin/ScuNET/preload.py

+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'))

modules/bsrgan_model.py → extensions-builtin/ScuNET/scripts/scunet_model.py

@@ -8,49 +8,54 @@ import torch
 from basicsr.utils.download_util import load_file_from_url
 
 import modules.upscaler
-from modules import shared, modelloader
-from modules.bsrgan_model_arch import RRDBNet
-from modules.paths import models_path
+from modules import devices, modelloader
+from scunet_model_arch import SCUNet as net
 
 
-class UpscalerBSRGAN(modules.upscaler.Upscaler):
+class UpscalerScuNET(modules.upscaler.Upscaler):
     def __init__(self, dirname):
-        self.name = "BSRGAN"
-        self.model_path = os.path.join(models_path, self.name)
-        self.model_name = "BSRGAN 4x"
-        self.model_url = "https://github.com/cszn/KAIR/releases/download/v1.0/BSRGAN.pth"
+        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=[".pt", ".pth"])
+        model_paths = self.find_models(ext_filter=[".pth"])
         scalers = []
-        if len(model_paths) == 0:
-            scaler_data = modules.upscaler.UpscalerData(self.model_name, self.model_url, self, 4)
-            scalers.append(scaler_data)
+        add_model2 = True
         for file in model_paths:
             if "http" in file:
                 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:
-                print(f"Error loading BSRGAN model: {file}", file=sys.stderr)
+                print(f"Error loading ScuNET model: {file}", file=sys.stderr)
                 print(traceback.format_exc(), file=sys.stderr)
+        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, selected_file):
         torch.cuda.empty_cache()
+
         model = self.load_model(selected_file)
         if model is None:
             return img
-        model.to(shared.device)
-        torch.cuda.empty_cache()
+
+        device = devices.get_device_for('scunet')
         img = np.array(img)
         img = img[:, :, ::-1]
         img = np.moveaxis(img, 2, 0) / 255
         img = torch.from_numpy(img).float()
-        img = img.unsqueeze(0).to(shared.device)
+        img = img.unsqueeze(0).to(device)
+
         with torch.no_grad():
             output = model(img)
         output = output.squeeze().float().cpu().clamp_(0, 1).numpy()
@@ -61,18 +66,22 @@ class UpscalerBSRGAN(modules.upscaler.Upscaler):
         return PIL.Image.fromarray(output, 'RGB')
 
     def load_model(self, path: str):
+        device = devices.get_device_for('scunet')
         if "http" in path:
             filename = load_file_from_url(url=self.model_url, model_dir=self.model_path, file_name="%s.pth" % self.name,
                                           progress=True)
         else:
             filename = path
-        if not os.path.exists(filename) or filename is None:
-            print(f"BSRGAN: Unable to load model from {filename}", file=sys.stderr)
+        if not os.path.exists(os.path.join(self.model_path, filename)) or filename is None:
+            print(f"ScuNET: Unable to load model from {filename}", file=sys.stderr)
             return None
-        model = RRDBNet(in_nc=3, out_nc=3, nf=64, nb=23, gc=32, sf=4)  # define network
+
+        model = net(in_nc=3, config=[4, 4, 4, 4, 4, 4, 4], dim=64)
         model.load_state_dict(torch.load(filename), strict=True)
         model.eval()
         for k, v in model.named_parameters():
             v.requires_grad = False
+        model = model.to(device)
+
         return model
 

extensions-builtin/ScuNET/scunet_model_arch.py

+# -*- coding: utf-8 -*-
+import numpy as np
+import torch
+import torch.nn as nn
+from einops import rearrange
+from einops.layers.torch import Rearrange
+from timm.models.layers import trunc_normal_, DropPath
+
+
+class WMSA(nn.Module):
+    """ Self-attention module in Swin Transformer
+    """
+
+    def __init__(self, input_dim, output_dim, head_dim, window_size, type):
+        super(WMSA, self).__init__()
+        self.input_dim = input_dim
+        self.output_dim = output_dim
+        self.head_dim = head_dim
+        self.scale = self.head_dim ** -0.5
+        self.n_heads = input_dim // head_dim
+        self.window_size = window_size
+        self.type = type
+        self.embedding_layer = nn.Linear(self.input_dim, 3 * self.input_dim, bias=True)
+
+        self.relative_position_params = nn.Parameter(
+            torch.zeros((2 * window_size - 1) * (2 * window_size - 1), self.n_heads))
+
+        self.linear = nn.Linear(self.input_dim, self.output_dim)
+
+        trunc_normal_(self.relative_position_params, std=.02)
+        self.relative_position_params = torch.nn.Parameter(
+            self.relative_position_params.view(2 * window_size - 1, 2 * window_size - 1, self.n_heads).transpose(1,
+                                                                                                                 2).transpose(
+                0, 1))
+
+    def generate_mask(self, h, w, p, shift):
+        """ generating the mask of SW-MSA
+        Args:
+            shift: shift parameters in CyclicShift.
+        Returns:
+            attn_mask: should be (1 1 w p p),
+        """
+        # supporting square.
+        attn_mask = torch.zeros(h, w, p, p, p, p, dtype=torch.bool, device=self.relative_position_params.device)
+        if self.type == 'W':
+            return attn_mask
+
+        s = p - shift
+        attn_mask[-1, :, :s, :, s:, :] = True
+        attn_mask[-1, :, s:, :, :s, :] = True
+        attn_mask[:, -1, :, :s, :, s:] = True
+        attn_mask[:, -1, :, s:, :, :s] = True
+        attn_mask = rearrange(attn_mask, 'w1 w2 p1 p2 p3 p4 -> 1 1 (w1 w2) (p1 p2) (p3 p4)')
+        return attn_mask
+
+    def forward(self, x):
+        """ Forward pass of Window Multi-head Self-attention module.
+        Args:
+            x: input tensor with shape of [b h w c];
+            attn_mask: attention mask, fill -inf where the value is True;
+        Returns:
+            output: tensor shape [b h w c]
+        """
+        if self.type != 'W': x = torch.roll(x, shifts=(-(self.window_size // 2), -(self.window_size // 2)), dims=(1, 2))
+        x = rearrange(x, 'b (w1 p1) (w2 p2) c -> b w1 w2 p1 p2 c', p1=self.window_size, p2=self.window_size)
+        h_windows = x.size(1)
+        w_windows = x.size(2)
+        # square validation
+        # assert h_windows == w_windows
+
+        x = rearrange(x, 'b w1 w2 p1 p2 c -> b (w1 w2) (p1 p2) c', p1=self.window_size, p2=self.window_size)
+        qkv = self.embedding_layer(x)
+        q, k, v = rearrange(qkv, 'b nw np (threeh c) -> threeh b nw np c', c=self.head_dim).chunk(3, dim=0)
+        sim = torch.einsum('hbwpc,hbwqc->hbwpq', q, k) * self.scale
+        # Adding learnable relative embedding
+        sim = sim + rearrange(self.relative_embedding(), 'h p q -> h 1 1 p q')
+        # Using Attn Mask to distinguish different subwindows.
+        if self.type != 'W':
+            attn_mask = self.generate_mask(h_windows, w_windows, self.window_size, shift=self.window_size // 2)
+            sim = sim.masked_fill_(attn_mask, float("-inf"))
+
+        probs = nn.functional.softmax(sim, dim=-1)
+        output = torch.einsum('hbwij,hbwjc->hbwic', probs, v)
+        output = rearrange(output, 'h b w p c -> b w p (h c)')
+        output = self.linear(output)
+        output = rearrange(output, 'b (w1 w2) (p1 p2) c -> b (w1 p1) (w2 p2) c', w1=h_windows, p1=self.window_size)
+
+        if self.type != 'W': output = torch.roll(output, shifts=(self.window_size // 2, self.window_size // 2),
+                                                 dims=(1, 2))
+        return output
+
+    def relative_embedding(self):
+        cord = torch.tensor(np.array([[i, j] for i in range(self.window_size) for j in range(self.window_size)]))
+        relation = cord[:, None, :] - cord[None, :, :] + self.window_size - 1
+        # negative is allowed
+        return self.relative_position_params[:, relation[:, :, 0].long(), relation[:, :, 1].long()]
+
+
+class Block(nn.Module):
+    def __init__(self, input_dim, output_dim, head_dim, window_size, drop_path, type='W', input_resolution=None):
+        """ SwinTransformer Block
+        """
+        super(Block, self).__init__()
+        self.input_dim = input_dim
+        self.output_dim = output_dim
+        assert type in ['W', 'SW']
+        self.type = type
+        if input_resolution <= window_size:
+            self.type = 'W'
+
+        self.ln1 = nn.LayerNorm(input_dim)
+        self.msa = WMSA(input_dim, input_dim, head_dim, window_size, self.type)
+        self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
+        self.ln2 = nn.LayerNorm(input_dim)
+        self.mlp = nn.Sequential(
+            nn.Linear(input_dim, 4 * input_dim),
+            nn.GELU(),
+            nn.Linear(4 * input_dim, output_dim),
+        )
+
+    def forward(self, x):
+        x = x + self.drop_path(self.msa(self.ln1(x)))
+        x = x + self.drop_path(self.mlp(self.ln2(x)))
+        return x
+
+
+class ConvTransBlock(nn.Module):
+    def __init__(self, conv_dim, trans_dim, head_dim, window_size, drop_path, type='W', input_resolution=None):
+        """ SwinTransformer and Conv Block
+        """
+        super(ConvTransBlock, self).__init__()
+        self.conv_dim = conv_dim
+        self.trans_dim = trans_dim
+        self.head_dim = head_dim
+        self.window_size = window_size
+        self.drop_path = drop_path
+        self.type = type
+        self.input_resolution = input_resolution
+
+        assert self.type in ['W', 'SW']
+        if self.input_resolution <= self.window_size:
+            self.type = 'W'
+
+        self.trans_block = Block(self.trans_dim, self.trans_dim, self.head_dim, self.window_size, self.drop_path,
+                                 self.type, self.input_resolution)
+        self.conv1_1 = nn.Conv2d(self.conv_dim + self.trans_dim, self.conv_dim + self.trans_dim, 1, 1, 0, bias=True)
+        self.conv1_2 = nn.Conv2d(self.conv_dim + self.trans_dim, self.conv_dim + self.trans_dim, 1, 1, 0, bias=True)
+
+        self.conv_block = nn.Sequential(
+            nn.Conv2d(self.conv_dim, self.conv_dim, 3, 1, 1, bias=False),
+            nn.ReLU(True),
+            nn.Conv2d(self.conv_dim, self.conv_dim, 3, 1, 1, bias=False)
+        )
+
+    def forward(self, x):
+        conv_x, trans_x = torch.split(self.conv1_1(x), (self.conv_dim, self.trans_dim), dim=1)
+        conv_x = self.conv_block(conv_x) + conv_x
+        trans_x = Rearrange('b c h w -> b h w c')(trans_x)
+        trans_x = self.trans_block(trans_x)
+        trans_x = Rearrange('b h w c -> b c h w')(trans_x)
+        res = self.conv1_2(torch.cat((conv_x, trans_x), dim=1))
+        x = x + res
+
+        return x
+
+
+class SCUNet(nn.Module):
+    # def __init__(self, in_nc=3, config=[2, 2, 2, 2, 2, 2, 2], dim=64, drop_path_rate=0.0, input_resolution=256):
+    def __init__(self, in_nc=3, config=None, dim=64, drop_path_rate=0.0, input_resolution=256):
+        super(SCUNet, self).__init__()
+        if config is None:
+            config = [2, 2, 2, 2, 2, 2, 2]
+        self.config = config
+        self.dim = dim
+        self.head_dim = 32
+        self.window_size = 8
+
+        # drop path rate for each layer
+        dpr = [x.item() for x in torch.linspace(0, drop_path_rate, sum(config))]
+
+        self.m_head = [nn.Conv2d(in_nc, dim, 3, 1, 1, bias=False)]
+
+        begin = 0
+        self.m_down1 = [ConvTransBlock(dim // 2, dim // 2, self.head_dim, self.window_size, dpr[i + begin],
+                                       'W' if not i % 2 else 'SW', input_resolution)
+                        for i in range(config[0])] + \
+                       [nn.Conv2d(dim, 2 * dim, 2, 2, 0, bias=False)]
+
+        begin += config[0]
+        self.m_down2 = [ConvTransBlock(dim, dim, self.head_dim, self.window_size, dpr[i + begin],
+                                       'W' if not i % 2 else 'SW', input_resolution // 2)
+                        for i in range(config[1])] + \
+                       [nn.Conv2d(2 * dim, 4 * dim, 2, 2, 0, bias=False)]
+
+        begin += config[1]
+        self.m_down3 = [ConvTransBlock(2 * dim, 2 * dim, self.head_dim, self.window_size, dpr[i + begin],
+                                       'W' if not i % 2 else 'SW', input_resolution // 4)
+                        for i in range(config[2])] + \
+                       [nn.Conv2d(4 * dim, 8 * dim, 2, 2, 0, bias=False)]
+
+        begin += config[2]
+        self.m_body = [ConvTransBlock(4 * dim, 4 * dim, self.head_dim, self.window_size, dpr[i + begin],
+                                      'W' if not i % 2 else 'SW', input_resolution // 8)
+                       for i in range(config[3])]
+
+        begin += config[3]
+        self.m_up3 = [nn.ConvTranspose2d(8 * dim, 4 * dim, 2, 2, 0, bias=False), ] + \
+                     [ConvTransBlock(2 * dim, 2 * dim, self.head_dim, self.window_size, dpr[i + begin],
+                                     'W' if not i % 2 else 'SW', input_resolution // 4)
+                      for i in range(config[4])]
+
+        begin += config[4]
+        self.m_up2 = [nn.ConvTranspose2d(4 * dim, 2 * dim, 2, 2, 0, bias=False), ] + \
+                     [ConvTransBlock(dim, dim, self.head_dim, self.window_size, dpr[i + begin],
+                                     'W' if not i % 2 else 'SW', input_resolution // 2)
+                      for i in range(config[5])]
+
+        begin += config[5]
+        self.m_up1 = [nn.ConvTranspose2d(2 * dim, dim, 2, 2, 0, bias=False), ] + \
+                     [ConvTransBlock(dim // 2, dim // 2, self.head_dim, self.window_size, dpr[i + begin],
+                                     'W' if not i % 2 else 'SW', input_resolution)
+                      for i in range(config[6])]
+
+        self.m_tail = [nn.Conv2d(dim, in_nc, 3, 1, 1, bias=False)]
+
+        self.m_head = nn.Sequential(*self.m_head)
+        self.m_down1 = nn.Sequential(*self.m_down1)
+        self.m_down2 = nn.Sequential(*self.m_down2)
+        self.m_down3 = nn.Sequential(*self.m_down3)
+        self.m_body = nn.Sequential(*self.m_body)
+        self.m_up3 = nn.Sequential(*self.m_up3)
+        self.m_up2 = nn.Sequential(*self.m_up2)
+        self.m_up1 = nn.Sequential(*self.m_up1)
+        self.m_tail = nn.Sequential(*self.m_tail)
+        # self.apply(self._init_weights)
+
+    def forward(self, x0):
+
+        h, w = x0.size()[-2:]
+        paddingBottom = int(np.ceil(h / 64) * 64 - h)
+        paddingRight = int(np.ceil(w / 64) * 64 - w)
+        x0 = nn.ReplicationPad2d((0, paddingRight, 0, paddingBottom))(x0)
+
+        x1 = self.m_head(x0)
+        x2 = self.m_down1(x1)
+        x3 = self.m_down2(x2)
+        x4 = self.m_down3(x3)
+        x = self.m_body(x4)
+        x = self.m_up3(x + x4)
+        x = self.m_up2(x + x3)
+        x = self.m_up1(x + x2)
+        x = self.m_tail(x + x1)
+
+        x = x[..., :h, :w]
+
+        return x
+
+    def _init_weights(self, m):
+        if isinstance(m, nn.Linear):
+            trunc_normal_(m.weight, std=.02)
+            if m.bias is not None:
+                nn.init.constant_(m.bias, 0)
+        elif isinstance(m, nn.LayerNorm):
+            nn.init.constant_(m.bias, 0)
+            nn.init.constant_(m.weight, 1.0)
\ No newline at end of file

extensions-builtin/SwinIR/preload.py

+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'))

modules/swinir_model.py → extensions-builtin/SwinIR/scripts/swinir_model.py

@@ -5,16 +5,16 @@ import numpy as np
 import torch
 from PIL import Image
 from basicsr.utils.download_util import load_file_from_url
+from tqdm import tqdm
 
-from modules import modelloader
-from modules.paths import models_path
-from modules.shared import cmd_opts, opts, device
-from modules.swinir_model_arch import SwinIR as net
+from modules import modelloader, devices, script_callbacks, shared
+from modules.shared import cmd_opts, opts
+from swinir_model_arch import SwinIR as net
+from swinir_model_arch_v2 import Swin2SR as net2
 from modules.upscaler import Upscaler, UpscalerData
 
-precision_scope = (
-    torch.autocast if cmd_opts.precision == "autocast" else contextlib.nullcontext
-)
+
+device_swinir = devices.get_device_for('swinir')
 
 
 class UpscalerSwinIR(Upscaler):
@@ -24,7 +24,6 @@ class UpscalerSwinIR(Upscaler):
                          "/003_realSR_BSRGAN_DFOWMFC_s64w8_SwinIR" \
                          "-L_x4_GAN.pth "
         self.model_name = "SwinIR 4x"
-        self.model_path = os.path.join(models_path, self.name)
         self.user_path = dirname
         super().__init__()
         scalers = []
@@ -42,7 +41,7 @@ class UpscalerSwinIR(Upscaler):
         model = self.load_model(model_file)
         if model is None:
             return img
-        model = model.to(device)
+        model = model.to(device_swinir, dtype=devices.dtype)
         img = upscale(img, model)
         try:
             torch.cuda.empty_cache()
@@ -58,41 +57,63 @@ class UpscalerSwinIR(Upscaler):
             filename = path
         if filename is None or not os.path.exists(filename):
             return None
-        model = net(
+        if filename.endswith(".v2.pth"):
+            model = net2(
             upscale=scale,
             in_chans=3,
             img_size=64,
             window_size=8,
             img_range=1.0,
-            depths=[6, 6, 6, 6, 6, 6, 6, 6, 6],
-            embed_dim=240,
-            num_heads=[8, 8, 8, 8, 8, 8, 8, 8, 8],
+            depths=[6, 6, 6, 6, 6, 6],
+            embed_dim=180,
+            num_heads=[6, 6, 6, 6, 6, 6],
             mlp_ratio=2,
             upsampler="nearest+conv",
-            resi_connection="3conv",
-        )
+            resi_connection="1conv",
+            )
+            params = None
+        else:
+            model = net(
+                upscale=scale,
+                in_chans=3,
+                img_size=64,
+                window_size=8,
+                img_range=1.0,
+                depths=[6, 6, 6, 6, 6, 6, 6, 6, 6],
+                embed_dim=240,
+                num_heads=[8, 8, 8, 8, 8, 8, 8, 8, 8],
+                mlp_ratio=2,
+                upsampler="nearest+conv",
+                resi_connection="3conv",
+            )
+            params = "params_ema"
 
         pretrained_model = torch.load(filename)
-        model.load_state_dict(pretrained_model["params_ema"], strict=True)
-        if not cmd_opts.no_half:
-            model = model.half()
+        if params is not None:
+            model.load_state_dict(pretrained_model[params], strict=True)
+        else:
+            model.load_state_dict(pretrained_model, strict=True)
         return model
 
 
 def upscale(
         img,
         model,
-        tile=opts.SWIN_tile,
-        tile_overlap=opts.SWIN_tile_overlap,
+        tile=None,
+        tile_overlap=None,
         window_size=8,
         scale=4,
 ):
+    tile = tile or opts.SWIN_tile
+    tile_overlap = tile_overlap or opts.SWIN_tile_overlap
+
+
     img = np.array(img)
     img = img[:, :, ::-1]
     img = np.moveaxis(img, 2, 0) / 255
     img = torch.from_numpy(img).float()
-    img = img.unsqueeze(0).to(device)
-    with torch.no_grad(), precision_scope("cuda"):
+    img = img.unsqueeze(0).to(device_swinir, dtype=devices.dtype)
+    with torch.no_grad(), devices.autocast():
         _, _, h_old, w_old = img.size()
         h_pad = (h_old // window_size + 1) * window_size - h_old
         w_pad = (w_old // window_size + 1) * window_size - w_old
@@ -119,21 +140,33 @@ def inference(img, model, tile, tile_overlap, window_size, scale):
     stride = tile - tile_overlap
     h_idx_list = list(range(0, h - tile, stride)) + [h - tile]
     w_idx_list = list(range(0, w - tile, stride)) + [w - tile]
-    E = torch.zeros(b, c, h * sf, w * sf, dtype=torch.half, device=device).type_as(img)
-    W = torch.zeros_like(E, dtype=torch.half, device=device)
-
-    for h_idx in h_idx_list:
-        for w_idx in w_idx_list:
-            in_patch = img[..., h_idx: h_idx + tile, w_idx: w_idx + tile]
-            out_patch = model(in_patch)
-            out_patch_mask = torch.ones_like(out_patch)
-
-            E[
-            ..., h_idx * sf: (h_idx + tile) * sf, w_idx * sf: (w_idx + tile) * sf
-            ].add_(out_patch)
-            W[
-            ..., h_idx * sf: (h_idx + tile) * sf, w_idx * sf: (w_idx + tile) * sf
-            ].add_(out_patch_mask)
+    E = torch.zeros(b, c, h * sf, w * sf, dtype=devices.dtype, device=device_swinir).type_as(img)
+    W = torch.zeros_like(E, dtype=devices.dtype, device=device_swinir)
+
+    with tqdm(total=len(h_idx_list) * len(w_idx_list), desc="SwinIR tiles") as pbar:
+        for h_idx in h_idx_list:
+            for w_idx in w_idx_list:
+                in_patch = img[..., h_idx: h_idx + tile, w_idx: w_idx + tile]
+                out_patch = model(in_patch)
+                out_patch_mask = torch.ones_like(out_patch)
+
+                E[
+                ..., h_idx * sf: (h_idx + tile) * sf, w_idx * sf: (w_idx + tile) * sf
+                ].add_(out_patch)
+                W[
+                ..., h_idx * sf: (h_idx + tile) * sf, w_idx * sf: (w_idx + tile) * sf
+                ].add_(out_patch_mask)
+                pbar.update(1)
     output = E.div_(W)
 
     return output
+
+
+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")))
+
+
+script_callbacks.on_ui_settings(on_ui_settings)

modules/swinir_model_arch.py → extensions-builtin/SwinIR/swinir_model_arch.py

@@ -166,7 +166,7 @@ class SwinTransformerBlock(nn.Module):
 
     Args:
         dim (int): Number of input channels.
-        input_resolution (tuple[int]): Input resulotion.
+        input_resolution (tuple[int]): Input resolution.
         num_heads (int): Number of attention heads.
         window_size (int): Window size.
         shift_size (int): Shift size for SW-MSA.

extensions-builtin/prompt-bracket-checker/javascript/prompt-bracket-checker.js

+// Stable Diffusion WebUI - Bracket checker
+// Version 1.0
+// By Hingashi no Florin/Bwin4L
+// 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(evt) {
+  textArea = evt.target;
+  tabName = evt.target.parentElement.parentElement.id.split("_")[0];
+  counterElt = document.querySelector('gradio-app').shadowRoot.querySelector('#' + tabName + '_token_counter');
+
+  promptName = evt.target.parentElement.parentElement.id.includes('neg') ? ' negative' : '';
+
+  errorStringParen  = '(' + tabName + promptName + ' prompt) - Different number of opening and closing parentheses detected.\n';
+  errorStringSquare = '[' + tabName + promptName + ' prompt] - Different number of opening and closing square brackets detected.\n';
+  errorStringCurly  = '{' + tabName + promptName + ' prompt} - Different number of opening and closing curly brackets detected.\n';
+
+  openBracketRegExp = /\(/g;
+  closeBracketRegExp = /\)/g;
+
+  openSquareBracketRegExp = /\[/g;
+  closeSquareBracketRegExp = /\]/g;
+
+  openCurlyBracketRegExp = /\{/g;
+  closeCurlyBracketRegExp = /\}/g;
+
+  totalOpenBracketMatches = 0;
+  totalCloseBracketMatches = 0;
+  totalOpenSquareBracketMatches = 0;
+  totalCloseSquareBracketMatches = 0;
+  totalOpenCurlyBracketMatches = 0;
+  totalCloseCurlyBracketMatches = 0;
+
+  openBracketMatches = textArea.value.match(openBracketRegExp);
+  if(openBracketMatches) {
+    totalOpenBracketMatches = openBracketMatches.length;
+  }
+
+  closeBracketMatches = textArea.value.match(closeBracketRegExp);
+  if(closeBracketMatches) {
+    totalCloseBracketMatches = closeBracketMatches.length;
+  }
+
+  openSquareBracketMatches = textArea.value.match(openSquareBracketRegExp);
+  if(openSquareBracketMatches) {
+    totalOpenSquareBracketMatches = openSquareBracketMatches.length;
+  }
+
+  closeSquareBracketMatches = textArea.value.match(closeSquareBracketRegExp);
+  if(closeSquareBracketMatches) {
+    totalCloseSquareBracketMatches = closeSquareBracketMatches.length;
+  }
+
+  openCurlyBracketMatches = textArea.value.match(openCurlyBracketRegExp);
+  if(openCurlyBracketMatches) {
+    totalOpenCurlyBracketMatches = openCurlyBracketMatches.length;
+  }
+
+  closeCurlyBracketMatches = textArea.value.match(closeCurlyBracketRegExp);
+  if(closeCurlyBracketMatches) {
+    totalCloseCurlyBracketMatches = closeCurlyBracketMatches.length;
+  }
+
+  if(totalOpenBracketMatches != totalCloseBracketMatches) {
+    if(!counterElt.title.includes(errorStringParen)) {
+      counterElt.title += errorStringParen;
+    }
+  } else {
+    counterElt.title = counterElt.title.replace(errorStringParen, '');
+  }
+
+  if(totalOpenSquareBracketMatches != totalCloseSquareBracketMatches) {
+    if(!counterElt.title.includes(errorStringSquare)) {
+      counterElt.title += errorStringSquare;
+    }
+  } else {
+    counterElt.title = counterElt.title.replace(errorStringSquare, '');
+  }
+
+  if(totalOpenCurlyBracketMatches != totalCloseCurlyBracketMatches) {
+    if(!counterElt.title.includes(errorStringCurly)) {
+      counterElt.title += errorStringCurly;
+    }
+  } else {
+    counterElt.title = counterElt.title.replace(errorStringCurly, '');
+  }
+
+  if(counterElt.title != '') {
+    counterElt.style = 'color: #FF5555;';
+  } else {
+    counterElt.style = '';
+  }
+}
+
+var shadowRootLoaded = setInterval(function() {
+  var shadowTextArea = document.querySelector('gradio-app').shadowRoot.querySelectorAll('#txt2img_prompt > label > textarea');
+  if(shadowTextArea.length < 1) {
+      return false;
+  }
+
+  clearInterval(shadowRootLoaded);
+
+  document.querySelector('gradio-app').shadowRoot.querySelector('#txt2img_prompt').onkeyup = checkBrackets;
+  document.querySelector('gradio-app').shadowRoot.querySelector('#txt2img_neg_prompt').onkeyup = checkBrackets;
+  document.querySelector('gradio-app').shadowRoot.querySelector('#img2img_prompt').onkeyup = checkBrackets;
+  document.querySelector('gradio-app').shadowRoot.querySelector('#img2img_neg_prompt').onkeyup = checkBrackets;
+}, 1000);

extensions-builtin/roll-artist/scripts/roll-artist.py

+import random
+
+from modules import script_callbacks, shared
+import gradio as gr
+
+art_symbol = '\U0001f3a8'  # 🎨
+global_prompt = None
+related_ids = {"txt2img_prompt", "txt2img_clear_prompt", "img2img_prompt", "img2img_clear_prompt" }
+
+
+def roll_artist(prompt):
+    allowed_cats = set([x for x in shared.artist_db.categories() if len(shared.opts.random_artist_categories)==0 or x in shared.opts.random_artist_categories])
+    artist = random.choice([x for x in shared.artist_db.artists if x.category in allowed_cats])
+
+    return prompt + ", " + artist.name if prompt != '' else artist.name
+
+
+def add_roll_button(prompt):
+    roll = gr.Button(value=art_symbol, elem_id="roll", visible=len(shared.artist_db.artists) > 0)
+
+    roll.click(
+        fn=roll_artist,
+        _js="update_txt2img_tokens",
+        inputs=[
+            prompt,
+        ],
+        outputs=[
+            prompt,
+        ]
+    )
+
+
+def after_component(component, **kwargs):
+    global global_prompt
+
+    elem_id = kwargs.get('elem_id', None)
+    if elem_id not in related_ids:
+        return
+
+    if elem_id == "txt2img_prompt":
+        global_prompt = component
+    elif elem_id == "txt2img_clear_prompt":
+        add_roll_button(global_prompt)
+    elif elem_id == "img2img_prompt":
+        global_prompt = component
+    elif elem_id == "img2img_clear_prompt":
+        add_roll_button(global_prompt)
+
+
+script_callbacks.on_after_component(after_component)

html/footer.html

+<div>
+        <a href="/docs">API</a>
+         • 
+        <a href="https://github.com/AUTOMATIC1111/stable-diffusion-webui">Github</a>
+         • 
+        <a href="https://gradio.app">Gradio</a>
+         • 
+        <a href="/" onclick="javascript:gradioApp().getElementById('settings_restart_gradio').click(); return false">Reload UI</a>
+</div>

javascript/aspectRatioOverlay.js

@@ -3,12 +3,12 @@ let currentWidth = null;
 let currentHeight = null;
 let arFrameTimeout = setTimeout(function(){},0);
 
-function dimensionChange(e,dimname){
+function dimensionChange(e, is_width, is_height){
 
-	if(dimname == 'Width'){
+	if(is_width){
 		currentWidth = e.target.value*1.0
 	}
-	if(dimname == 'Height'){
+	if(is_height){
 		currentHeight = e.target.value*1.0
 	}
 
@@ -18,22 +18,13 @@ function dimensionChange(e,dimname){
 		return;
 	}
 
-	var img2imgMode = gradioApp().querySelector('#mode_img2img.tabs > div > button.rounded-t-lg.border-gray-200')
-	if(img2imgMode){
-		img2imgMode=img2imgMode.innerText
-	}else{
-		return;
-	}
-
-	var redrawImage = gradioApp().querySelector('div[data-testid=image] img');
-	var inpaintImage = gradioApp().querySelector('#img2maskimg div[data-testid=image] img')
-
 	var targetElement = null;
 
-	if(img2imgMode=='img2img' && redrawImage){
-		targetElement = redrawImage;
-	}else if(img2imgMode=='Inpaint' && inpaintImage){
-		targetElement = inpaintImage;
+    var tabIndex = get_tab_index('mode_img2img')
+	if(tabIndex == 0){
+		targetElement = gradioApp().querySelector('div[data-testid=image] img');
+	} else if(tabIndex == 1){
+		targetElement = gradioApp().querySelector('#img2maskimg div[data-testid=image] img');
 	}
 
 	if(targetElement){
@@ -98,22 +89,20 @@ onUiUpdate(function(){
 	var inImg2img   = Boolean(gradioApp().querySelector("button.rounded-t-lg.border-gray-200"))
 	if(inImg2img){
 		let inputs = gradioApp().querySelectorAll('input');
-		inputs.forEach(function(e){ 
-			let parentLabel = e.parentElement.querySelector('label')
-			if(parentLabel && parentLabel.innerText){
-				if(!e.classList.contains('scrollwatch')){
-					if(parentLabel.innerText == 'Width' || parentLabel.innerText == 'Height'){
-						e.addEventListener('input', function(e){dimensionChange(e,parentLabel.innerText)} )
-						e.classList.add('scrollwatch')
-					}
-					if(parentLabel.innerText == 'Width'){
-						currentWidth = e.value*1.0
-					}
-					if(parentLabel.innerText == 'Height'){
-						currentHeight = e.value*1.0
-					}
-				}
-			} 
+		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
+			}
 		})
 	}
 });

javascript/contextMenus.js

+
+contextMenuInit = function(){
+  let eventListenerApplied=false;
+  let menuSpecs = new Map();
+
+  const uid = function(){
+    return Date.now().toString(36) + Math.random().toString(36).substr(2);
+  }
+
+  function showContextMenu(event,element,menuEntries){
+    let posx = event.clientX + document.body.scrollLeft + document.documentElement.scrollLeft;
+    let posy = event.clientY + document.body.scrollTop + document.documentElement.scrollTop;
+
+    let oldMenu = gradioApp().querySelector('#context-menu')
+    if(oldMenu){
+      oldMenu.remove()
+    }
+
+    let tabButton = uiCurrentTab
+    let baseStyle = window.getComputedStyle(tabButton)
+
+    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 = posy+'px'
+    contextMenu.style.left = posx+'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(e) {
+        entry['func']();
+      })
+      contextMenuList.append(contextMenuEntry);
+
+    })
+
+    gradioApp().getRootNode().appendChild(contextMenu)
+
+    let menuWidth = contextMenu.offsetWidth + 4;
+    let menuHeight = contextMenu.offsetHeight + 4;
+
+    let windowWidth = window.innerWidth;
+    let windowHeight = window.innerHeight;
+
+    if ( (windowWidth - posx) < menuWidth ) {
+      contextMenu.style.left = windowWidth - menuWidth + "px";
+    }
+
+    if ( (windowHeight - posy) < menuHeight ) {
+      contextMenu.style.top = windowHeight - menuHeight + "px";
+    }
+
+  }
+
+  function appendContextMenuOption(targetElementSelector,entryName,entryFunction){
+
+    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,k) {
+      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) {
+      let source = e.composedPath()[0]
+      if(source.id && source.id.indexOf('check_progress')>-1){
+        return
+      }
+
+      let oldMenu = gradioApp().querySelector('#context-menu')
+      if(oldMenu){
+        oldMenu.remove()
+      }
+    });
+    gradioApp().addEventListener("contextmenu", function(e) {
+      let oldMenu = gradioApp().querySelector('#context-menu')
+      if(oldMenu){
+        oldMenu.remove()
+      }
+      menuSpecs.forEach(function(v,k) {
+        if(e.composedPath()[0].matches(k)){
+          showContextMenu(e,e.composedPath()[0],v)
+          e.preventDefault()
+          return
+        }
+      })
+    });
+    eventListenerApplied=true
+
+  }
+
+  return [appendContextMenuOption, removeContextMenuOption, addContextMenuEventListener]
+}
+
+initResponse = contextMenuInit();
+appendContextMenuOption     = initResponse[0];
+removeContextMenuOption     = initResponse[1];
+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)
+  }
+
+  appendContextMenuOption('#txt2img_generate','Generate forever',function(){
+    generateOnRepeat('#txt2img_generate','#txt2img_interrupt');
+  })
+  appendContextMenuOption('#img2img_generate','Generate forever',function(){
+    generateOnRepeat('#img2img_generate','#img2img_interrupt');
+  })
+
+  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)
+
+  appendContextMenuOption('#roll','Roll three',
+    function(){
+      let rollbutton = get_uiCurrentTabContent().querySelector('#roll');
+      setTimeout(function(){rollbutton.click()},100)
+      setTimeout(function(){rollbutton.click()},200)
+      setTimeout(function(){rollbutton.click()},300)
+    }
+  )
+})();
+//End example Context Menu Items
+
+onUiUpdate(function(){
+  addContextMenuEventListener()
+});

javascript/dragdrop.js

@@ -9,11 +9,19 @@ function dropReplaceImage( imgWrap, 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 ) {
-            fileInput.files = files;
+            if ( files.length === 0 ) {
+                files = new DataTransfer();
+                files.items.add(tmpFile);
+                fileInput.files = files.files;
+            } else {
+                fileInput.files = files;
+            }
             fileInput.dispatchEvent(new Event('change'));   
         }
     };
@@ -43,7 +51,7 @@ function dropReplaceImage( imgWrap, files ) {
 window.document.addEventListener('dragover', e => {
     const target = e.composedPath()[0];
     const imgWrap = target.closest('[data-testid="image"]');
-    if ( !imgWrap ) {
+    if ( !imgWrap && target.placeholder && target.placeholder.indexOf("Prompt") == -1) {
         return;
     }
     e.stopPropagation();
@@ -53,6 +61,9 @@ window.document.addEventListener('dragover', e => {
 
 window.document.addEventListener('drop', e => {
     const target = e.composedPath()[0];
+    if (target.placeholder.indexOf("Prompt") == -1) {
+        return;
+    }
     const imgWrap = target.closest('[data-testid="image"]');
     if ( !imgWrap ) {
         return;

javascript/imageMaskFix.js

@@ -31,8 +31,8 @@ function imageMaskResize() {
 
     wrapper.style.width = `${wW}px`;
     wrapper.style.height = `${wH}px`;
-    wrapper.style.left = `${(w-wW)/2}px`;
-    wrapper.style.top = `${(h-wH)/2}px`;
+    wrapper.style.left = `0px`;
+    wrapper.style.top = `0px`;
 
     canvases.forEach( c => {
         c.style.width = c.style.height = '';
@@ -42,4 +42,4 @@ function imageMaskResize() {
     });
  }
   
- onUiUpdate(() => imageMaskResize());
\ No newline at end of file
+ onUiUpdate(() => imageMaskResize());