Custom Models Auto (#75)

* Update auto

.editorconfig

@@ -0,0 +1,9 @@
+root = true
+
+[*]
+end_of_line = lf
+indent_style = space
+indent_size = 2
+charset = utf-8
+insert_final_newline = true
+trim_trailing_whitespace = true

.gitattributes

@@ -0,0 +1 @@
+* text=auto eol=lf

.github/ISSUE_TEMPLATE/bug.md

@@ -0,0 +1,36 @@
+---
+name: Bug
+about: Report a bug
+title: ''
+labels: bug
+assignees: ''
+
+---
+
+**Has this issue been opened before? Check the [FAQ](https://github.com/AbdBarho/stable-diffusion-webui-docker/wiki/Main), the [issues](https://github.com/AbdBarho/stable-diffusion-webui-docker/issues?q=is%3Aissue)**
+
+
+
+**Describe the bug**
+
+
+**Which UI**
+
+hlky or auto or auto-cpu or lstein?
+
+**Steps to Reproduce**
+1. Go to '...'
+2. Click on '....'
+3. Scroll down to '....'
+4. See error
+
+**Hardware / Software:**
+ - OS: [e.g. Windows / Ubuntu and version]
+ - RAM:
+ - GPU: [Nvidia 1660 / No GPU]
+ - VRAM:
+ - Docker Version, Docker compose version
+ - Release version [e.g. 1.0.1]
+
+**Additional context**
+Any other context about the problem here. If applicable, add screenshots to help explain your problem.

.github/workflows/docker.yml

@@ -0,0 +1,19 @@
+name: Build Images
+
+on: [push]
+
+jobs:
+  build:
+    strategy:
+      matrix:
+        profile:
+          - auto
+          - hlky
+          - lstein
+          - download
+    runs-on: ubuntu-latest
+    name: ${{ matrix.profile }}
+    steps:
+      - uses: actions/checkout@v3
+      # better caching?
+      - run: docker compose --profile ${{ matrix.profile }} build --progress plain

.github/workflows/executable.yml1

@@ -0,0 +1,22 @@
+name: Check executable
+
+on: [push]
+
+jobs:
+  check:
+    runs-on: ubuntu-latest
+    name: Check all sh
+    steps:
+      - run: git config --global core.fileMode true
+      - uses: actions/checkout@v3
+      - shell: bash
+        run: |
+          shopt -s globstar;
+          FAIL=0
+          for file in **/*.sh; do
+              if [ -f "${file}" ] && [ -r "${file}" ] && [ ! -x "${file}" ]; then
+                  echo "$file" is not executable;
+                  FAIL=1
+              fi
+          done
+          exit ${FAIL}

.github/workflows/stale.yml

@@ -0,0 +1,20 @@
+name: 'Close stale issues and PRs'
+on:
+  schedule:
+    - cron: '30 1 * * *'
+
+jobs:
+  stale:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/stale@v5
+        with:
+          only-labels: awaiting-response
+          stale-issue-message: This issue is stale because it has been open 14 days with no activity. Remove stale label or comment or this will be closed in 7 days.
+          stale-pr-message: This PR is stale because it has been open 14 days with no activity. Remove stale label or comment or this will be closed in 7 days.
+          close-issue-message: This issue was closed because it has been stalled for 7 days with no activity.
+          close-pr-message: This PR was closed because it has been stalled for 7 days with no activity.
+          days-before-issue-stale: 14
+          days-before-pr-stale: 14
+          days-before-issue-close: 7
+          days-before-pr-close: 7

README.md

@@ -1,62 +1,74 @@
-# Stable Diffusion WebUI Docker
+# Stable Diffusion WebUI Docker
 
 Run Stable Diffusion on your machine with a nice UI without any hassle!
 
-This repository provides the [WebUI](https://github.com/hlky/stable-diffusion-webui) as docker for easy setup and deployment. Please note that this repo delivers all cutting-edge unstable changes from the WebUI, so expect some bugs.
+This repository provides multiple UIs for you to play around with stable diffusion:
 
-## Setup
+## Features
 
-make sure you have docker installed and up to date. Download this repo and run:
+### AUTOMATIC1111
 
-```
+[AUTOMATIC1111's fork](https://github.com/AUTOMATIC1111/stable-diffusion-webui) is imho the most feature rich yet elegant UI:
-docker compose build
-```
 
-you can let it build in the background while you download the different models
+- Text to image, with many samplers and even negative prompts!
+- Image to image, with masking, cropping, in-painting, out-painting, variations.
+- GFPGAN, RealESRGAN, LDSR, CodeFormer.
+- Loopback, prompt weighting, prompt matrix, X/Y plot
+- Live preview of the generated images.
+- Highly optimized 4GB GPU support, or even CPU only!
+- [Full feature list here](https://github.com/AUTOMATIC1111/stable-diffusion-webui-feature-showcase)
 
-- [Stable Diffusion v1.4 (4GB)](https://www.googleapis.com/storage/v1/b/aai-blog-files/o/sd-v1-4.ckpt?alt=media), rename to `model.ckpt`
+| Text to image                                                                                              | Image to image                                                                                             | Extras                                                                                                     |
-- (Optional) [GFPGANv1.3.pth (333MB)](https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth) to improve generated faces.
+| ---------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------- |
-- (Optional) [RealESRGAN_x4plus.pth (64MB)](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth) and [RealESRGAN_x4plus_anime_6B.pth (18MB)](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth) for super-sampling.
+| ![](https://user-images.githubusercontent.com/24505302/189541954-46afd772-d0c8-4005-874c-e2eca40c02f2.jpg) | ![](https://user-images.githubusercontent.com/24505302/189541956-5b528de7-1b5d-479f-a1db-d3f5a53afc59.jpg) | ![](https://user-images.githubusercontent.com/24505302/189541957-cf78b352-a071-486d-8889-f26952779a61.jpg) |
 
-Put all of the downloaded files in the `models` folder, it should look something like this:
+### hlky
 
-```
+[hlky's fork](https://github.com/hlky/stable-diffusion-webui) is one of the most popular UIs, with many features:
-models/
-├── GFPGANv1.3.pth
-├── RealESRGAN_x4plus.pth
-├── RealESRGAN_x4plus_anime_6B.pth
-└── model.ckpt
-```
 
-## Run
+- Text to image, with many samplers
+- Image to image, with masking, cropping, in-painting, variations.
+- GFPGAN, RealESRGAN, LDSR, GoBig, GoLatent
+- Loopback, prompt weighting
+- 6GB or even 4GB GPU support!
+- [Full feature list here](https://github.com/sd-webui/stable-diffusion-webui/blob/master/README.md)
 
-After the build is done, you can run the app with:
+Screenshots:
 
-```
+| Text to image                                                                                              | Image to image                                                                                             | Image Lab                                                                                                  |
-docker compose up --build
+| ---------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------- |
-```
+| ![](https://user-images.githubusercontent.com/24505302/189541298-f902b021-a1eb-4e4b-b2eb-b6a696a8ec80.jpg) | ![](https://user-images.githubusercontent.com/24505302/189541295-7d7f2162-2189-4e0a-abbd-703f4779e1cd.jpg) | ![](https://user-images.githubusercontent.com/24505302/189541294-aa7f7735-a973-4e17-ada0-1fe3acbb1772.jpg) |
 
-Will start the app on http://localhost:7860/
+### lstein
 
-Note: the first start will take sometime as some other models will be downloaded, these will be cached in the `cache` folder, so next runs are faster.
+[lstein's fork](https://github.com/lstein/stable-diffusion) is very mature when it comes to the cli, and the WebUI has potential.
 
-## Config
+| Text to image                                                                                              | Image to image                                                                                             | Extras                                                                                                     |
+| ---------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------- |
+| ![](https://user-images.githubusercontent.com/24505302/190662506-dabdc967-93af-4d78-8533-394604d29ba4.jpg) | ![](https://user-images.githubusercontent.com/24505302/190662557-7640d9f0-30d8-4527-97b0-07d3f48108d4.jpg) | ![](https://user-images.githubusercontent.com/24505302/190662588-37a01fad-f993-4674-9ae6-8714aa229f7b.jpg) |
 
-in the `docker-compose.yml` you can change the `CLI_ARGS` variable contains all of the variables that will be passed to [the web ui](https://github.com/hlky/stable-diffusion/blob/fa977b3d6f9d0b264035c949fd70415476f00036/scripts/webui.py).
+## Setup & Usage
 
-By default: `--gfpgan-gpu 0 --esrgan-cpu --optimized-turbo` are given, which allow you to use this model on a 6GB GPU.
+Visit the wiki for [Setup](https://github.com/AbdBarho/stable-diffusion-webui-docker/wiki/Setup) and [Usage](https://github.com/AbdBarho/stable-diffusion-webui-docker/wiki/Usage) instructions, checkout the [FAQ](https://github.com/AbdBarho/stable-diffusion-webui-docker/wiki/FAQ) page if you face any problems, or create a new issue!
-NOTE: GFPGAN does not work on the CPU [More info here](https://github.com/AbdBarho/stable-diffusion-webui-docker/issues/4)
 
-# Disclaimer
+## Contributing
+
+Contributions are welcome! create an issue first of what you want to contribute (before you implement anything) so we can talk about it.
+
+## Disclaimer
 
 The authors of this project are not responsible for any content generated using this interface.
 
 This license of this software forbids you from sharing any content that violates any laws, produce any harm to a person, disseminate any personal information that would be meant for harm, spread misinformation and target vulnerable groups. For the full list of restrictions please read [the license](./LICENSE).
 
-# Thanks
+## Thanks
 
 Special thanks to everyone behind these awesome projects, without them, none of this would have been possible:
 
 - [hlky/stable-diffusion-webui](https://github.com/hlky/stable-diffusion-webui)
 - [AUTOMATIC1111/stable-diffusion-webui](https://github.com/AUTOMATIC1111/stable-diffusion-webui)
+- [lstein/stable-diffusion](https://github.com/lstein/stable-diffusion)
 - [CompVis/stable-diffusion](https://github.com/CompVis/stable-diffusion)
+- [hlky/sd-enable-textual-inversion](https://github.com/hlky/sd-enable-textual-inversion)
+- [devilismyfriend/latent-diffusion](https://github.com/devilismyfriend/latent-diffusion)
+- [Hafiidz/latent-diffusion](https://github.com/Hafiidz/latent-diffusion)

build/Dockerfile

@@ -1,57 +0,0 @@
-# syntax=docker/dockerfile:1
-
-FROM continuumio/miniconda3:4.12.0
-
-
-RUN conda install python=3.8.5 && conda clean -a -y
-RUN conda install pytorch==1.11.0 torchvision==0.12.0 cudatoolkit=11.3 -c pytorch && conda clean -a -y
-RUN git clone https://github.com/hlky/stable-diffusion.git && cd stable-diffusion && git reset --hard 554bd068e6f2f6bc55449a67fe017ddd77090f28
-RUN conda env update --file stable-diffusion/environment.yaml --name base && conda clean -a -y
-
-# fonts for generating the grid
-RUN apt-get update && apt install fonts-dejavu-core && apt-get clean
-
-# Note: don't update the sha of previous versions because the install will take forever
-# instead, update the repo state in a later step
-RUN cd stable-diffusion && git pull && git reset --hard fa977b3d6f9d0b264035c949fd70415476f00036 && \
-  conda env update --file environment.yaml --name base && conda clean -a -y
-
-# download dev UI version, update the sha below in case you want some other version
-# RUN <<EOF
-# git clone https://github.com/hlky/stable-diffusion-webui.git
-# cd stable-diffusion-webui
-# # map to this file: https://github.com/hlky/stable-diffusion-webui/blob/master/.github/sync.yml
-# git reset --hard 49e6178fd82ca736f9bbc621c6b12487c300e493
-# cp -t /stable-diffusion/scripts/ webui.py relauncher.py txt2img.yaml
-# cp -t /stable-diffusion/configs/webui webui.yaml
-# cp -t /stable-diffusion/frontend/ frontend/*
-# cd / && rm -rf stable-diffusion-webui
-# EOF
-
-# Textual-inversion:
-# RUN <<EOF
-# git clone https://github.com/hlky/sd-enable-textual-inversion.git
-# cp -rf sd-enable-textual-inversion /stable-diffusion
-# EOF
-
-# add info
-COPY info.py /info.py
-RUN  python /info.py /stable-diffusion/frontend/frontend.py
-
-WORKDIR /stable-diffusion
-ENV TRANSFORMERS_CACHE=/cache/transformers TORCH_HOME=/cache/torch CLI_ARGS="" \
-  GFPGAN_PATH=/stable-diffusion/src/gfpgan/experiments/pretrained_models/GFPGANv1.3.pth \
-  RealESRGAN_PATH=/stable-diffusion/src/realesrgan/experiments/pretrained_models/RealESRGAN_x4plus.pth \
-  RealESRGAN_ANIME_PATH=/stable-diffusion/src/realesrgan/experiments/pretrained_models/RealESRGAN_x4plus_anime_6B.pth
-EXPOSE 7860
-CMD \
-  for path in "${GFPGAN_PATH}" "${RealESRGAN_PATH}" "${RealESRGAN_ANIME_PATH}"; do \
-  name=$(basename "${path}"); \
-  base=$(dirname "${path}"); \
-  test -f "/models/${name}" && mkdir -p "${base}" && ln -sf "/models/${name}" "${path}" && echo "Mounted ${name}";\
-  done;\
-  # force facexlib cache
-  mkdir -p /cache/weights/ && rm -rf /stable-diffusion/src/facexlib/facexlib/weights && \
-  ln -sf  /cache/weights/ /stable-diffusion/src/facexlib/facexlib/ && \
-  # run, -u to not buffer stdout / stderr
-  python3 -u scripts/webui.py --outdir /output --ckpt /models/model.ckpt --save-metadata ${CLI_ARGS}

cache/.gitignore

@@ -1,3 +1,5 @@
 /torch
 /transformers
 /weights
+/models
+/custom-models

docker-compose.yml

@@ -1,17 +1,11 @@
 version: '3.9'
 
-services:
+x-base_service: &base_service
-  model:
-    build: ./build/
-    restart: on-failure
     ports:
       - "7860:7860"
     volumes:
-      - ./cache:/cache
+      - &v1 ./cache:/cache
-      - ./output:/output
+      - &v2 ./output:/output
-      - ./models:/models
-    environment:
-      - CLI_ARGS=--extra-models-cpu --optimized-turbo
     deploy:
       resources:
         reservations:
@@ -19,3 +13,45 @@ services:
               - driver: nvidia
                 device_ids: ['0']
                 capabilities: [gpu]
+
+name: webui-docker
+
+services:
+  download:
+    build: ./services/download/
+    profiles: ["download"]
+    volumes:
+      - *v1
+
+  hlky:
+    <<: *base_service
+    profiles: ["hlky"]
+    build: ./services/hlky/
+    environment:
+      - CLI_ARGS=--optimized-turbo
+
+  automatic1111: &automatic
+    <<: *base_service
+    profiles: ["auto"]
+    build: ./services/AUTOMATIC1111
+    volumes:
+      - *v1
+      - *v2
+      - ./services/AUTOMATIC1111/config.json:/stable-diffusion-webui/config.json
+    environment:
+      - CLI_ARGS=--medvram --opt-split-attention
+
+  automatic1111-cpu:
+    <<: *automatic
+    profiles: ["auto-cpu"]
+    deploy: {}
+    environment:
+      - CLI_ARGS=--no-half --precision full
+
+  lstein:
+    <<: *base_service
+    profiles: ["lstein"]
+    build: ./services/lstein/
+    environment:
+      - PRELOAD=false
+      - CLI_ARGS=

models/.gitignore

@@ -1,4 +0,0 @@
-/model.ckpt
-/GFPGANv1.3.pth
-/RealESRGAN_x4plus.pth
-/RealESRGAN_x4plus_anime_6B.pth

scripts/chmod.sh

@@ -0,0 +1,5 @@
+#!/bin/bash
+
+set -Eeuo pipefail
+
+find . -name "*.sh" -exec git update-index --chmod=+x {} \;

services/AUTOMATIC1111/Dockerfile

@@ -0,0 +1,65 @@
+# syntax=docker/dockerfile:1
+
+FROM alpine/git:2.36.2 as download
+RUN <<EOF
+# because taming-transformers is huge
+git config --global http.postBuffer 1048576000
+git clone https://github.com/sczhou/CodeFormer.git repositories/CodeFormer
+git clone https://github.com/CompVis/stable-diffusion.git repositories/stable-diffusion
+git clone https://github.com/salesforce/BLIP.git repositories/BLIP
+git clone https://github.com/CompVis/taming-transformers.git repositories/taming-transformers
+rm -rf repositories/taming-transformers/data repositories/taming-transformers/assets
+EOF
+
+
+FROM continuumio/miniconda3:4.12.0
+
+SHELL ["/bin/bash", "-ceuxo", "pipefail"]
+
+ENV DEBIAN_FRONTEND=noninteractive
+
+RUN conda install python=3.8.5 && conda clean -a -y
+RUN conda install pytorch==1.11.0 torchvision==0.12.0 cudatoolkit=11.3 -c pytorch && conda clean -a -y
+
+RUN apt-get update && apt install fonts-dejavu-core rsync -y && apt-get clean
+
+
+RUN <<EOF
+git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git
+cd stable-diffusion-webui
+git reset --hard 13eec4f3d4081fdc43883c5ef02e471a2b6c7212
+conda env update --file environment-wsl2.yaml -n base
+conda clean -a -y
+pip install --prefer-binary --no-cache-dir -r requirements.txt
+EOF
+
+ENV ROOT=/stable-diffusion-webui \
+  WORKDIR=/stable-diffusion-webui/repositories/stable-diffusion
+
+COPY --from=download /git/ ${ROOT}
+RUN pip install --prefer-binary --no-cache-dir -r ${ROOT}/repositories/CodeFormer/requirements.txt
+
+# Note: don't update the sha of previous versions because the install will take forever
+# instead, update the repo state in a later step
+
+ARG SHA=99585b3514e2d7e987651d5c6a0806f933af012b
+RUN <<EOF
+cd stable-diffusion-webui
+git pull --rebase
+git reset --hard ${SHA}
+pip install --prefer-binary --no-cache-dir -r requirements.txt
+EOF
+
+RUN pip install --prefer-binary -U --no-cache-dir opencv-python-headless
+
+ENV TRANSFORMERS_CACHE=/cache/transformers TORCH_HOME=/cache/torch CLI_ARGS=""
+
+COPY . /docker
+RUN chmod +x /docker/mount.sh && python3 /docker/info.py ${ROOT}/modules/ui.py
+
+
+WORKDIR ${WORKDIR}
+EXPOSE 7860
+# run, -u to not buffer stdout / stderr
+CMD /docker/mount.sh && \
+  python3 -u ../../webui.py --listen --port 7860 --hide-ui-dir-config --ckpt-dir /cache/custom-models --ckpt /cache/models/model.ckpt ${CLI_ARGS}

services/AUTOMATIC1111/config.json

@@ -0,0 +1,58 @@
+{
+  "outdir_samples": "/output",
+  "outdir_txt2img_samples": "/output/txt2img-images",
+  "outdir_img2img_samples": "/output/img2img-images",
+  "outdir_extras_samples": "/output/extras-images",
+  "outdir_txt2img_grids": "/output/txt2img-grids",
+  "outdir_img2img_grids": "/output/img2img-grids",
+  "outdir_save": "/output/saved",
+  "font": "DejaVuSans.ttf",
+  "__WARNING__": "DON'T CHANGE ANYTHING BEFORE THIS",
+
+  "samples_filename_format": "",
+  "outdir_grids": "",
+  "save_to_dirs": false,
+  "grid_save_to_dirs": false,
+  "save_to_dirs_prompt_len": 10,
+  "samples_save": true,
+  "samples_format": "png",
+  "grid_save": true,
+  "return_grid": true,
+  "grid_format": "png",
+  "grid_extended_filename": false,
+  "grid_only_if_multiple": true,
+  "n_rows": -1,
+  "jpeg_quality": 80,
+  "export_for_4chan": true,
+  "enable_pnginfo": true,
+  "add_model_hash_to_info": false,
+  "enable_emphasis": true,
+  "save_txt": false,
+  "ESRGAN_tile": 192,
+  "ESRGAN_tile_overlap": 8,
+  "random_artist_categories": [],
+  "upscale_at_full_resolution_padding": 16,
+  "show_progressbar": true,
+  "show_progress_every_n_steps": 7,
+  "multiple_tqdm": true,
+  "face_restoration_model": null,
+  "code_former_weight": 0.5,
+  "save_images_before_face_restoration": false,
+  "face_restoration_unload": false,
+  "interrogate_keep_models_in_memory": false,
+  "interrogate_use_builtin_artists": true,
+  "interrogate_clip_num_beams": 1,
+  "interrogate_clip_min_length": 24,
+  "interrogate_clip_max_length": 48,
+  "interrogate_clip_dict_limit": 1500.0,
+  "samples_filename_pattern": "",
+  "directories_filename_pattern": "",
+  "save_selected_only": false,
+  "filter_nsfw": false,
+  "img2img_color_correction": false,
+  "img2img_fix_steps": false,
+  "enable_quantization": false,
+  "enable_batch_seeds": true,
+  "memmon_poll_rate": 8,
+  "sd_model_checkpoint": null
+}

services/AUTOMATIC1111/info.py

@@ -0,0 +1,14 @@
+import sys
+from pathlib import Path
+
+file = Path(sys.argv[1])
+file.write_text(
+  file.read_text()\
+  .replace('    return demo', """
+    with demo:
+        gr.Markdown(
+          'Created by [AUTOMATIC1111 / stable-diffusion-webui-docker](https://github.com/AbdBarho/stable-diffusion-webui-docker/)'
+        )
+    return demo
+""", 1)
+)

services/AUTOMATIC1111/mount.sh

@@ -0,0 +1,35 @@
+#!/bin/bash
+
+set -e
+
+declare -A MODELS
+
+MODELS["${WORKDIR}/models/ldm/stable-diffusion-v1/model.ckpt"]=model.ckpt
+MODELS["${ROOT}/GFPGANv1.3.pth"]=GFPGANv1.3.pth
+
+MODELS_DIR=/cache/models
+
+for path in "${!MODELS[@]}"; do
+  name=${MODELS[$path]}
+  base=$(dirname "${path}")
+  from_path="${MODELS_DIR}/${name}"
+  if test -f "${from_path}"; then
+    mkdir -p "${base}" && ln -sf "${from_path}" "${path}" && echo "Mounted ${name}"
+  else
+    echo "Skipping ${name}"
+  fi
+done
+
+# force realesrgan cache
+rm -rf /opt/conda/lib/python3.8/site-packages/realesrgan/weights
+ln -s -T "${MODELS_DIR}" /opt/conda/lib/python3.8/site-packages/realesrgan/weights
+
+# force facexlib cache
+mkdir -p /cache/weights/ ${WORKDIR}/gfpgan/
+ln -sf /cache/weights/ ${WORKDIR}/gfpgan/
+# code former cache
+rm -rf ${ROOT}/repositories/CodeFormer/weights/CodeFormer ${ROOT}/repositories/CodeFormer/weights/facelib
+ln -sf -T /cache/weights ${ROOT}/repositories/CodeFormer/weights/CodeFormer
+ln -sf -T /cache/weights ${ROOT}/repositories/CodeFormer/weights/facelib
+
+mkdir -p /cache/torch /cache/transformers /cache/weights /cache/models /cache/custom-models

services/download/Dockerfile

@@ -0,0 +1,6 @@
+FROM bash:alpine3.15
+
+RUN apk add parallel aria2
+COPY . /docker
+RUN chmod +x /docker/download.sh
+ENTRYPOINT ["/docker/download.sh"]

services/download/checksums.sha256

@@ -0,0 +1,6 @@
+fe4efff1e174c627256e44ec2991ba279b3816e364b49f9be2abc0b3ff3f8556  /cache/models/model.ckpt
+c953a88f2727c85c3d9ae72e2bd4846bbaf59fe6972ad94130e23e7017524a70  /cache/models/GFPGANv1.3.pth
+4fa0d38905f75ac06eb49a7951b426670021be3018265fd191d2125df9d682f1  /cache/models/RealESRGAN_x4plus.pth
+f872d837d3c90ed2e05227bed711af5671a6fd1c9f7d7e91c911a61f155e99da  /cache/models/RealESRGAN_x4plus_anime_6B.pth
+c209caecac2f97b4bb8f4d726b70ac2ac9b35904b7fc99801e1f5e61f9210c13  /cache/models/LDSR.ckpt
+9d6ad53c5dafeb07200fb712db14b813b527edd262bc80ea136777bdb41be2ba  /cache/models/LDSR.yaml

services/download/download.sh

@@ -0,0 +1,13 @@
+#!/usr/bin/env bash
+
+set -Eeuo pipefail
+
+mkdir -p /cache/torch /cache/transformers /cache/weights /cache/models /cache/custom-models
+
+echo "Downloading, this might take a while..."
+
+aria2c --input-file /docker/links.txt --dir /cache/models --continue
+
+echo "Checking SHAs..."
+
+parallel --will-cite -a /docker/checksums.sha256 "echo -n {} | sha256sum -c"

services/download/links.txt

@@ -0,0 +1,12 @@
+https://www.googleapis.com/storage/v1/b/aai-blog-files/o/sd-v1-4.ckpt?alt=media
+  out=model.ckpt
+https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth
+  out=GFPGANv1.3.pth
+https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth
+  out=RealESRGAN_x4plus.pth
+https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth
+  out=RealESRGAN_x4plus_anime_6B.pth
+https://heibox.uni-heidelberg.de/f/31a76b13ea27482981b4/?dl=1
+  out=LDSR.yaml
+https://heibox.uni-heidelberg.de/f/578df07c8fc04ffbadf3/?dl=1
+  out=LDSR.ckpt

services/hlky/Dockerfile

@@ -0,0 +1,64 @@
+# syntax=docker/dockerfile:1
+
+FROM continuumio/miniconda3:4.12.0
+
+SHELL ["/bin/bash", "-ceuxo", "pipefail"]
+
+ENV DEBIAN_FRONTEND=noninteractive
+
+RUN conda install python=3.8.5 && conda clean -a -y
+RUN conda install pytorch==1.11.0 torchvision==0.12.0 cudatoolkit=11.3 -c pytorch && conda clean -a -y
+
+RUN apt-get update && apt install fonts-dejavu-core rsync gcc -y && apt-get clean
+
+
+RUN <<EOF
+git config --global http.postBuffer 1048576000
+git clone https://github.com/sd-webui/stable-diffusion-webui.git stable-diffusion
+cd stable-diffusion
+git reset --hard 7623a5734740025d79b710f3744bff9276e1467b
+conda env update --file environment.yaml -n base
+conda clean -a -y
+EOF
+
+# new dependency, should be added to the environment.yaml
+RUN pip install -U --no-cache-dir pyperclip
+
+# Note: don't update the sha of previous versions because the install will take forever
+# instead, update the repo state in a later step
+ARG BRANCH=master
+ARG SHA=833a91047df999302f699637768741cecee9c37b
+# ARG BRANCH=dev
+# ARG SHA=5f3d7facdea58fc4f89b8c584d22a4639615a2f8
+RUN <<EOF
+cd stable-diffusion
+git fetch
+git checkout ${BRANCH}
+git reset --hard ${SHA}
+conda env update --file environment.yaml -n base
+conda clean -a -y
+EOF
+
+# Latent diffusion
+RUN <<EOF
+git clone https://github.com/Hafiidz/latent-diffusion.git
+cd latent-diffusion
+git reset --hard e1a84a89fcbb49881546cf2acf1e7e250923dba0
+# hacks all the way down
+mv ldm ldm_latent &&
+sed -i -- 's/from ldm/from ldm_latent/g' *.py
+# dont forget to update the yaml!!
+EOF
+
+
+# add info
+COPY . /docker/
+RUN python /docker/info.py /stable-diffusion/frontend/frontend.py && chmod +x /docker/mount.sh
+
+WORKDIR /stable-diffusion
+ENV TRANSFORMERS_CACHE=/cache/transformers TORCH_HOME=/cache/torch CLI_ARGS=""
+EXPOSE 7860
+# run, -u to not buffer stdout / stderr
+CMD /docker/mount.sh && \
+  python3 -u scripts/webui.py --outdir /output --ckpt /cache/models/model.ckpt --ldsr-dir /latent-diffusion --inbrowser ${CLI_ARGS}
+# STREAMLIT_SERVER_PORT=7860 python -m streamlit run scripts/webui_streamlit.py

services/hlky/info.py

@@ -9,7 +9,5 @@ file.write_text(
     Created using <a href="https://github.com/AbdBarho/stable-diffusion-webui-docker">stable-diffusion-webui-docker</a>.
   </p>
   <p>For help and advanced usage guides,
-""", 1)\
+""", 1)
-  .replace('img2img_cfg = gr.Slider(minimum=1.0, maximum=30.0', 'img2img_cfg = gr.Slider(minimum=1.0, maximum=60.0')
-
 )

services/hlky/mount.sh

@@ -0,0 +1,38 @@
+#!/bin/bash
+
+set -e
+
+declare -A MODELS
+
+ROOT=/stable-diffusion/src
+
+MODELS["${ROOT}/gfpgan/experiments/pretrained_models/GFPGANv1.3.pth"]=GFPGANv1.3.pth
+MODELS["${ROOT}/realesrgan/experiments/pretrained_models/RealESRGAN_x4plus.pth"]=RealESRGAN_x4plus.pth
+MODELS["${ROOT}/realesrgan/experiments/pretrained_models/RealESRGAN_x4plus_anime_6B.pth"]=RealESRGAN_x4plus_anime_6B.pth
+MODELS["/latent-diffusion/experiments/pretrained_models/model.ckpt"]=LDSR.ckpt
+# MODELS["/latent-diffusion/experiments/pretrained_models/project.yaml"]=LDSR.yaml
+
+MODELS_DIR=/cache/models
+
+for path in "${!MODELS[@]}"; do
+  name=${MODELS[$path]}
+  base=$(dirname "${path}")
+  from_path="${MODELS_DIR}/${name}"
+  if test -f "${from_path}"; then
+    mkdir -p "${base}" && ln -sf "${from_path}" "${path}" && echo "Mounted ${name}"
+  else
+    echo "Skipping ${name}"
+  fi
+done
+
+# hack for latent-diffusion
+if test -f "${MODELS_DIR}/LDSR.yaml"; then
+  sed 's/ldm\./ldm_latent\./g' "${MODELS_DIR}/LDSR.yaml" >/latent-diffusion/experiments/pretrained_models/project.yaml
+fi
+
+# force facexlib cache
+mkdir -p /cache/weights/ /stable-diffusion/gfpgan/
+ln -sf /cache/weights/ /stable-diffusion/gfpgan/
+
+# streamlit config
+ln -sf /docker/webui_streamlit.yaml /stable-diffusion/configs/webui/webui_streamlit.yaml

services/hlky/webui_streamlit.yaml

@@ -0,0 +1,155 @@
+# UI defaults configuration file. It is automatically loaded if located at configs/webui/webui_streamlit.yaml.
+general:
+  gpu: 0
+  outdir: /outputs
+
+  default_model: "Stable Diffusion v1.4"
+  default_model_config: "configs/stable-diffusion/v1-inference.yaml"
+  default_model_path: "/cache/models/model.ckpt"
+  fp:
+    name:
+  GFPGAN_dir: "./src/gfpgan"
+  RealESRGAN_dir: "./src/realesrgan"
+  RealESRGAN_model: "RealESRGAN_x4plus"
+  outdir_txt2img: /outputs/txt2img-samples
+  outdir_img2img: /outputs/img2img-samples
+  gfpgan_cpu: False
+  esrgan_cpu: False
+  extra_models_cpu: False
+  extra_models_gpu: False
+  save_metadata: True
+  save_format: "png"
+  skip_grid: False
+  skip_save: False
+  grid_format: "jpg:95"
+  n_rows: -1
+  no_verify_input: False
+  no_half: False
+  use_float16: False
+  precision: "autocast"
+  optimized: False
+  optimized_turbo: True
+  optimized_config: "optimizedSD/v1-inference.yaml"
+  update_preview: True
+  update_preview_frequency: 5
+
+txt2img:
+  prompt:
+  height: 512
+  width: 512
+  cfg_scale: 7.5
+  seed: ""
+  batch_count: 1
+  batch_size: 1
+  sampling_steps: 30
+  default_sampler: "k_euler"
+  separate_prompts: False
+  update_preview: True
+  update_preview_frequency: 5
+  normalize_prompt_weights: True
+  save_individual_images: True
+  save_grid: True
+  group_by_prompt: True
+  save_as_jpg: False
+  use_GFPGAN: False
+  use_RealESRGAN: False
+  RealESRGAN_model: "RealESRGAN_x4plus"
+  variant_amount: 0.0
+  variant_seed: ""
+  write_info_files: True
+
+txt2vid:
+  default_model: "CompVis/stable-diffusion-v1-4"
+  custom_models_list:
+    [
+      "CompVis/stable-diffusion-v1-4",
+      "naclbit/trinart_stable_diffusion_v2",
+      "hakurei/waifu-diffusion",
+      "osanseviero/BigGAN-deep-128",
+    ]
+  prompt:
+  height: 512
+  width: 512
+  cfg_scale: 7.5
+  seed: ""
+  batch_count: 1
+  batch_size: 1
+  sampling_steps: 30
+  num_inference_steps: 200
+  default_sampler: "k_euler"
+  scheduler_name: "klms"
+  separate_prompts: False
+  update_preview: True
+  update_preview_frequency: 5
+  dynamic_preview_frequency: True
+  normalize_prompt_weights: True
+  save_individual_images: True
+  save_video: True
+  group_by_prompt: True
+  write_info_files: True
+  do_loop: False
+  save_as_jpg: False
+  use_GFPGAN: False
+  use_RealESRGAN: False
+  RealESRGAN_model: "RealESRGAN_x4plus"
+  variant_amount: 0.0
+  variant_seed: ""
+  beta_start: 0.00085
+  beta_end: 0.012
+  beta_scheduler_type: "linear"
+  max_frames: 1000
+
+img2img:
+  prompt:
+  sampling_steps: 30
+  # Adding an int to toggles enables the corresponding feature.
+  # 0: Create prompt matrix (separate multiple prompts using |, and get all combinations of them)
+  # 1: Normalize Prompt Weights (ensure sum of weights add up to 1.0)
+  # 2: Loopback (use images from previous batch when creating next batch)
+  # 3: Random loopback seed
+  # 4: Save individual images
+  # 5: Save grid
+  # 6: Sort samples by prompt
+  # 7: Write sample info files
+  # 8: jpg samples
+  # 9: Fix faces using GFPGAN
+  # 10: Upscale images using Real-ESRGAN
+  sampler_name: "k_euler"
+  denoising_strength: 0.45
+  # 0: Keep masked area
+  # 1: Regenerate only masked area
+  mask_mode: 0
+  mask_restore: False
+  # 0: Just resize
+  # 1: Crop and resize
+  # 2: Resize and fill
+  resize_mode: 0
+  # Leave blank for random seed:
+  seed: ""
+  ddim_eta: 0.0
+  cfg_scale: 7.5
+  batch_count: 1
+  batch_size: 1
+  height: 512
+  width: 512
+  # Textual inversion embeddings file path:
+  fp: ""
+  loopback: True
+  random_seed_loopback: True
+  separate_prompts: False
+  update_preview: True
+  update_preview_frequency: 5
+  normalize_prompt_weights: True
+  save_individual_images: True
+  save_grid: True
+  group_by_prompt: True
+  save_as_jpg: False
+  use_GFPGAN: False
+  use_RealESRGAN: False
+  RealESRGAN_model: "RealESRGAN_x4plus"
+  variant_amount: 0.0
+  variant_seed: ""
+  write_info_files: True
+
+gfpgan:
+  strength: 100

services/lstein/Dockerfile

@@ -0,0 +1,44 @@
+# syntax=docker/dockerfile:1
+
+FROM continuumio/miniconda3:4.12.0
+
+SHELL ["/bin/bash", "-ceuxo", "pipefail"]
+
+ENV DEBIAN_FRONTEND=noninteractive
+
+RUN conda install python=3.8.5 && conda clean -a -y
+RUN conda install pytorch==1.11.0 torchvision==0.12.0 cudatoolkit=11.3 -c pytorch && conda clean -a -y
+
+RUN apt-get update && apt install fonts-dejavu-core rsync gcc -y && apt-get clean
+
+
+RUN <<EOF
+git clone https://github.com/lstein/stable-diffusion.git
+cd stable-diffusion
+git reset --hard 751283a2de81bee4bb571fbabe4adb19f1d85b97
+conda env update --file environment.yaml -n base
+conda clean -a -y
+EOF
+
+
+ARG BRANCH=development SHA=45af30f3a4c98b50c755717831c5fff75a3a8b43
+# ARG BRANCH=main SHA=89da371f4841f7e05da5a1672459d700c3920784
+RUN <<EOF
+cd stable-diffusion
+git fetch
+git checkout ${BRANCH}
+git reset --hard ${SHA}
+conda env update --file environment.yaml -n base
+conda clean -a -y
+EOF
+
+RUN pip uninstall opencv-python -y && pip install --prefer-binary --upgrade --force-reinstall --no-cache-dir opencv-python-headless
+
+COPY . /docker/
+RUN python3 /docker/info.py /stable-diffusion/static/dream_web/index.html && chmod +x /docker/mount.sh
+
+ENV TRANSFORMERS_CACHE=/cache/transformers TORCH_HOME=/cache/torch PRELOAD=false CLI_ARGS=""
+WORKDIR /stable-diffusion
+EXPOSE 7860
+
+CMD /docker/mount.sh && python3 -u scripts/dream.py --outdir /output --web --host 0.0.0.0 --port 7860 ${CLI_ARGS}

services/lstein/info.py

@@ -0,0 +1,10 @@
+import sys
+from pathlib import Path
+
+file = Path(sys.argv[1])
+file.write_text(
+  file.read_text()\
+  .replace('GitHub site</a>', """
+  GitHub site</a>, Deployed with <a href="https://github.com/AbdBarho/stable-diffusion-webui-docker/">stable-diffusion-webui-docker</a>
+""", 1)
+)

services/lstein/mount.sh

@@ -0,0 +1,26 @@
+#!/bin/bash
+
+set -eu
+
+ROOT=/stable-diffusion
+
+mkdir -p "${ROOT}/models/ldm/stable-diffusion-v1/"
+ln -sf /cache/models/model.ckpt "${ROOT}/models/ldm/stable-diffusion-v1/model.ckpt"
+
+if test -f /cache/models/GFPGANv1.3.pth; then
+  base="${ROOT}/src/gfpgan/experiments/pretrained_models/"
+  mkdir -p "${base}"
+  ln -sf /cache/models/GFPGANv1.3.pth "${base}/GFPGANv1.3.pth"
+  echo "Mounted GFPGANv1.3.pth"
+fi
+
+# facexlib
+FACEX_WEIGHTS=/opt/conda/lib/python3.8/site-packages/facexlib/weights
+
+rm -rf "${FACEX_WEIGHTS}"
+mkdir -p /cache/weights
+ln -sf -T /cache/weights "${FACEX_WEIGHTS}"
+
+if "${PRELOAD}" == "true"; then
+  python3 -u scripts/preload_models.py
+fi