Update Automatic1111 to 1.5.1 to add compatibility for SDXL (#560)

Uses the latest release of
https://github.com/Stability-AI/generative-models
45c443b316737a4ab6e40413d7794a7f5657c19f

Tested with the official SDXL 1.0 model from
https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/sd_xl_base_1.0.safetensors
and official refiner from
https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0/blob/main/sd_xl_refiner_1.0.safetensors.
VAE:
https://huggingface.co/stabilityai/sdxl-vae/blob/main/sdxl_vae.safetensors

Closes #558
Closes #559

68f336bd99

---------

Co-authored-by: AbdBarho <ka70911@gmail.com>

.devscripts/migratev7tov8.sh

@@ -0,0 +1,28 @@
+#!/bin/bash
+
+set -Eeuo pipefail
+
+echo "Renaming..."
+
+# compatible with default auto-names
+mv -v ./data/StableDiffusion ./data/Stable-diffusion
+mv -v ./data/Deepdanbooru ./data/torch_deepdanbooru
+
+# casing problem on windows
+mv -v ./data/Hypernetworks ./data/hypernetworks1
+mv -v ./data/hypernetworks1 ./data/hypernetworks
+
+mv -v ./data/MiDaS ./data/midas1
+mv -v ./data/midas1 ./data/midas
+
+
+echo "Moving folders..."
+
+mkdir -pv ./final
+
+mv -v ./data/config ./final/config
+mv -v ./data/.cache ./final/.cache
+mv -v ./data/embeddings ./final/embeddings
+mv -v ./data ./final/models
+
+mv -v ./final ./data

data/.gitignore

@@ -1,28 +1,4 @@
-# for all of the stuff downloaded by transformers, pytorch, and others
 /.cache
-# for UIs
 /config
-# for all stable diffusion models (main, waifu diffusion, etc..)
-/StableDiffusion
-# others
-/Codeformer
-/GFPGAN
-/ESRGAN
-/BSRGAN
-/RealESRGAN
-/SwinIR
-/MiDaS
-/BLIP
-/ScuNET
-/LDSR
-/Deepdanbooru
-/Hypernetworks
-/VAE
 /embeddings
-/Lora
+/models
-/ControlNet
-/openpose
-/ModelScope
-/LyCORIS
-/GLIGEN
-/CLIPEncoder

docker-compose.yml

@@ -2,11 +2,12 @@ version: '3.9'
 
 x-base_service: &base_service
     ports:
-      - "7860:7860"
+      - "${WEBUI_PORT:-7860}:7860"
     volumes:
       - &v1 ./data:/data
       - &v2 ./output:/output
-    stop_signal: SIGINT
+    stop_signal: SIGKILL
+    tty: true
     deploy:
       resources:
         reservations:
@@ -28,7 +29,7 @@ services:
     <<: *base_service
     profiles: ["auto"]
     build: ./services/AUTOMATIC1111
-    image: sd-auto:58
+    image: sd-auto:63
     environment:
       - CLI_ARGS=--allow-code --medvram --xformers --enable-insecure-extension-access --api
 
@@ -43,7 +44,7 @@ services:
     <<: *base_service
     profiles: ["invoke"]
     build: ./services/invoke/
-    image: sd-invoke:29
+    image: sd-invoke:30
     environment:
       - PRELOAD=true
       - CLI_ARGS=--xformers
@@ -59,8 +60,7 @@ services:
     <<: *base_service
     profiles: ["comfy"]
     build: ./services/comfy/
-    image: sd-comfy:2
+    image: sd-comfy:4
-    tty: true
     environment:
       - CLI_ARGS=
 

services/AUTOMATIC1111/Dockerfile

@@ -12,8 +12,9 @@ RUN . /clone.sh CodeFormer https://github.com/sczhou/CodeFormer.git c5b4593074ba
   && rm -rf assets inputs
 
 RUN . /clone.sh BLIP https://github.com/salesforce/BLIP.git 48211a1594f1321b00f14c9f7a5b4813144b2fb9
-RUN . /clone.sh k-diffusion https://github.com/crowsonkb/k-diffusion.git 5b3af030dd83e0297272d861c19477735d0317ec
+RUN . /clone.sh k-diffusion https://github.com/crowsonkb/k-diffusion.git c9fe758757e022f05ca5a53fa8fac28889e4f1cf
 RUN . /clone.sh clip-interrogator https://github.com/pharmapsychotic/clip-interrogator 2486589f24165c8e3b303f84e9dbbea318df83e8
+RUN . /clone.sh generative-models https://github.com/Stability-AI/generative-models 45c443b316737a4ab6e40413d7794a7f5657c19f
 
 
 FROM alpine:3.17 as xformers
@@ -30,7 +31,7 @@ RUN --mount=type=cache,target=/var/cache/apt \
   # we need those
   apt-get install -y fonts-dejavu-core rsync git jq moreutils aria2 \
   # extensions needs those
-  ffmpeg libglfw3-dev libgles2-mesa-dev pkg-config libcairo2 libcairo2-dev
+  ffmpeg libglfw3-dev libgles2-mesa-dev pkg-config libcairo2 libcairo2-dev build-essential
 
 
 RUN --mount=type=cache,target=/cache --mount=type=cache,target=/root/.cache/pip \
@@ -71,7 +72,7 @@ RUN --mount=type=cache,target=/root/.cache/pip \
 RUN apt-get -y install libgoogle-perftools-dev && apt-get clean
 ENV LD_PRELOAD=libtcmalloc.so
 
-ARG SHA=20ae71faa8ef035c31aa3a410b707d792c8203a3
+ARG SHA=68f336bd994bed5442ad95bad6b6ad5564a5409a
 RUN --mount=type=cache,target=/root/.cache/pip \
   cd stable-diffusion-webui && \
   git fetch && \

services/AUTOMATIC1111/entrypoint.sh

@@ -19,30 +19,16 @@ if [ ! -f /data/config/auto/styles.csv ]; then
   touch /data/config/auto/styles.csv
 fi
 
+# copy models from original models folder
+mkdir -p /data/models/VAE-approx/ /data/models/karlo/
+
+rsync -a --info=NAME ${ROOT}/models/VAE-approx/ /data/models/VAE-approx/
+rsync -a --info=NAME ${ROOT}/models/karlo/ /data/models/karlo/
+
 declare -A MOUNTS
 
 MOUNTS["/root/.cache"]="/data/.cache"
-
+MOUNTS["${ROOT}/models"]="/data/models"
-# main
-MOUNTS["${ROOT}/models/Stable-diffusion"]="/data/StableDiffusion"
-MOUNTS["${ROOT}/models/VAE"]="/data/VAE"
-MOUNTS["${ROOT}/models/Codeformer"]="/data/Codeformer"
-MOUNTS["${ROOT}/models/GFPGAN"]="/data/GFPGAN"
-MOUNTS["${ROOT}/models/ESRGAN"]="/data/ESRGAN"
-MOUNTS["${ROOT}/models/BSRGAN"]="/data/BSRGAN"
-MOUNTS["${ROOT}/models/RealESRGAN"]="/data/RealESRGAN"
-MOUNTS["${ROOT}/models/SwinIR"]="/data/SwinIR"
-MOUNTS["${ROOT}/models/ScuNET"]="/data/ScuNET"
-MOUNTS["${ROOT}/models/LDSR"]="/data/LDSR"
-MOUNTS["${ROOT}/models/hypernetworks"]="/data/Hypernetworks"
-MOUNTS["${ROOT}/models/torch_deepdanbooru"]="/data/Deepdanbooru"
-MOUNTS["${ROOT}/models/BLIP"]="/data/BLIP"
-MOUNTS["${ROOT}/models/midas"]="/data/MiDaS"
-MOUNTS["${ROOT}/models/Lora"]="/data/Lora"
-MOUNTS["${ROOT}/models/LyCORIS"]="/data/LyCORIS"
-MOUNTS["${ROOT}/models/ControlNet"]="/data/ControlNet"
-MOUNTS["${ROOT}/models/openpose"]="/data/openpose"
-MOUNTS["${ROOT}/models/ModelScope"]="/data/ModelScope"
 
 MOUNTS["${ROOT}/embeddings"]="/data/embeddings"
 MOUNTS["${ROOT}/config.json"]="/data/config/auto/config.json"
@@ -66,8 +52,22 @@ for to_path in "${!MOUNTS[@]}"; do
   echo Mounted $(basename "${from_path}")
 done
 
+echo "Installing extension dependencies (if any)"
+
+# because we build our container as root:
+chown -R root ~/.cache/
+chmod 766 ~/.cache/
+
+shopt -s nullglob
+# For install.py, please refer to https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Developing-extensions#installpy
+list=(./extensions/*/install.py)
+for installscript in "${list[@]}"; do
+  PYTHONPATH=${ROOT} python "$installscript"
+done
+
 if [ -f "/data/config/auto/startup.sh" ]; then
   pushd ${ROOT}
+  echo "Running startup script"
   . /data/config/auto/startup.sh
   popd
 fi

services/comfy/Dockerfile

@@ -1,14 +1,11 @@
 FROM alpine:3.17 as xformers
 RUN apk add --no-cache aria2
-RUN aria2c -x 5 --dir / --out wheel.whl 'https://github.com/AbdBarho/stable-diffusion-webui-docker/releases/download/5.0.0/xformers-0.0.17.dev449-cp310-cp310-manylinux2014_x86_64.whl'
+RUN aria2c -x 5 --dir / --out wheel.whl 'https://github.com/AbdBarho/stable-diffusion-webui-docker/releases/download/6.0.0/xformers-0.0.21.dev544-cp310-cp310-manylinux2014_x86_64-pytorch201.whl'
 
-
+FROM pytorch/pytorch:2.0.1-cuda11.7-cudnn8-runtime
-FROM python:3.10.9-slim
 
 ENV DEBIAN_FRONTEND=noninteractive PIP_PREFER_BINARY=1
 
-RUN --mount=type=cache,target=/root/.cache/pip pip install torch==1.13.1 torchvision --extra-index-url https://download.pytorch.org/whl/cu117
-
 RUN apt-get update && apt-get install -y git && apt-get clean
 
 ENV ROOT=/stable-diffusion
@@ -21,13 +18,13 @@ RUN --mount=type=cache,target=/root/.cache/pip \
 
 
 RUN --mount=type=cache,target=/root/.cache/pip  \
-  --mount=type=bind,from=xformers,source=/wheel.whl,target=/xformers-0.0.17-cp310-cp310-linux_x86_64.whl \
+  --mount=type=bind,from=xformers,source=/wheel.whl,target=/xformers-0.0.21-cp310-cp310-linux_x86_64.whl \
-  pip install triton /xformers-0.0.17-cp310-cp310-linux_x86_64.whl
+  pip install /xformers-0.0.21-cp310-cp310-linux_x86_64.whl
 
 
 WORKDIR ${ROOT}
 
-ARG BRANCH=master SHA=884ea653c8d6fe19b3724f45a04a0d74cd881f2f
+ARG BRANCH=master SHA=8607c2d42d10b0108de02528e813cc703e58813f
 RUN --mount=type=cache,target=/root/.cache/pip \
   git fetch && \
   git checkout ${BRANCH} && \
@@ -37,6 +34,8 @@ RUN --mount=type=cache,target=/root/.cache/pip \
 # add info
 COPY . /docker/
 RUN cp /docker/extra_model_paths.yaml ${ROOT}
+RUN chmod u+x /docker/entrypoint.sh
+RUN cp /docker/extra_model_paths.yaml ${ROOT}
 
 ENV NVIDIA_VISIBLE_DEVICES=all
 ENV PYTHONPATH="${PYTHONPATH}:${PWD}" CLI_ARGS=""

services/comfy/entrypoint.sh

@@ -22,4 +22,10 @@ for to_path in "${!MOUNTS[@]}"; do
   echo Mounted $(basename "${from_path}")
 done
 
+if [ -f "/data/config/comfy/startup.sh" ]; then
+  pushd ${ROOT}
+  . /data/config/comfy/startup.sh
+  popd
+fi
+
 exec "$@"

services/comfy/extra_model_paths.yaml

@@ -1,20 +1,20 @@
 a111:
   base_path: /data
 
-  checkpoints: StableDiffusion
+  checkpoints: models/Stable-diffusion
-  configs: StableDiffusion
+  configs: models/Stable-diffusion
-  vae: VAE
+  vae: models/VAE
-  loras: Lora
+  loras: models/Lora
   upscale_models: |
-    RealESRGAN
+    models/RealESRGAN
-    ESRGAN
+    models/ESRGAN
-    SwinIR
+    models/SwinIR
-    GFPGAN
+    models/GFPGAN
+  hypernetworks: models/hypernetworks
+  controlnet: models/ControlNet
+  gligen: models/GLIGEN
+  clip: models/CLIPEncoder
   embeddings: embeddings
-  hypernetworks: Hypernetworks
-  controlnet: ControlNet
-  gligen: GLIGEN
-  clip: CLIPEncoder
 
   custom_nodes: config/comfy/custom_nodes
 

services/download/checksums.sha256

@@ -1,8 +1,8 @@
-cc6cb27103417325ff94f52b7a5d2dde45a7515b25c255d8e396c90014281516  /data/StableDiffusion/v1-5-pruned-emaonly.ckpt
+cc6cb27103417325ff94f52b7a5d2dde45a7515b25c255d8e396c90014281516  /data/models/Stable-diffusion/v1-5-pruned-emaonly.ckpt
-c6bbc15e3224e6973459ba78de4998b80b50112b0ae5b5c67113d56b4e366b19  /data/StableDiffusion/sd-v1-5-inpainting.ckpt
+c6bbc15e3224e6973459ba78de4998b80b50112b0ae5b5c67113d56b4e366b19  /data/models/Stable-diffusion/sd-v1-5-inpainting.ckpt
-c6a580b13a5bc05a5e16e4dbb80608ff2ec251a162311590c1f34c013d7f3dab  /data/VAE/vae-ft-mse-840000-ema-pruned.ckpt
+c6a580b13a5bc05a5e16e4dbb80608ff2ec251a162311590c1f34c013d7f3dab  /data/models/VAE/vae-ft-mse-840000-ema-pruned.ckpt
-e2cd4703ab14f4d01fd1383a8a8b266f9a5833dacee8e6a79d3bf21a1b6be5ad  /data/GFPGAN/GFPGANv1.4.pth
+e2cd4703ab14f4d01fd1383a8a8b266f9a5833dacee8e6a79d3bf21a1b6be5ad  /data/models/GFPGAN/GFPGANv1.4.pth
-4fa0d38905f75ac06eb49a7951b426670021be3018265fd191d2125df9d682f1  /data/RealESRGAN/RealESRGAN_x4plus.pth
+4fa0d38905f75ac06eb49a7951b426670021be3018265fd191d2125df9d682f1  /data/models/RealESRGAN/RealESRGAN_x4plus.pth
-f872d837d3c90ed2e05227bed711af5671a6fd1c9f7d7e91c911a61f155e99da  /data/RealESRGAN/RealESRGAN_x4plus_anime_6B.pth
+f872d837d3c90ed2e05227bed711af5671a6fd1c9f7d7e91c911a61f155e99da  /data/models/RealESRGAN/RealESRGAN_x4plus_anime_6B.pth
-c209caecac2f97b4bb8f4d726b70ac2ac9b35904b7fc99801e1f5e61f9210c13  /data/LDSR/model.ckpt
+c209caecac2f97b4bb8f4d726b70ac2ac9b35904b7fc99801e1f5e61f9210c13  /data/models/LDSR/model.ckpt
-9d6ad53c5dafeb07200fb712db14b813b527edd262bc80ea136777bdb41be2ba  /data/LDSR/project.yaml
+9d6ad53c5dafeb07200fb712db14b813b527edd262bc80ea136777bdb41be2ba  /data/models/LDSR/project.yaml

services/download/download.sh

@@ -4,30 +4,18 @@ set -Eeuo pipefail
 
 # TODO: maybe just use the .gitignore file to create all of these
 mkdir -vp /data/.cache \
-  /data/StableDiffusion \
-  /data/LyCORIS \
-  /data/Codeformer \
-  /data/ModelScope \
-  /data/GFPGAN \
-  /data/ESRGAN \
-  /data/BSRGAN \
-  /data/RealESRGAN \
-  /data/SwinIR \
-  /data/LDSR \
-  /data/ScuNET \
   /data/embeddings \
-  /data/VAE \
+  /data/config/ \
-  /data/Deepdanbooru \
+  /data/models/ \
-  /data/MiDaS \
+  /data/models/Stable-diffusion \
-  /data/Lora \
+  /data/models/GFPGAN \
-  /data/ControlNet \
+  /data/models/RealESRGAN \
-  /data/openpose \
+  /data/models/LDSR \
-  /data/GLIGEN \
+  /data/models/VAE
-  /data/CLIPEncoder # this is different from the cached pre-train ViT saved in /data/.cache/clip TODO: find out how
 
 echo "Downloading, this might take a while..."
 
-aria2c -x 10 --disable-ipv6 --input-file /docker/links.txt --dir /data --continue
+aria2c -x 10 --disable-ipv6 --input-file /docker/links.txt --dir /data/models --continue
 
 echo "Checking SHAs..."
 
@@ -39,11 +27,5 @@ https://github.com/AbdBarho/stable-diffusion-webui-docker/blob/master/LICENSE
 https://github.com/CompVis/stable-diffusion/blob/main/LICENSE
 https://github.com/AUTOMATIC1111/stable-diffusion-webui/blob/master/LICENSE.txt
 https://github.com/invoke-ai/InvokeAI/blob/main/LICENSE
-https://github.com/sd-webui/stable-diffusion-webui/blob/master/LICENSE
+And licenses of all UIs, third party libraries, and extensions.
-https://github.com/cszn/BSRGAN/blob/main/LICENSE
-https://github.com/sczhou/CodeFormer/blob/master/LICENSE
-https://github.com/TencentARC/GFPGAN/blob/master/LICENSE
-https://github.com/xinntao/Real-ESRGAN/blob/master/LICENSE
-https://github.com/xinntao/ESRGAN/blob/master/LICENSE
-https://github.com/cszn/SCUNet/blob/main/LICENSE
 EOF

services/download/links.txt

@@ -1,9 +1,9 @@
 https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.ckpt
-  out=StableDiffusion/v1-5-pruned-emaonly.ckpt
+  out=Stable-diffusion/v1-5-pruned-emaonly.ckpt
 https://huggingface.co/stabilityai/sd-vae-ft-mse-original/resolve/main/vae-ft-mse-840000-ema-pruned.ckpt
   out=VAE/vae-ft-mse-840000-ema-pruned.ckpt
 https://huggingface.co/runwayml/stable-diffusion-inpainting/resolve/main/sd-v1-5-inpainting.ckpt
-  out=StableDiffusion/sd-v1-5-inpainting.ckpt
+  out=Stable-diffusion/sd-v1-5-inpainting.ckpt
 https://github.com/TencentARC/GFPGAN/releases/download/v1.3.4/GFPGANv1.4.pth
   out=GFPGAN/GFPGANv1.4.pth
 https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth

services/invoke/Dockerfile

@@ -48,6 +48,6 @@ EXPOSE 7860
 
 ENTRYPOINT ["/docker/entrypoint.sh"]
 CMD invokeai --web --host 0.0.0.0 --port 7860 --root_dir ${ROOT} --config ${CONFIG_DIR}/models.yaml \
-  --outdir /output/invoke --embedding_directory /data/embeddings/ --lora_directory /data/Lora \
+  --outdir /output/invoke --embedding_directory /data/embeddings/ --lora_directory /data/models/Lora \
   --no-nsfw_checker --no-safety_checker ${CLI_ARGS}
 

services/invoke/entrypoint.sh

@@ -13,10 +13,10 @@ MOUNTS["/root/.cache"]=/data/.cache/
 rm -rf ${HF_HOME}/diffusers
 
 # ui specific
-MOUNTS["${ROOT}/models/codeformer"]=/data/Codeformer/
+MOUNTS["${ROOT}/models/codeformer"]=/data/models/Codeformer/
-MOUNTS["${ROOT}/models/gfpgan/GFPGANv1.4.pth"]=/data/GFPGAN/GFPGANv1.4.pth
+MOUNTS["${ROOT}/models/gfpgan/GFPGANv1.4.pth"]=/data/models/GFPGAN/GFPGANv1.4.pth
-MOUNTS["${ROOT}/models/gfpgan/weights"]=/data/GFPGAN/
+MOUNTS["${ROOT}/models/gfpgan/weights"]=/data/models/GFPGAN/
-MOUNTS["${ROOT}/models/realesrgan"]=/data/RealESRGAN/
+MOUNTS["${ROOT}/models/realesrgan"]=/data/models/RealESRGAN/
 
 MOUNTS["${ROOT}/models/ldm"]=/data/.cache/invoke/ldm/