Update Dockerfiles and docker-compose for ROCm support and version upgrades

Refactor Dockerfile and docker-compose for ROCm support and improved build context
Refactor docker-compose.yml for improved service configuration and organization

docker-compose.yml

@@ -1,18 +1,57 @@
-x-base_service: &base_service
+# Base configurations
-    ports:
+x-common: &common
-      - "${WEBUI_PORT:-7860}:7860"
+  ports:
-    volumes:
+    - "${WEBUI_PORT:-7860}:7860"
-      - &v1 ./data:/data
+  volumes:
-      - &v2 ./output:/output
+    - &v1 ./data:/data
-    stop_signal: SIGKILL
+    - &v2 ./output:/output
-    tty: true
+  stop_signal: SIGKILL
-    deploy:
+  tty: true
-      resources:
+
-        reservations:
+# Device configurations
-          devices:
+x-cuda: &cuda
-              - driver: nvidia
+  deploy:
-                device_ids: ['0']
+    resources:
-                capabilities: [compute, utility]
+      reservations:
+        devices:
+          - driver: nvidia
+            device_ids: ['0']
+            capabilities: [compute, utility]
+
+x-rocm: &rocm
+  devices:
+    - /dev/kfd
+    - /dev/dri
+  security_opt:
+    - seccomp=unconfined
+  group_add:
+    - video
+  deploy:
+    # resources:
+      reservations:
+        devices:
+          - driver: amd
+            capabilities: [gpu]
+  environment:
+    - ROCm_VERSION=6.4
+    - HIP_VISIBLE_DEVICES=0
+    - HSA_OVERRIDE_GFX_VERSION=11.0.0
+
+x-cpu: &cpu
+  deploy: {}
+
+# CLI arguments
+x-auto-args: &auto_args
+  CLI_ARGS: --allow-code --medvram --xformers --enable-insecure-extension-access --api
+
+x-auto-cpu-args: &auto_cpu_args
+  CLI_ARGS: --no-half --precision full --allow-code --enable-insecure-extension-access --api
+
+x-comfy-args: &comfy_args
+  CLI_ARGS: ""
+
+x-comfy-cpu-args: &comfy_cpu_args
+  CLI_ARGS: --cpu
 
 name: webui-docker
 
@@ -23,33 +62,46 @@ services:
     volumes:
       - *v1
 
-  auto: &automatic
+  # AUTOMATIC1111 services
-    <<: *base_service
+  auto-cuda:
-    profiles: ["auto"]
+    <<: [*common, *cuda]
+    profiles: ["auto-cuda"]
     build: ./services/AUTOMATIC1111
-    image: sd-auto:78
+    image: sd-auto:79
     environment:
-      - CLI_ARGS=--allow-code --medvram --xformers --enable-insecure-extension-access --api
+      <<: *auto_args
+
+  auto-rocm:
+    <<: [*common, *rocm]
+    profiles: ["auto-rocm"]
+    build:
+      context: ./services/AUTOMATIC1111
+      dockerfile: Dockerfile-rocm
+    image: sd-auto-rocm:79
+    environment:
+      <<: *auto_args
 
   auto-cpu:
-    <<: *automatic
+    <<: [*common, *cpu]
     profiles: ["auto-cpu"]
-    deploy: {}
+    build: ./services/AUTOMATIC1111
+    image: sd-auto-cpu:79
     environment:
-      - CLI_ARGS=--no-half --precision full --allow-code --enable-insecure-extension-access --api
+      <<: *auto_cpu_args
 
-  comfy: &comfy
+  # ComfyUI services
-    <<: *base_service
+  comfy-cuda:
-    profiles: ["comfy"]
+    <<: [*common, *cuda]
+    profiles: ["comfy-cuda"]
     build: ./services/comfy/
     image: sd-comfy:7
     environment:
-      - CLI_ARGS=
+      <<: *comfy_args
-
 
   comfy-cpu:
-    <<: *comfy
+    <<: [*common, *cpu]
     profiles: ["comfy-cpu"]
-    deploy: {}
+    build: ./services/comfy/
+    image: sd-comfy-cpu:7
     environment:
-      - CLI_ARGS=--cpu
+      <<: *comfy_cpu_args

services/AUTOMATIC1111/Dockerfile

@@ -1,4 +1,4 @@
-FROM alpine/git:2.36.2 as download
+FROM alpine/git:2.49.1 AS download
 
 COPY clone.sh /clone.sh
 
@@ -14,7 +14,7 @@ RUN . /clone.sh generative-models https://github.com/Stability-AI/generative-mod
 RUN . /clone.sh stable-diffusion-webui-assets https://github.com/AUTOMATIC1111/stable-diffusion-webui-assets 6f7db241d2f8ba7457bac5ca9753331f0c266917
 
 
-FROM pytorch/pytorch:2.3.0-cuda12.1-cudnn8-runtime
+FROM pytorch/pytorch:2.5.1-cuda12.1-cudnn9-runtime
 
 ENV DEBIAN_FRONTEND=noninteractive PIP_PREFER_BINARY=1
 
@@ -30,7 +30,7 @@ WORKDIR /
 RUN --mount=type=cache,target=/root/.cache/pip \
   git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git && \
   cd stable-diffusion-webui && \
-  git reset --hard v1.9.4 && \
+  git reset --hard v1.10.1 && \
   pip install -r requirements_versions.txt
 
 
@@ -55,8 +55,8 @@ COPY . /docker
 RUN \
   # mv ${ROOT}/style.css ${ROOT}/user.css && \
   # one of the ugliest hacks I ever wrote \
-  sed -i 's/in_app_dir = .*/in_app_dir = True/g' /opt/conda/lib/python3.10/site-packages/gradio/routes.py && \
+  find /opt -name "routes.py" -path "*/gradio/*" -exec sed -i 's/in_app_dir = .*/in_app_dir = True/g' {} \; 2>/dev/null || true && \
-  git config --global --add safe.directory '*'
+  git config --global --add safe.directory '*' || true
 
 WORKDIR ${ROOT}
 ENV NVIDIA_VISIBLE_DEVICES=all

services/AUTOMATIC1111/Dockerfile-rocm

@@ -0,0 +1,79 @@
+FROM alpine/git:2.49.1 AS download
+
+COPY clone.sh /clone.sh
+
+RUN . /clone.sh stable-diffusion-webui-assets https://github.com/AUTOMATIC1111/stable-diffusion-webui-assets.git 6f7db241d2f8ba7457bac5ca9753331f0c266917
+
+RUN . /clone.sh stable-diffusion-stability-ai https://github.com/Stability-AI/stablediffusion.git cf1d67a6fd5ea1aa600c4df58e5b47da45f6bdbf \
+  && rm -rf assets data/**/*.png data/**/*.jpg data/**/*.gif
+
+RUN . /clone.sh BLIP https://github.com/salesforce/BLIP.git 48211a1594f1321b00f14c9f7a5b4813144b2fb9
+RUN . /clone.sh k-diffusion https://github.com/crowsonkb/k-diffusion.git ab527a9a6d347f364e3d185ba6d714e22d80cb3c
+RUN . /clone.sh clip-interrogator https://github.com/pharmapsychotic/clip-interrogator 2cf03aaf6e704197fd0dae7c7f96aa59cf1b11c9
+RUN . /clone.sh generative-models https://github.com/Stability-AI/generative-models 45c443b316737a4ab6e40413d7794a7f5657c19f
+RUN . /clone.sh stable-diffusion-webui-assets https://github.com/AUTOMATIC1111/stable-diffusion-webui-assets 6f7db241d2f8ba7457bac5ca9753331f0c266917
+
+
+FROM rocm/pytorch:rocm6.4.3_ubuntu24.04_py3.12_pytorch_release_2.6.0
+
+ENV DEBIAN_FRONTEND=noninteractive PIP_PREFER_BINARY=1
+
+RUN --mount=type=cache,target=/var/cache/apt \
+  apt-get update && \
+  # 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 build-essential libssl-dev \
+  # build-from-source toolchain for py3.12-only wheels like tokenizers (curl for rustup)
+  rustc cargo curl ca-certificates && \
+  update-ca-certificates
+
+# Install a recent Rust toolchain (Cargo/rustc) that supports edition2024 crates needed by tokenizers deps
+RUN curl -sSf https://sh.rustup.rs | sh -s -- -y \
+  && /root/.cargo/bin/rustup toolchain install stable \
+  && /root/.cargo/bin/rustup default stable \
+  && /root/.cargo/bin/rustc --version \
+  && /root/.cargo/bin/cargo --version
+
+ENV PATH=/root/.cargo/bin:${PATH}
+ENV RUSTFLAGS="-A invalid_reference_casting"
+
+
+WORKDIR /
+RUN --mount=type=cache,target=/root/.cache/pip \
+  git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git && \
+  cd stable-diffusion-webui && \
+  git reset --hard v1.10.1 && \
+  python -m pip install --upgrade pip setuptools wheel && \
+  pip install -r requirements_versions.txt
+
+
+ENV ROOT=/stable-diffusion-webui
+
+COPY --from=download /repositories/ ${ROOT}/repositories/
+RUN mkdir ${ROOT}/interrogate && cp ${ROOT}/repositories/clip-interrogator/clip_interrogator/data/* ${ROOT}/interrogate
+
+RUN --mount=type=cache,target=/root/.cache/pip \
+  pip install pyngrok xformers==0.0.26.post1 \
+  git+https://github.com/TencentARC/GFPGAN.git@8d2447a2d918f8eba5a4a01463fd48e45126a379 \
+  git+https://github.com/openai/CLIP.git@d50d76daa670286dd6cacf3bcd80b5e4823fc8e1 \
+  git+https://github.com/mlfoundations/open_clip.git@v2.20.0
+
+# there seems to be a memory leak (or maybe just memory not being freed fast enough) that is fixed by this version of malloc
+# maybe move this up to the dependencies list.
+RUN apt-get -y install libgoogle-perftools-dev && apt-get clean
+ENV LD_PRELOAD=libtcmalloc.so
+
+COPY . /docker
+
+RUN \
+  # mv ${ROOT}/style.css ${ROOT}/user.css && \
+  # one of the ugliest hacks I ever wrote \
+  find /opt -name "routes.py" -path "*/gradio/*" -exec sed -i 's/in_app_dir = .*/in_app_dir = True/g' {} \; 2>/dev/null || true && \
+  git config --global --add safe.directory '*' || true
+
+WORKDIR ${ROOT}
+ENV CLI_ARGS=""
+EXPOSE 7860
+ENTRYPOINT ["/docker/entrypoint.sh"]
+CMD python -u webui.py --listen --port 7860 ${CLI_ARGS}

services/download/Dockerfile

@@ -1,4 +1,4 @@
-FROM bash:alpine3.19
+FROM bash:alpine3.22
 
 RUN apk update && apk add parallel aria2
 COPY . /docker