v6.0

It’s been a long time since the last release, and many major events have taken place in the AIGC field. This project itself has also undergone significant updates — it’s time to mark a new milestone.

Added Image Tags

• cpu
• cu126-slim
• cu128-slim
• cu130-slim
• cu126-megapak
• cu128-megapak
• xpu
• xpu-cn

Retired Image Tags

• cu118-slim
• cu118-megapak
  • Retired with PyTorch 2.7.1
• cu121
• cu121-megapak
  • Retired with PyTorch 2.5.1
• cu124-cn
• cu124-slim
• cu124-megapak
  • Retired with PyTorch 2.6.0
• cu128-test
• cu129-slim
• cu129-test
• cu129-megapak
  • Retired with PyTorch 2.8.0
• comfy3d-pt22
• comfy3d-pt23
• comfy3d-pt25
• direct3ds2

Planned Image Tags

• cu130-megapak
  • Planned to use Python 3.14t (free-threading, no GIL). Waiting for the ecosystem.
  • Python 3.14t not feasible, rollback to Python 3.13 (with GIL).
• cu128-cn
• rocm-cn

Features for New Image Tags

• Speed up startup time. First starts no longer download anything from the Internet.

  • Now a ComfyUI bundle is preloaded in the image for copy on-demand.
  • No longer download "out-of-box" SD models. It's not necessary now.

• Mount model files and user files separately.

• Speed up image pulling by breaking down the steps in Dockerfile to have more smaller image layers.

• All changes are backward-compatible.

Minor Changes

• Dropped mediapipe in all images. Ref: google-ai-edge/mediapipe#5810

• Full Changelog: v5.0...v6.0

Thanks

• Thanks @nhtua for #67 (critical ROCm env vars)

• Thanks @seasuu for #101 (fix libgl for Ubuntu, now replaced by Fedora)

• Thanks @DarthGibblet for #110 (NVIDIA cusparselt newly introduced in PyTorch)

• Thanks @SergeyFilippov for #114 (update rocm to 6.4.2)

• Thanks for the information in issues #79 #81 #85 #87 #90 #107 #124 #126 #128 #130 #131

v5.0

We have come a long way since the last release, and now is a good time to mark a milestone.

Major changes

• Aliased latest as cu121.
• Aliased megapak as cu121-megapak.
• Added cu124-megapak, using CUDA 12.4.
• Added cu124-cn for users in mainland China.
• Added nightly, using preview version of PyTorch
• Added comfy3d-pt22, dedicated for 3D-Pack.
• Added comfy3d-pt23, dedicated for 3D-Pack.
• Removed support for Comfy3D in other images.

Minor changes

• Images on Docker Hub are now tagged with date.
• cu121, cu121-megapak, and cu124-cn now use stable version of ComfyUI (with a release tag on GitHub).
• Updated download lists, concise for cu121, comprehensive for megapaks.
• Added sponsor link (Ko-fi).
• More

Thanks

Thanks @bashtoni for committing 9f1c4ed
Thanks for the information in issues #36 #37 #38 #41 #42 #55 #56

v4.0

Major changes

• Added new image megapak for dev and all-in-one usage.
• Overhauled rocm with AMD official PyTorch packages.

Minor changes

• Added support for ComfyUI-3D-Pack.
• Added wrapper script for rootless delploy.
• Added x264 & x265 codec for ffmpeg.
• Fixed "missing CUDA provider" for ONNX Runtime.
• Pycache (.pyc files) will be saved in .cache folder (easy for cleaning).
• User script set-proxy.sh will run before downloading starts.
• Shrink download list.
• More

Thanks

Thanks @M1kep for committing 3471e8d, b8c9d87, 2d75635
Thanks @petemyron for committing 0d27a97
Thanks @chadly for committing 3448bdd
Thanks for information #15 #16 #20 #26

Quick start

• using docker run:

mkdir -p storage

docker run -it --rm \
  --name comfyui \
  --gpus all \
  -p 8188:8188 \
  -v "$(pwd)"/storage:/home/runner \
  -e CLI_ARGS="" \
  yanwk/comfyui-boot:latest

v3.1

• Add back xFormers for compatibility on some Linux hosts.
  • To skip xFormers, add --use-pytorch-cross-attention to CLI_ARGS.

Quick start using docker run:

mkdir -p storage

docker run -it \
  --name comfyui \
  --gpus all \
  -p 8188:8188 \
  -v "$(pwd)"/storage:/home/runner \
  -e CLI_ARGS="" \
  yanwk/comfyui-boot:latest

v3.0

• Removed xFormers as PyTorch now performs good enough.

Quick start using docker run:

mkdir -p storage

docker run -it \
  --name comfyui \
  --gpus all \
  -p 8188:8188 \
  -v "$(pwd)"/storage:/home/runner \
  --env CLI_ARGS="" \
  yanwk/comfyui-boot:latest

v2.0

Quick start using docker run:

mkdir -p storage

docker run -it \
  --name comfyui \
  --gpus all \
  -p 8188:8188 \
  -v "$(pwd)"/storage:/home/runner \
  --env CLI_ARGS="" \
  yanwk/comfyui-boot:latest

v1.0

Quick start using docker run:

mkdir -p storage

docker run -it \
  --name comfyui \
  --gpus all \
  -p 8188:8188 \
  -v "$(pwd)"/storage:/home/runner \
  --env CLI_ARGS="" \
  yanwk/comfyui-boot:latest