README.adoc

Docker Image for ComfyUI-3D-Pack

View on <Docker Hub>

Note	Currently Not Working on WSL2.

• By default, only install ComfyUI, ComfyUI-3D-Pack, and any custom nodes required by example workflows.

• ComfyUI-Manager will be installed but disabled by default.

• After the download is complete, the script will attempt to rebuild dependencies for the 3D-Pack.

  • This process could take about 10 minutes.

  • If the rebuild is unnecessary (some workflows such as TripoSR can run directly), add an empty file named .build-complete to the storage folder (similar to the .download-complete file).

  • The build process will auto target local GPU, usually no need to config. If having issues, try set env var TORCH_CUDA_ARCH_LIST (see the table below).

Version Info

• ComfyUI-3D-Pack version: latest

• Dev kits:

  • CUDA dev kit (12.4)

  • Python dev package (3.12)

  • GCC C++ (13)

• Key Components:

  • torch==2.5.1+cu124

  • xformers==0.0.29.post1

Additionally, compiled wheel files for Comfy3D can be found here and instructions for compiling can be found here.

Usage

Run with Docker

mkdir -p storage

docker run -it --rm \
  --name comfy3d-pt25 \
  --gpus all \
  -p 8188:8188 \
  -v "$(pwd)"/storage:/root \
  -e CLI_ARGS="" \
  yanwk/comfyui-boot:comfy3d-pt25

Run with Podman

mkdir -p storage

podman run -it --rm \
  --name comfy3d-pt25 \
  --device nvidia.com/gpu=all \
  --security-opt label=disable \
  -p 8188:8188 \
  -v "$(pwd)"/storage:/root \
  -e CLI_ARGS="" \
  docker.io/yanwk/comfyui-boot:comfy3d-pt25

Environment Variables Reference

Variable	Example Value	Memo
HTTP_PROXY HTTPS_PROXY	http://localhost:1081 http://localhost:1081	Set HTTP proxy.
PIP_INDEX_URL	'https://pypi.org/simple'	Set mirror site for Python Package Index.
HF_ENDPOINT	'https://huggingface.co'	Set mirror site for HuggingFace Hub.
HF_TOKEN	'hf_your_token'	Set HuggingFace Access Token. More
HF_HUB_ENABLE_HF_TRANSFER	1	Enable HuggingFace Hub experimental high-speed file transfers. Only make sense if you have >1000Mbps and VERY STABLE connection (e.g. cloud server). More
TORCH_CUDA_ARCH_LIST	7.5 or '5.2+PTX;6.0;6.1+PTX;7.5;8.0;8.6;8.9+PTX'	Build target for PyTorch and its extensions. For most users, you only need to set one build target for your GPU. More
CMAKE_ARGS	(Default) '-DBUILD_opencv_world=ON -DWITH_CUDA=ON -DCUDA_FAST_MATH=ON -DWITH_CUBLAS=ON -DWITH_NVCUVID=ON'	Build options for CMAKE for projects using CUDA.

Additional: Running the TRELLIS Demo Using This Image

TRELLIS officially provides a Gradio demo that can generate orbit videos and .glb models from images. This Docker image has almost all the necessary dependencies, so you can easily run the demo. The execution script is provided below.

• Note: Requires more than 16G VRAM.

• ATTN_BACKEND options

  • flash-attn is suitable for Ampere architecture (30 series/A100) and later GPUs.

  • xformers has better compatibility.

• SPCONV_ALGO options

  • native starts faster and is suitable for single runs.

  • auto has better performance, but will take some time for benchmarking at the beginning.

1. Run the Container

mkdir -p storage

podman run -it \
  --name trellis-demo \
  --device nvidia.com/gpu=all \
  --security-opt label=disable \
  -p 7860:7860 \
  -v "$(pwd)"/storage:/root \
  -e ATTN_BACKEND="flash-attn" \
  -e SPCONV_ALGO="native" \
  -e GRADIO_SERVER_NAME="0.0.0.0" \
  -e PIP_USER=true \
  -e PIP_ROOT_USER_ACTION=ignore \
  -e PYTHONPYCACHEPREFIX="/root/.cache/pycache" \
  docker.io/yanwk/comfyui-boot:comfy3d-pt25 \
  /bin/fish

2. Run the Commands

export PATH="$PATH:/root/.local/bin"

# Run the compilation script, takes about 10 minutes.
bash /runner-scripts/build-deps-trellis-demo.sh

# Download the model
huggingface-cli download JeffreyXiang/TRELLIS-image-large

# Download and run TRELLIS demo
git clone --depth=1 --recurse-submodules \
  https://github.com/microsoft/TRELLIS.git \
  /root/TRELLIS

cd /root/TRELLIS

python3 app.py

Note	You may safely ignore the message matrix-client 0.4.0 requires urllib3~=1.21, but you have urllib3 2.2.3 which is incompatible. As matrix-client is used by ComfyUI-Manager, it is not relevant in this context.