>?中文说明点我?<
This repo is for Docker images that runs ComfyUI - a Stable Diffusion GUI powering node-based workflow.
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:cu121
cu121
, latest
Recommended for anyone trying ComfyUI for the first time.
Equipped with many dependencies. Starts with ComfyUI core only.
Using a low-privilege user within the container (easy for WSL2 deploy).
Not recommended for Podman or rootless deploy (use megapak
instead).
Using CUDA 12.1 + Python 3.11.
cu121-megapak
, megapak
All-in-one bundle, including dev kits.
Using 'root' user within the container (easy for rootless deploy).
Using CUDA 12.1 + Python 3.11.
cu124-megapak
All-in-one bundle, including dev kits.
Using 'root' user within the container (easy for rootless deploy).
Using CUDA 12.4 + Python 3.12. May perform better on newer GPUs.
cu124-cn
For users in mainland China. Using mirror sites for all download links.
rocm
For AMD GPUs with ROCm.
nightly
Using preview version of PyTorch.
Images dedicated for ComfyUI-3D-Pack:
comfy3d-pt22
Running the
Jun 23, 2024
version of Comfy3D based on PyTorch 2.2.
comfy3d-pt23
Running the
Oct 18, 2024
version of Comfy3D based on PyTorch 2.3.
comfy3d-pt25
Running the latest version of Comfy3D based on PyTorch 2.5.
Mulan Public License,Version 2
This open source license is written and valid both in Chinese and English, how good is that!