The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
Go to file
2025-12-26 15:36:44 -08:00
.github pylint tweak 2025-12-09 23:56:47 -08:00
comfy tests pass 2025-12-26 15:20:45 -08:00
comfy_api Merge branch 'master' of github.com:comfyanonymous/ComfyUI 2025-12-26 14:36:35 -08:00
comfy_api_nodes Merge branch 'master' of github.com:comfyanonymous/ComfyUI 2025-12-26 14:36:35 -08:00
comfy_compatibility Improvements to compatibility with custom nodes, distributed 2025-11-04 17:40:19 -08:00
comfy_config fix pylint issues 2025-07-14 17:44:43 -07:00
comfy_execution Merge branch 'master' of github.com:comfyanonymous/ComfyUI 2025-12-26 14:36:35 -08:00
comfy_extras tests pass 2025-12-26 15:20:45 -08:00
custom_nodes Merge commit 'a4787ac83bf6c83eeb459ed80fc9b36f63d2a3a7' of github.com:comfyanonymous/ComfyUI into fix-merge 2025-10-21 10:53:43 -07:00
docs tidy up README 2025-12-26 15:36:44 -08:00
input LoadLatent and SaveLatent should behave like the LoadImage and SaveImage. 2023-05-18 00:09:12 -04:00
models Merge branch 'master' of github.com:comfyanonymous/ComfyUI into merge/0.3.76-snapshot 2025-12-09 08:58:52 -08:00
output Initial commit. 2023-01-16 22:37:14 -05:00
pkg Fix distributed previews, add sageattention to the docker container 2025-09-12 11:48:25 -07:00
pypi sageattention fixup 2025-12-11 17:21:44 -08:00
tests tests pass 2025-12-26 15:20:45 -08:00
.dockerignore Fix distributed previews, add sageattention to the docker container 2025-09-12 11:48:25 -07:00
.editorconfig Improvements to node loading, node API, folder paths and progress 2024-03-13 16:14:18 -07:00
.gitattributes Merge branch 'master' of github.com:comfyanonymous/ComfyUI 2025-08-07 13:23:38 -07:00
.gitignore Further improvements to logic nodes, lazy evaluation and related 2025-10-31 16:14:08 -07:00
amd.Dockerfile ROCm support 2025-09-24 14:40:28 -07:00
CODEOWNERS Merge branch 'master' of github.com:comfyanonymous/ComfyUI into merge/0.3.76-snapshot 2025-12-09 08:58:52 -08:00
CONTRIBUTING.md Add CONTRIBUTING.md (#3910) 2024-07-01 13:51:00 -04:00
docker-compose.yml Update compose file to use tagged image 2025-09-12 12:08:46 -07:00
Dockerfile wip eval nodes, test tracing with full integration test, fix dockerfile barfing on flash_attn 2.8.3 2025-11-07 16:50:55 -08:00
LICENSE Initial commit. 2023-01-16 22:37:14 -05:00
main.py Set OCL_SET_SVM_SIZE on AMD. (#11139) 2025-12-06 00:15:21 -05:00
mypy.ini merge upstream 2023-10-17 14:47:59 -07:00
pyproject.toml Merge branch 'master' of github.com:comfyanonymous/ComfyUI 2025-12-26 14:36:35 -08:00
pytest.ini Merge branch 'execution_model_inversion' of github.com:guill/ComfyUI into pr-execution 2024-07-19 17:49:41 -07:00
QUANTIZATION.md Quantized Ops fixes (#10715) 2025-11-12 18:26:52 -05:00
README.md tidy up README 2025-12-26 15:36:44 -08:00
SPONSORS.md sponsor information 2025-07-18 09:04:29 -07:00

ComfyUI LTS

A vanilla, up-to-date fork of ComfyUI intended for long term support (LTS) from AppMana and Hidden Switch.

Quickstart (Linux)

UI Users

For users who want to run ComfyUI for generating images and videos.

  1. Install uv:

    curl -LsSf https://astral.sh/uv/install.sh | sh
    
  2. Create a Workspace:

    mkdir comfyui-workspace
    cd comfyui-workspace
    
  3. Install and Run:

    # Create a virtual environment
    uv venv --python 3.12
    
    # Install ComfyUI LTS
    uv pip install --torch-backend=auto "comfyui@git+https://github.com/hiddenswitch/ComfyUI.git"
    
    # Run
    uv run comfyui
    

Developers

For developers contributing to the codebase or building on top of it.

  1. Clone the Repository:

    git clone https://github.com/hiddenswitch/ComfyUI.git
    cd ComfyUI
    
  2. Setup Environment:

    # Create virtual environment
    uv venv --python 3.12
    source .venv/bin/activate
    
    # Install in editable mode with dev dependencies
    uv pip install -e .[dev]
    
  3. Run:

    uv run comfyui
    

Documentation

Full documentation is available in docs/index.md.

Table of Contents