comfyui
https://github.com/comfyanonymous/comfyui
Python
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported24 Subscribers
Add a CodeTriage badge to comfyui
Help out
- Issues
- [AMD ROCm] hipErrorInvalidValue in SDPA when running Anima models (gfx1201, torch 2.13.0+rocm10.0.0)
- Add device option to triple and quadruple clip loaders
- chore: bound standard approval with core team CODEOWNERS exceptions
- SaveVideo H.264 re-encode fails with avcodec_open2 EINVAL when width or height is odd
- Fix SaveVideo H.264 failure on odd width or height
- Fix uni_pc corrector coefficients losing precision in float32
- Fix 403 on top-level navigation from another site
- No se encuentra nodo
- Fix washed-out TAEHV previews for models with normalized latents (lighttaew2_1)
- Qwen3-VL vision tower runs in float32, so NVFP4-quantized vision layers crash: 'Unsupported dtype code (only FP16/BF16 supported): 0'
- Docs
- Python not yet supported