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 supported11 Subscribers
Add a CodeTriage badge to comfyui
Help out
- Issues
- Fix LatentInterpolate corrupting batched latents
- Fix overlap-linear context window crash when context_overlap is 0
- seedvr int8 always load from disk
- How to disable Sage attention ?!
- force LowVramPatch for quantized patched weights
- feat: add torchao INT4 weight-only quantization backend to comfy/quantization/
- QWEN EDIT 2511 AIO model image generation fails to work properly after version 0.22.
- flux fill onereward int8-convrot generated Artifact during inpaint
- Fix silent output corruption on MPS for large attention matrices
- Native INT8 ConvRot significantly slower than FP8 on A100 (Torch 2.10 + cu130)
- Docs
- Python not yet supported