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
- CLIPVisionEncode VRAM usage grows linearly with frame count — long videos silently spill into shared memory
- testing
- SAM3_Detect ignores the presence score, so prompts for absent objects mask whatever is in the image
- Fix bounding box scaling with linked dimensions
- WanVAE: adopt comfy_has_chunked_io to remove whole-video VRAM residency (encode input / decode output)
- comfy_kitchen bug: infer_schema(func): Parameter stride has unsupported type list[int]
- Fix PoseBranchCache.select() crashing on tensor compare
- Fix portable startup when the asset database is in use
- Fix SAM3 detection scores for absent text prompts
- Docs: two Linux/AMD traps that stop ComfyUI before a model loads (segfault, missing torchaudio wheel)
- Docs
- Python not yet supported