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
- [WeightAdapter, bug fix] Fix the qkv separation handling in Bypass mode in weight adapter system
- Fix Blend Images failing on unequal batch sizes
- feat: classify execution failures in a machine-readable way
- Fix wrong results from large GEMMs on ROCm
- --enable-manager on a non-loopback listener exposes an unauthenticated management API (remote node install / config write / restart); Manager 4.3 relaxes the install gate
- Add PLZ "Pixaroma" Node_pack to "cloud.comfy.org"
- Pinned-memory steal race comes back under torch.compile with Dynamic VRAM (copies on the compute stream aren't covered by #17297)
- YuE2 / MiniMax Music 3 int8 text encoders crash on MPS with aten::_int_mm (missing disabled quant formats)
- Cropping a tensor-backed HDR video resets its color space to sRGB
- JoyAI-Image-Edit: text encoder fails for every input (mat1 52x4096 vs mat2 1024x4096)
- Docs
- Python not yet supported