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
- Fix PerpNegGuider returning an all-NaN image when positive equals empty_conditioning
- Fix CFGNorm silently producing an all-NaN image for large strength
- Add Phonon-2 / Parakeet TDT speech to text
- fix(assets): keep SQLite temp storage in memory
- SAM3.1: SAM3 Detect node not detecting faces properly with a prompt "face:10" and threshold==0.1
- Dynamic VRAM: "VBAR allocation failed" on NVIDIA vGPU (CUDA VMM not available), `--disable-dynamic-vram` is the only workaround
- RemeshMesh not supported for torch.int64
- KarrasScheduler silently returns NaN sigmas for small rho, producing an all-NaN image with no error
- ExponentialScheduler and PolyexponentialScheduler accept sigma_min/sigma_max = 0, which their own maths cannot compute
- network problem
- Docs
- Python not yet supported