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 /free ignoring an explicit "unload_models": false
- Fix live weight casts being overwritten during async offload
- Fix VRAM reporting, mmap loading and cuDNN on backends that lack them
- Re-enable the --enable-assets tests in CI
- [Fix] ROCm / AMD Navi 31: Fix GPU Page Faults, LoRA Hook Leaks & Glibc RAM Bloat
- MiniMax H3-Base: warn or validate when an accepted graph exceeds the documented native canvas
- MiniMax H3 Ref2VA: major reference-fidelity regression in local ComfyUI despite same workflow/model files
- SeedVR2 (native core nodes): periodic near-frozen frames, exactly every 4 frames, in video upscaling
- TAE previews for Wan 2.1-latent models (lighttaew2_1) are decoded from normalized latents, so they look washed out
- Resume a paused asset scan as soon as the prompt queue is idle
- Docs
- Python not yet supported