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
- Use dynamic activation scaling in legacy fast FP8 linear
- Get Video Components: hold the decoded frames once, not twice
- no
- SeedVR2: CUDA illegal memory access (MMU NACK) above a total video size on RTX 5090, reproducible, process can hang
- video_metadata.py: fps can report stream time_base rate instead of the real frame rate (variable-frame-rate / SPS-timed videos)
- Connected node replacements fail after renaming a consumer input
- Add a prompt state cache for Qwen3.5 TextGenerate
- [Partner Nodes] chore(Grok): remove retired image models from Grok Image node and update prices
- backend crash when using the new idol workflow
- Read free XPU memory from the device
- Docs
- Python not yet supported