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 supported21 Subscribers
Add a CodeTriage badge to comfyui
Help out
- Issues
- Merge (concatenate) Videos blueprint use Concatenate Audio Instead of Merge Audio
- Fix/aimdo windows pin budget
- Fail closed prompt cache signatures for opaque, unstable, and recursive inputs
- After exiting a Subgraph, the exited subgraph should be visibly highlighted
- [Feature Request] Native [Ctrl] + [F] search shortcut within workflows (Prompts, LoRA models, etc.)
- Extract and Save Lora is broken
- uni_pc sampler diverges for Wan2.2-TI2V-5B on MPS when cfg > 1 and video length exceeds ~5 latent frames
- LoadImageDataSetFromFolder loads images in os.listdir order (filesystem-dependent), scrambling frame sequences
- MiniMax H3 VAE: replace temporal F.pad(constant) with torch.cat — fixes silent encode corruption on MPS
- Z-Image Turbo bf16: non-finite output on warm rerun on ROCm gfx1201 (RX 9070 XT), cold run valid
- Docs
- Python not yet supported