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
- Fix character_mask row placement in WanAnimateToVideo
- Add VIDEO support to Resize Image/Mask
- feat(yue2): 18x throughput speedup & VRAM residency fix on entry-level GPUs (RTX 3050 4GB)
- MiniMax H3: artifacts when enable Larryvrh lora with Model Sparse Attention (sol-attn) ; disabling it restores normal video
- The lip-sync feature for digital human MV in MiniMax H3 cannot be used in version 0.35 and later releases.
- Minimax H3 VAE encode issue on xpu on ComfyUI v0.36.0
- Support text generation for qwen3vl_32b_minimax_03_int8_comvrot, so that it can be used to generate hints for h3 using official skills
- Support MiniMax H3 Keyless in Model Sparse Attention
- Fail closed on generic LoRA loading for MiniMax H3 Keyless
- Please support Qwen Image 2.1 day0
- Docs
- Python not yet supported