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
- [HIP] Speed up MiniMax H3 audio VAE
- Standart Sam 3 Body workflow does not work with the sam_3d_body_dinov3_bf16.safetensors model
- Qwen2.1 doesn't utilize or offload to RAM
- Fix stale Qwen3-VL generation cache state
- Dynamic VRAM: a ModelSamplingDiscrete schedule leaks into later runs of the same checkpoint (buffers restored by attribute path), giving wrong or black images reported as success
- Prevent conditioning fill from indexing empty regional destinations
- Drain the device before unpinning prefix-cache host memory
- Fix dynamic VRAM buffer restore leaking a sampling schedule between models
- Fix: Allow SaveConditioning and ConditioningLoader to handle nested dictionary/list tensors (MiniMax H3 / DiT keyframes)
- [DO NOT MERGE] Assets: integration branch for #16358 + #16393
- Docs
- Python not yet supported