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 supported11 Subscribers
Add a CodeTriage badge to comfyui
Help out
- Issues
- DynamicVRAM on Windows: 'NoneType' object has no attribute 'is_floating_point' when loading CLIP Vision model
- something wrong when I run the model
- The specified pointer resides on host memory and is not registered with any CUDA device.
- LoRAs trained with AceStep Gradio Portable show weak effect in ComfyUI requiring excessive strength scaling (1.5–2.0)
- fix: CPU fallback for FP8 quantization on MPS (Apple Silicon)
- Use NORMAL_VRAM instead of SHARED for MPS memory management
- Please support new model "Qwen Image 2.0"
- ace step turbo shift3 and sft support
- Deleting loaded/imported images from the GUI
- Fix conditioning mask normalization for arbitrary spatial dimensions.
- Docs
- Python not yet supported