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 supported0 Subscribers
Add a CodeTriage badge to comfyui
Help out
- Issues
- ComfyUI-Impact-Pack (V8.8.1) [WARN] ComfyUI-Impact-Pack: custom_wildcards path not found: C:\_a\comfyui-aki-v1.6\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\custom_wildcards. Using default path.
- More built-in data types: vector, matrix, color, image (with ColorSpace)
- Error while processing rearrange-reduction pattern "B (T S) N C -> (B S) N T C". Input tensor shape: torch.Size([1, 34320, 40, 128]). Additional info: {'T': 21, 'S': 1634, 'N': 40, 'C': 128}. Shape mismatch, 34320 != 34314
- After upgrading to the latest Comfyui, as long as you use the internal compensation model condition node (check the noise mask), some of the generated image masks will become rough and sharp. There was no such problem before
- TAE for Hunyuan Video and WAN 2.1
- camera for live record animation
- Support for SingLoRA weights
- Kontext doesn't work well with lora when rank is large
- Different Conditioning for each Transformer block
- Comfyui portable
- Docs
- Python not yet supported