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
- How to use last nvidia CUDNN v. 9.16 with ComfyUI and get a subtantial performance leap (or potentially break your setup, YMMV)
- Prompt execution failed
- Intel B580 XPU: Native API failed. Native API returns: 20 (UR_RESULT_ERROR_DEVICE_LOST)
- Wan Speech 2 Video Workflow. Does not support dtype. WHAT MODEL for the WAN2.2 S2V??
- Using multiple processes for a single device can result in the same image names being saved.
- Cannot execute because a node is missing the class type property.: Node lD “#100
- ComfyUI Cloud Workflows doesnt accept Image Res changes
- The latest update broke controls and opening saved built-in workflows.
- add svdquant int4 quantization support based on QuantizedLayout
- [Urgent] Your ComfyUI version 0.3.77 broke OVIS type setting of Load Clip node worked on version 0.3.76
- Docs
- Python not yet supported