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
- ⚡️ Speed up function `state_dict_prefix_replace` by 127%
- Native support for Skyreels AutoRegressive Diffusion-Forcing architecture
- Support for MAGI-1 (Autoregressive Video Generation)
- Support for better quality Ksampler previews for WAN models
- Option to run live preview in a CUDA stream for better performance.
- When using reverse proxy, some dynamic endpoints do not resolve
- Can we not default to installing the CPU version of 'torch torchvision torchauudio'
- fix(memory, docker): support for reading cgroup data
- fully interference using only CPU use cpu at low power 10% of cpu , how to make comfy use 100% cpu?
- Comfy doesn't seem to offload vram correctly on amd cards
- Docs
- Python not yet supported