diffusers
https://github.com/huggingface/diffusers
Python
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
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 supported1 Subscribers
Add a CodeTriage badge to diffusers
Help out
- Issues
- Fix: allow Flux Fill pipeline to skip image preprocessing when latents are provided
- DDIMScheduler.step() logic mismatches set_timesteps() list when using timestep_spacing='linspace'
- Potential incorrect indentation for logging in train_dreambooth.py
- [tests] enable cpu offload test in torchao without compilation.
- Feat: fal flashpack support
- from_pipe: Keep existing dtype by default
- Fix duplicate timesteps in DPMSolverMultistepScheduler with sigma conversion methods
- [chore] updates in the pypi publication workflow.
- train_controlnet
- [tests] enhance attention backend tests
- Docs
- Python not yet supported