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 supported3 Subscribers
Add a CodeTriage badge to diffusers
Help out
- Issues
- Fix NaN corruption on final step in DPMSolverMultistep and UniPCMultistep with `final_sigmas_type="sigma_min"`
- Fix Qwen Image 2.1 compile recompiles
- Deprecate output_type="latent" in modular decoders
- [UniPCMultistepScheduler] Fix final-step NaN/inf at sigma=0 and rks dtype mismatch
- Qwen-Image 2.1 Turbo: VAE tiling introduces vertical streaks at 2048x2048 on NVIDIA/CUDA
- Follow-up to #14737: drop `output_type="latent"` from modular decode blocks
- Add EdenLive
- Warn when a copy of `pipeline.blocks` is modified
- fix(ci): scope GITHUB_TOKEN permissions per job (#15046)
- fix(ci): pin GitHub Actions to commit SHAs (#15046)
- Docs
- Python not yet supported