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
- Bump torch from 2.7.0 to 2.13.0 in /examples/server
- fix(aura_flow): cast latents to VAE dtype on every decode
- fix(schedulers): prevent NaN in ancestral schedulers with squaredcos_cap_v2
- [tests] migrate `test_pipelines.py` to use pytest.
- fix(image_processor): return uint16 from LDM3D rgblike_to_depthmap
- [chore] update rest of the licensing headers to 2026.
- fix(pipelines): use forward slash in per-component config.json download allow patterns
- Fix DDIMParallelScheduler batch path ignoring final_alpha_cumprod
- Add a regression test for partial unfuse_lora bookkeeping
- LDM3D rgblike_to_depthmap truncates the 16-bit depth map back to the 8-bit input dtype
- Docs
- Python not yet supported