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 additive attention mask handling in the native NPU attention backend.
- [feat] add KVAE-Audio autoencoder
- fix: remove deprecated VQModel/VQEncoderOutput shim past target version 0.31
- Modular: `required=True` is silently ignored when an `InputParam` carries a default
- [Modular] Krea2 Img2Img, Inpaint and Reference Images modular pipeline
- fix(embeddings): change default output_type from np to pt in positional embedding helpers
- fix(ltx2): pass actual sequence length to calculate_shift for dynamic timestep shift
- Fix NaN in KDPM2DiscreteScheduler.sigmas_interpol (all-NaN output on MPS)
- Guard float64 against fp64-less devices in the Helios schedulers
- Secret Leaks workflow fails on every new-branch push (6 of the last 30 runs)
- Docs
- Python not yet supported