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(ci): harden workflow triggers, secrets and gates (#15046)
- Third-order DPM++ multistep coefficients fail a quadratic forcing test
- Fix third-order DPM++ multistep coefficients
- [MiniMax-H3] Distribute VAE tiles across a process group
- Quick survey: your experience as a PyTorch Ecosystem maintainer
- add_noise() before set_timesteps() uses the wrong noise level (DPMSolverMultistep, DPMSolverSinglestep, UniPC, DEIS; also SanaPipeline)
- fix(schedulers): use timestep-indexed sigma in add_noise before set_timesteps
- Qwen Image 2.1 with torch.compile triggers a recompile on each run with varying image size
- LTX2 HDR reference preprocessing applies an unintended stride-aligned resize
- [Wan2.2 VAE, Qwen-Image-2.1 VAE] Redundant x.clone() in residual up/down blocks keeps an extra activation alive
- Docs
- Python not yet supported