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(schedulers.lms): bound multistep order by available derivatives (#15108)
- MiniMax-H3 creates full-clip FP32 temporaries after VAE decoding
- Test model imports with older TorchAO installations
- [modular] conditional block triggers should be workflow inputs
- [modular] `ConditionalPipelineBlocks` should declare its own trigger inputs
- Keep fractional fps in encode_video
- Fix: filter Cosmos3 warnings for auxiliary FP8 export scales
- `LMSDiscreteScheduler` uses the wrong multistep order when sampling starts part-way through the schedule (img2img, inpainting)
- use the PLMS schedule when PNDM has fewer than four steps
- warn that pipeline.blocks is a copy
- Docs
- Python not yet supported