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
- Add native INT8 ConvRot checkpoint loading
- [MiniMax-H3, Pika H3 Flex] Resample reference soundtracks without torchaudio
- fix: do not add noise at DDPM terminal transition when final timestep is positive
- [core] keep every CPU-overflow component in the balanced device map
- UniPCMultistepScheduler.set_timesteps(sigmas=...) raises TypeError for a list when use_flow_sigmas=True
- [modular] Per-workflow input signature in the docstring of blocks with `_workflow_map`
- `device_map="balanced"` drops all but the last CPU-overflow component, which then loads without offload hooks and breaks inference
- `flash_4_hub` does not forward `return_lse` to its kernel
- Fix FlashAttention 4 log-sum-exp return
- `flash_varlen` raises when requesting log-sum-exp
- Docs
- Python not yet supported