diffusers
https://github.com/huggingface/diffusers
Python
๐ค 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 supported1 Subscribers
Add a CodeTriage badge to diffusers
Help out
- Issues
- fix(attention): download hub kernel in AttentionModuleMixin.set_attention_backend
- fix: cast input to weight dtype in PatchEmbed and FluxTransformer2DModel to prevent dtype mismatch
- fix: support torchao >= 0.16.0 by importing renamed CamelCase Config classes
- fix: skip pin_memory and non_blocking transfer for tensor subclasses in group offloading
- fix(dreambooth): batch size mismatch with --with_prior_preservation in flux2 scripts
- fix: disable non-blocking tensor copies to MPS during model loading
- When generating images, if the generator device is on cuda, it break things
- Fix missing latents_bn_std dtype cast in VAE normalization
- Modular Diffusers ๐งจ
- [Neuron] Add AWS Neuron (Trainium/Inferentia) as an officially supported device
- Docs
- Python not yet supported