diffusers 0.36.0

State-of-the-art diffusion in PyTorch and JAX.

Stars: 32810, Watchers: 32810, Forks: 6773, Open Issues: 908

The huggingface/diffusers repo was created 3 years ago and the last code push was 20 hours ago.
The project is extremely popular with a mindblowing 32810 github stars!

How to Install diffusers

You can install diffusers using pip

pip install diffusers

or add it to a project with poetry

poetry add diffusers

Package Details

Author

The Hugging Face team (past and future) with the help of all our contributors (https://github.com/huggingface/diffusers/graphs/contributors)

License

Apache 2.0 License

Homepage

https://github.com/huggingface/diffusers

PyPi:

https://pypi.org/project/diffusers/

GitHub Repo:

https://github.com/huggingface/diffusers

Classifiers

• Scientific/Engineering/Artificial Intelligence

Related Packages

Errors

A list of common diffusers errors.

Code Examples

Here are some diffusers code examples and snippets.

GitHub Issues

The diffusers package has 908 open issues on GitHub

• [Modular] add explicit workflow support
• Remove *pooled_* mentions from Chroma as it has just one TE.
• [Modular] loader related
• Fix: Cosmos2.5 Video2World frame extraction and add default negative prompt
• [Bug] Fix QwenImageEditPlus Series on NPU
• [Feature] Support QwenImageEditPlus series attention mask for NPU
• [Bug] QwenImageEditPlus series error Expected all tensors to be on the same device on NPU
• [Modular] guard ModularPipeline.blocks attribute
• Modular[add more tests]
• Add train flux2 series lora config
• Question about VAE_IMAGE_SIZE and CONDITION_IMAGE_SIZE constants in pipeline_qwenimage_edit_plus.py
• Support for Multi-Image Input LoRA Training Pipeline for FLUX.2-Klein (e.g., Style Transfer and Multi-Subject Composition)
• [GLM-Image] Add batch support for GlmImagePipeline
• Feature/zimage inpaint pipeline
• Add Flux.2 Klein Inpaint pipeline

See more issues on GitHub