diffusers 0.29.2


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

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

Stars: 24189, Watchers: 24189, Forks: 4992, Open Issues: 535

The huggingface/diffusers repo was created 2 years ago and the last code push was 17 minutes ago.
The project is extremely popular with a mindblowing 24189 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

The Hugging Face team (past and future) with the help of all our contributors (
Apache 2.0 License
GitHub Repo:


  • Scientific/Engineering/Artificial Intelligence
No  diffusers  pypi packages just yet.


A list of common diffusers errors.

Code Examples

Here are some diffusers code examples and snippets.

GitHub Issues

The diffusers package has 535 open issues on GitHub

  • Loading StableDiffusionXLControlNetPipeline from single file
  • How to call a different scheduler when training a model from repo
  • Add SDXL long weighted prompt pipeline (replace pr:4629)
  • Should AudioLDM pipeline use separate unet class
  • StableDiffusionXLControlNetPipeline is missing denoising_end
  • Fix Disentangle ONNX and non-ONNX pipeline
  • add data_dir parameter when calling load_dataset
  • Different results after DDIM inverse.
  • Allow passing a checkpoint state_dict to convert_from_ckpt (instead of just a string path)
  • Key-Locked Rank One Editing for Text-to-Image Personalization
  • if "text_embeds" not in added_cond_kwargs: TypeError: argument of type 'NoneType' is not iterable
  • raise EnvironmentError( OSError: Error no file named config.json found in directory /workspace/canny/ControlNet-v1-1.
  • convert controlnet to onnx failed
  • Implementing Fooocus
  • [docs] ControlNet guide

See more issues on GitHub

Related Packages & Articles

clean-fid 0.1.35

FID calculation in PyTorch with proper image resizing and quantization steps

PennyLane 0.37.0

PennyLane is a cross-platform Python library for quantum computing, quantum machine learning, and quantum chemistry. Train a quantum computer the same way as a neural network.

thinc 9.0.0

A refreshing functional take on deep learning, compatible with your favorite libraries

keras 3.4.1

Keras is a deep learning API written in Python, running on top of the machine learning platform TensorFlow. The core data structures of Keras are layers and models. The philosophy is to keep simple things simple, while allowing the user to be fully in control when they need to (the ultimate control being the easy extensibility of the source code via subclassing).

ludwig 0.10.3

Declarative machine learning: End-to-end machine learning pipelines using data-driven configurations.

auto-gptq 0.7.1

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.