🤗 Diffusers is the go-to library for state-of-the-art pretrained diffusion models for generating images, audio, and even 3D structures of molecules. Whether you're looking for a simple inference solution or training your own diffusion models, 🤗 Diffusers is a modular toolbox that supports both. Our library is designed with a focus on usability over performance, simple over easy, and customizability over abstractions.
🤗 Diffusers offers three core components:
- State-of-the-art diffusion pipelines that can be run in inference with just a few lines of code.
- Interchangeable noise schedulers for different diffusion speeds and output quality.
- Pretrained models that can be used as building blocks, and combined with schedulers, for creating your own end-to-end diffusion systems.
We recommend installing 🤗 Diffusers in a virtual environment from PyPi or Conda. For more details about installing PyTorch and Flax, please refer to their official documentation.
With pip (official package):
pip install --upgrade diffusers[torch]With conda (maintained by the community):
conda install -c conda-forge diffusersWith pip (official package):
pip install --upgrade diffusers[flax]Please refer to the How to use Stable Diffusion in Apple Silicon guide.
Generating outputs is super easy with 🤗 Diffusers. To generate an image from text, use the from_pretrained method to load any pretrained diffusion model (browse the Hub for 4000+ checkpoints):
from diffusers import DiffusionPipeline
import torch
pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
pipeline.to("cuda")
pipeline("An image of a squirrel in Picasso style").images[0]You can also dig into the models and schedulers toolbox to build your own diffusion system:
from diffusers import DDPMScheduler, UNet2DModel
from PIL import Image
import torch
import numpy as np
scheduler = DDPMScheduler.from_pretrained("google/ddpm-cat-256")
model = UNet2DModel.from_pretrained("google/ddpm-cat-256").to("cuda")
scheduler.set_timesteps(50)
sample_size = model.config.sample_size
noise = torch.randn((1, 3, sample_size, sample_size)).to("cuda")
input = noise
for t in scheduler.timesteps:
with torch.no_grad():
noisy_residual = model(input, t).sample
prev_noisy_sample = scheduler.step(noisy_residual, t, input).prev_sample
input = prev_noisy_sample
image = (input / 2 + 0.5).clamp(0, 1)
image = image.cpu().permute(0, 2, 3, 1).numpy()[0]
image = Image.fromarray((image * 255).round().astype("uint8"))
imageCheck out the Quickstart to launch your diffusion journey today!
| Documentation | What can I learn? |
|---|---|
| Tutorial | A basic crash course for learning how to use the library's most important features like using models and schedulers to build your own diffusion system, and training your own diffusion model. |
| Loading | Guides for how to load and configure all the components (pipelines, models, and schedulers) of the library, as well as how to use different schedulers. |
| Pipelines for inference | Guides for how to use pipelines for different inference tasks, batched generation, controlling generated outputs and randomness, and how to contribute a pipeline to the library. |
| Optimization | Guides for how to optimize your diffusion model to run faster and consume less memory. |
| Training | Guides for how to train a diffusion model for different tasks with different training techniques. |
We ❤️ contributions from the open-source community! If you want to contribute to this library, please check out our Contribution guide. You can look out for issues you'd like to tackle to contribute to the library.
- See Good first issues for general opportunities to contribute
- See New model/pipeline to contribute exciting new diffusion models / diffusion pipelines
- See New scheduler
Also, say 👋 in our public Discord channel 
| Task | Pipeline | 🤗 Hub |
|---|---|---|
| Unconditional Image Generation | DDPM | google/ddpm-ema-church-256 |
| Text-to-Image | Stable Diffusion Text-to-Image | runwayml/stable-diffusion-v1-5 |
| Text-to-Image | unclip | kakaobrain/karlo-v1-alpha |
| Text-to-Image | DeepFloyd IF | DeepFloyd/IF-I-XL-v1.0 |
| Text-to-Image | Kandinsky | kandinsky-community/kandinsky-2-2-decoder |
| Text-guided Image-to-Image | Controlnet | lllyasviel/sd-controlnet-canny |
| Text-guided Image-to-Image | Instruct Pix2Pix | timbrooks/instruct-pix2pix |
| Text-guided Image-to-Image | Stable Diffusion Image-to-Image | runwayml/stable-diffusion-v1-5 |
| Text-guided Image Inpainting | Stable Diffusion Inpaint | runwayml/stable-diffusion-inpainting |
| Image Variation | Stable Diffusion Image Variation | lambdalabs/sd-image-variations-diffusers |
| Super Resolution | Stable Diffusion Upscale | stabilityai/stable-diffusion-x4-upscaler |
| Super Resolution | Stable Diffusion Latent Upscale | stabilityai/sd-x2-latent-upscaler |
- https://github.com/microsoft/TaskMatrix
- https://github.com/invoke-ai/InvokeAI
- https://github.com/apple/ml-stable-diffusion
- https://github.com/Sanster/lama-cleaner
- https://github.com/IDEA-Research/Grounded-Segment-Anything
- https://github.com/ashawkey/stable-dreamfusion
- https://github.com/deep-floyd/IF
- https://github.com/bentoml/BentoML
- https://github.com/bmaltais/kohya_ss
- +3000 other amazing GitHub repositories 💪
Thank you for using us ❤️
This library concretizes previous work by many different authors and would not have been possible without their great research and implementations. We'd like to thank, in particular, the following implementations which have helped us in our development and without which the API could not have been as polished today:
- @CompVis' latent diffusion models library, available here
- @hojonathanho original DDPM implementation, available here as well as the extremely useful translation into PyTorch by @pesser, available here
- @ermongroup's DDIM implementation, available here
- @yang-song's Score-VE and Score-VP implementations, available here
We also want to thank @heejkoo for the very helpful overview of papers, code and resources on diffusion models, available here as well as @crowsonkb and @rromb for useful discussions and insights.
@inproceedings{vladimir-etal-2024-kandinsky,
title = "Kandinsky 3: Text-to-Image Synthesis for Multifunctional Generative Framework",
author = "Vladimir, Arkhipkin and
Vasilev, Viacheslav and
Filatov, Andrei and
Pavlov, Igor and
Agafonova, Julia and
Gerasimenko, Nikolai and
Averchenkova, Anna and
Mironova, Evelina and
Anton, Bukashkin and
Kulikov, Konstantin and
Kuznetsov, Andrey and
Dimitrov, Denis",
editor = "Hernandez Farias, Delia Irazu and
Hope, Tom and
Li, Manling",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-demo.48",
pages = "475--485",
abstract = "Text-to-image (T2I) diffusion models are popular for introducing image manipulation methods, such as editing, image fusion, inpainting, etc. At the same time, image-to-video (I2V) and text-to-video (T2V) models are also built on top of T2I models. We present Kandinsky 3, a novel T2I model based on latent diffusion, achieving a high level of quality and photorealism. The key feature of the new architecture is the simplicity and efficiency of its adaptation for many types of generation tasks. We extend the base T2I model for various applications and create a multifunctional generation system that includes text-guided inpainting/outpainting, image fusion, text-image fusion, image variations generation, I2V and T2V generation. We also present a distilled version of the T2I model, evaluating inference in 4 steps of the reverse process without reducing image quality and 3 times faster than the base model. We deployed a user-friendly demo system in which all the features can be tested in the public domain. Additionally, we released the source code and checkpoints for the Kandinsky 3 and extended models. Human evaluations show that Kandinsky 3 demonstrates one of the highest quality scores among open source generation systems.",
}@misc{arkhipkin2023kandinsky,
title={Kandinsky 3.0 Technical Report},
author={Vladimir Arkhipkin and Andrei Filatov and Viacheslav Vasilev and Anastasia Maltseva and Said Azizov and Igor Pavlov and Julia Agafonova and Andrey Kuznetsov and Denis Dimitrov},
year={2023},
eprint={2312.03511},
archivePrefix={arXiv},
primaryClass={cs.CV}
}@misc{von-platen-etal-2022-diffusers,
author = {Patrick von Platen and Suraj Patil and Anton Lozhkov and Pedro Cuenca and Nathan Lambert and Kashif Rasul and Mishig Davaadorj and Thomas Wolf},
title = {Diffusers: State-of-the-art diffusion models},
year = {2022},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/huggingface/diffusers}}
}