🤗 Diffusers provides pretrained diffusion models across multiple modalities, such as vision and audio, and serves as a modular toolbox for inference and training of diffusion models.
More precisely, 🤗 Diffusers offers:
- State-of-the-art diffusion pipelines that can be run in inference with just a couple of lines of code (see src/diffusers/pipelines). Check this overview to see all supported pipelines and their corresponding official papers.
- Various noise schedulers that can be used interchangeably for the preferred speed vs. quality trade-off in inference (see src/diffusers/schedulers).
- Multiple types of models, such as UNet, can be used as building blocks in an end-to-end diffusion system (see src/diffusers/models).
- Training examples to show how to train the most popular diffusion model tasks (see examples, e.g. unconditional-image-generation).
With pip (official package)
pip install --upgrade diffusers[torch]With conda (maintained by the community)
conda install -c conda-forge diffusersWith pip
pip install --upgrade diffusers[flax]Apple Silicon (M1/M2) support
Please, refer to the documentation.
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 
In order to get started, we recommend taking a look at two notebooks:
- The Getting started with Diffusers
notebook, which showcases an end-to-end example of usage for diffusion models, schedulers and pipelines. Take a look at this notebook to learn how to use the pipeline abstraction, which takes care of everything (model, scheduler, noise handling) for you, and also to understand each independent building block in the library.
- The Training a diffusers model
Stable Diffusion is a text-to-image latent diffusion model created by the researchers and engineers from CompVis, Stability AI, LAION and RunwayML. It's trained on 512x512 images from a subset of the LAION-5B database. This model uses a frozen CLIP ViT-L/14 text encoder to condition the model on text prompts. With its 860M UNet and 123M text encoder, the model is relatively lightweight and runs on a GPU with at least 4GB VRAM. See the model card for more information.
First let's install
pip install --upgrade diffusers transformers accelerateWe recommend using the model in half-precision (fp16) as it gives almost always the same results as full
precision while being roughly twice as fast and requiring half the amount of GPU RAM.
import torch
from diffusers import StableDiffusionPipeline
pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "a photo of an astronaut riding a horse on mars"
image = pipe(prompt).images[0] You can also simply download the model folder and pass the path to the local folder to the StableDiffusionPipeline.
git lfs install
git clone https://huggingface.co/runwayml/stable-diffusion-v1-5
Assuming the folder is stored locally under ./stable-diffusion-v1-5, you can run stable diffusion
as follows:
pipe = StableDiffusionPipeline.from_pretrained("./stable-diffusion-v1-5")
pipe = pipe.to("cuda")
prompt = "a photo of an astronaut riding a horse on mars"
image = pipe(prompt).images[0] If you are limited by GPU memory, you might want to consider chunking the attention computation in addition
to using fp16.
The following snippet should result in less than 4GB VRAM.
pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "a photo of an astronaut riding a horse on mars"
pipe.enable_attention_slicing()
image = pipe(prompt).images[0] If you wish to use a different scheduler (e.g.: DDIM, LMS, PNDM/PLMS), you can instantiate
it before the pipeline and pass it to from_pretrained.
from diffusers import LMSDiscreteScheduler
pipe.scheduler = LMSDiscreteScheduler.from_config(pipe.scheduler.config)
prompt = "a photo of an astronaut riding a horse on mars"
image = pipe(prompt).images[0]
image.save("astronaut_rides_horse.png")If you want to run Stable Diffusion on CPU or you want to have maximum precision on GPU, please run the model in the default full-precision setting:
from diffusers import StableDiffusionPipeline
pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")
# disable the following line if you run on CPU
pipe = pipe.to("cuda")
prompt = "a photo of an astronaut riding a horse on mars"
image = pipe(prompt).images[0]
image.save("astronaut_rides_horse.png")Diffusers offers a JAX / Flax implementation of Stable Diffusion for very fast inference. JAX shines specially on TPU hardware because each TPU server has 8 accelerators working in parallel, but it runs great on GPUs too.
Running the pipeline with the default PNDMScheduler:
import jax
import numpy as np
from flax.jax_utils import replicate
from flax.training.common_utils import shard
from diffusers import FlaxStableDiffusionPipeline
pipeline, params = FlaxStableDiffusionPipeline.from_pretrained(
"runwayml/stable-diffusion-v1-5", revision="flax", dtype=jax.numpy.bfloat16
)
prompt = "a photo of an astronaut riding a horse on mars"
prng_seed = jax.random.PRNGKey(0)
num_inference_steps = 50
num_samples = jax.device_count()
prompt = num_samples * [prompt]
prompt_ids = pipeline.prepare_inputs(prompt)
# shard inputs and rng
params = replicate(params)
prng_seed = jax.random.split(prng_seed, jax.device_count())
prompt_ids = shard(prompt_ids)
images = pipeline(prompt_ids, params, prng_seed, num_inference_steps, jit=True).images
images = pipeline.numpy_to_pil(np.asarray(images.reshape((num_samples,) + images.shape[-3:])))Note:
If you are limited by TPU memory, please make sure to load the FlaxStableDiffusionPipeline in bfloat16 precision instead of the default float32 precision as done above. You can do so by telling diffusers to load the weights from "bf16" branch.
import jax
import numpy as np
from flax.jax_utils import replicate
from flax.training.common_utils import shard
from diffusers import FlaxStableDiffusionPipeline
pipeline, params = FlaxStableDiffusionPipeline.from_pretrained(
"runwayml/stable-diffusion-v1-5", revision="bf16", dtype=jax.numpy.bfloat16
)
prompt = "a photo of an astronaut riding a horse on mars"
prng_seed = jax.random.PRNGKey(0)
num_inference_steps = 50
num_samples = jax.device_count()
prompt = num_samples * [prompt]
prompt_ids = pipeline.prepare_inputs(prompt)
# shard inputs and rng
params = replicate(params)
prng_seed = jax.random.split(prng_seed, jax.device_count())
prompt_ids = shard(prompt_ids)
images = pipeline(prompt_ids, params, prng_seed, num_inference_steps, jit=True).images
images = pipeline.numpy_to_pil(np.asarray(images.reshape((num_samples,) + images.shape[-3:])))Diffusers also has a Image-to-Image generation pipeline with Flax/Jax
import jax
import numpy as np
import jax.numpy as jnp
from flax.jax_utils import replicate
from flax.training.common_utils import shard
import requests
from io import BytesIO
from PIL import Image
from diffusers import FlaxStableDiffusionImg2ImgPipeline
def create_key(seed=0):
return jax.random.PRNGKey(seed)
rng = create_key(0)
url = "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg"
response = requests.get(url)
init_img = Image.open(BytesIO(response.content)).convert("RGB")
init_img = init_img.resize((768, 512))
prompts = "A fantasy landscape, trending on artstation"
pipeline, params = FlaxStableDiffusionImg2ImgPipeline.from_pretrained(
"CompVis/stable-diffusion-v1-4", revision="flax",
dtype=jnp.bfloat16,
)
num_samples = jax.device_count()
rng = jax.random.split(rng, jax.device_count())
prompt_ids, processed_image = pipeline.prepare_inputs(prompt=[prompts]*num_samples, image = [init_img]*num_samples)
p_params = replicate(params)
prompt_ids = shard(prompt_ids)
processed_image = shard(processed_image)
output = pipeline(
prompt_ids=prompt_ids,
image=processed_image,
params=p_params,
prng_seed=rng,
strength=0.75,
num_inference_steps=50,
jit=True,
height=512,
width=768).images
output_images = pipeline.numpy_to_pil(np.asarray(output.reshape((num_samples,) + output.shape[-3:])))The StableDiffusionImg2ImgPipeline lets you pass a text prompt and an initial image to condition the generation of new images.
import requests
import torch
from PIL import Image
from io import BytesIO
from diffusers import StableDiffusionImg2ImgPipeline
# load the pipeline
device = "cuda"
model_id_or_path = "runwayml/stable-diffusion-v1-5"
pipe = StableDiffusionImg2ImgPipeline.from_pretrained(model_id_or_path, torch_dtype=torch.float16)
# or download via git clone https://huggingface.co/runwayml/stable-diffusion-v1-5
# and pass `model_id_or_path="./stable-diffusion-v1-5"`.
pipe = pipe.to(device)
# let's download an initial image
url = "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg"
response = requests.get(url)
init_image = Image.open(BytesIO(response.content)).convert("RGB")
init_image = init_image.resize((768, 512))
prompt = "A fantasy landscape, trending on artstation"
images = pipe(prompt=prompt, image=init_image, strength=0.75, guidance_scale=7.5).images
images[0].save("fantasy_landscape.png")You can also run this example on colab
The StableDiffusionInpaintPipeline lets you edit specific parts of an image by providing a mask and a text prompt.
import PIL
import requests
import torch
from io import BytesIO
from diffusers import StableDiffusionInpaintPipeline
def download_image(url):
response = requests.get(url)
return PIL.Image.open(BytesIO(response.content)).convert("RGB")
img_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png"
mask_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png"
init_image = download_image(img_url).resize((512, 512))
mask_image = download_image(mask_url).resize((512, 512))
pipe = StableDiffusionInpaintPipeline.from_pretrained("runwayml/stable-diffusion-inpainting", torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "Face of a yellow cat, high resolution, sitting on a park bench"
image = pipe(prompt=prompt, image=init_image, mask_image=mask_image).images[0]You can generate your own latents to reproduce results, or tweak your prompt on a specific result you liked. Please have a look at Reusing seeds for deterministic generation.
Fine-tuning techniques make it possible to adapt Stable Diffusion to your own dataset, or add new subjects to it. These are some of the techniques supported in diffusers:
Textual Inversion is a technique for capturing novel concepts from a small number of example images in a way that can later be used to control text-to-image pipelines. It does so by learning new 'words' in the embedding space of the pipeline's text encoder. These special words can then be used within text prompts to achieve very fine-grained control of the resulting images.
-
Textual Inversion. Capture novel concepts from a small set of sample images, and associate them with new "words" in the embedding space of the text encoder. Please, refer to our training examples or documentation to try for yourself.
-
Dreambooth. Another technique to capture new concepts in Stable Diffusion. This method fine-tunes the UNet (and, optionally, also the text encoder) of the pipeline to achieve impressive results. Please, refer to our training example and training report for additional details and training recommendations.
-
Full Stable Diffusion fine-tuning. If you have a more sizable dataset with a specific look or style, you can fine-tune Stable Diffusion so that it outputs images following those examples. This was the approach taken to create a Pokémon Stable Diffusion model (by Justing Pinkney / Lambda Labs), a Japanese specific version of Stable Diffusion (by Rinna Co. and others. You can start at our text-to-image fine-tuning example and go from there.
The release of Stable Diffusion as an open source model has fostered a lot of interesting ideas and experimentation. Our Community Examples folder contains many ideas worth exploring, like interpolating to create animated videos, using CLIP Guidance for additional prompt fidelity, term weighting, and much more! Take a look and contribute your own.
There are many ways to try running Diffusers! Here we outline code-focused tools (primarily using DiffusionPipelines and Google Colab) and interactive web-tools.
If you want to run the code yourself 💻, you can try out:
# !pip install diffusers["torch"] transformers
from diffusers import DiffusionPipeline
device = "cuda"
model_id = "CompVis/ldm-text2im-large-256"
# load model and scheduler
ldm = DiffusionPipeline.from_pretrained(model_id)
ldm = ldm.to(device)
# run pipeline in inference (sample random noise and denoise)
prompt = "A painting of a squirrel eating a burger"
image = ldm([prompt], num_inference_steps=50, eta=0.3, guidance_scale=6).images[0]
# save image
image.save("squirrel.png")# !pip install diffusers["torch"]
from diffusers import DDPMPipeline, DDIMPipeline, PNDMPipeline
model_id = "google/ddpm-celebahq-256"
device = "cuda"
# load model and scheduler
ddpm = DDPMPipeline.from_pretrained(model_id) # you can replace DDPMPipeline with DDIMPipeline or PNDMPipeline for faster inference
ddpm.to(device)
# run pipeline in inference (sample random noise and denoise)
image = ddpm().images[0]
# save image
image.save("ddpm_generated_image.png")Other Image Notebooks:
- image-to-image generation with Stable Diffusion
- tweak images via repeated Stable Diffusion seeds
Diffusers for Other Modalities:
If you just want to play around with some web demos, you can try out the following 🚀 Spaces:
| Model | Hugging Face Spaces |
|---|---|
| Text-to-Image Latent Diffusion |  |
| Faces generator | |
| DDPM with different schedulers | |
| Conditional generation from sketch | |
| Composable diffusion | |
Models: Neural network that models
Figure from DDPM paper (https://arxiv.org/abs/2006.11239).
Schedulers: Algorithm class for both inference and training. The class provides functionality to compute previous image according to alpha, beta schedule as well as predict noise for training. Also known as Samplers. Examples: DDPM, DDIM, PNDM, DEIS
Sampling and training algorithms. Figure from DDPM paper (https://arxiv.org/abs/2006.11239).
Diffusion Pipeline: End-to-end pipeline that includes multiple diffusion models, possible text encoders, ... Examples: Glide, Latent-Diffusion, Imagen, DALL-E 2
Figure from ImageGen (https://imagen.research.google/).
- Readability and clarity is preferred over highly optimized code. A strong importance is put on providing readable, intuitive and elementary code design. E.g., the provided schedulers are separated from the provided models and provide well-commented code that can be read alongside the original paper.
- Diffusers is modality independent and focuses on providing pretrained models and tools to build systems that generate continuous outputs, e.g. vision and audio.
- Diffusion models and schedulers are provided as concise, elementary building blocks. In contrast, diffusion pipelines are a collection of end-to-end diffusion systems that can be used out-of-the-box, should stay as close as possible to their original implementation and can include components of another library, such as text-encoders. Examples for diffusion pipelines are Glide and Latent Diffusion.
For the first release, 🤗 Diffusers focuses on text-to-image diffusion techniques. However, diffusers can be used for much more than that! Over the upcoming releases, we'll be focusing on:
- Diffusers for audio
- Diffusers for reinforcement learning (initial work happening in huggingface#105).
- Diffusers for video generation
- Diffusers for molecule generation (initial work happening in huggingface#54)
A few pipeline components are already being worked on, namely:
- BDDMPipeline for spectrogram-to-sound vocoding
- GLIDEPipeline to support OpenAI's GLIDE model
- Grad-TTS for text to audio generation / conditional audio generation
We want diffusers to be a toolbox useful for diffusers models in general; if you find yourself limited in any way by the current API, or would like to see additional models, schedulers, or techniques, please open a GitHub issue mentioning what you would like to see.
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.
@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}}
}