Skip to content

Releases: huggingface/diffusers

v0.16.0 DeepFloyd IF & ControlNet v1.1

26 Apr 19:52
@patrickvonplaten patrickvonplaten
v0.16.0
6ba0efb
Compare
Choose a tag to compare
v0.16.0 DeepFloyd IF & ControlNet v1.1

DeepFloyd's IF: The open-sourced Imagen

IF

IF is a pixel-based text-to-image generation model and was released in late April 2023 by DeepFloyd.

The model architecture is strongly inspired by Google's closed-sourced Imagen and a novel state-of-the-art open-source text-to-image model with a high degree of photorealism and language understanding:

nabla (1)

Installation

pip install torch --upgrade  # diffusers' IF is optimized for torch 2.0
pip install diffusers --upgrade

Accept the License

Before you can use IF, you need to accept its usage conditions. To do so:

  1. Make sure to have a Hugging Face account and be logged in
  2. Accept the license on the model card of DeepFloyd/IF-I-XL-v1.0
  3. Log-in locally
from huggingface_hub import login

login()

and enter your Hugging Face Hub access token.

Code example

from diffusers import DiffusionPipeline
from diffusers.utils import pt_to_pil
import torch

# stage 1
stage_1 = DiffusionPipeline.from_pretrained("DeepFloyd/IF-I-XL-v1.0", variant="fp16", torch_dtype=torch.float16)
stage_1.enable_model_cpu_offload()

# stage 2
stage_2 = DiffusionPipeline.from_pretrained(
    "DeepFloyd/IF-II-L-v1.0", text_encoder=None, variant="fp16", torch_dtype=torch.float16
)
stage_2.enable_model_cpu_offload()

# stage 3
safety_modules = {
    "feature_extractor": stage_1.feature_extractor,
    "safety_checker": stage_1.safety_checker,
    "watermarker": stage_1.watermarker,
}
stage_3 = DiffusionPipeline.from_pretrained(
    "stabilityai/stable-diffusion-x4-upscaler", **safety_modules, torch_dtype=torch.float16
)
stage_3.enable_model_cpu_offload()

prompt = 'a photo of a kangaroo wearing an orange hoodie and blue sunglasses standing in front of the eiffel tower holding a sign that says "very deep learning"'
generator = torch.manual_seed(1)

# text embeds
prompt_embeds, negative_embeds = stage_1.encode_prompt(prompt)

# stage 1
image = stage_1(
    prompt_embeds=prompt_embeds, negative_prompt_embeds=negative_embeds, generator=generator, output_type="pt"
).images
pt_to_pil(image)[0].save("./if_stage_I.png")
# stage 2
image = stage_2(
    image=image,
    prompt_embeds=prompt_embeds,
    negative_prompt_embeds=negative_embeds,
    generator=generator,
    output_type="pt",
).images
pt_to_pil(image)[0].save("./if_stage_II.png")
# stage 3
image = stage_3(prompt=prompt, image=image, noise_level=100, generator=generator).images
image[0].save("./if_stage_III.png")

For more details about speed and memory optimizations, please have a look at the blog or docs below.

Useful links

👉 The official codebase
👉 Blog post
👉 Space Demo
👉 In-detail docs

ControlNet v1.1

Lvmin Zhang has released improved ControlNet checkpoints as well as a couple of new ones.

You can find all 🧨 Diffusers checkpoints here
Please have a look directly at the model cards on how to use the checkpoins:

Improved checkpoints:

Model Name Control Image Overview Control Image Example Generated Image Example
lllyasviel/control_v11p_sd15_canny
Trained with canny edge detection		 A monochrome image with white edges on a black background.
lllyasviel/control_v11p_sd15_mlsd
Trained with multi-level line segment detection		 An image with annotated line segments.
lllyasviel/control_v11f1p_sd15_depth
Trained with depth estimation		 An image with depth information, usually represented as a grayscale image.
lllyasviel/control_v11p_sd15_normalbae
Trained with surface normal estimation		 An image with surface normal information, usually represented as a color-coded image.
lllyasviel/control_v11p_sd15_seg
Trained with image segmentation		 An image with segmented regions, usually represented as a color-coded image.
lllyasviel/control_v11p_sd15_lineart
Trained with line art generation		 An image with line art, usually black lines on a white background.
lllyasviel/control_v11p_sd15_openpose
Trained with human pose estimation		 An image with human poses, usually represented as a set of keypoints or skeletons.
lllyasviel/control_v11p_sd15_scribble
Trained with scribble-based image generation		 An image with scribbles, usually random or user-drawn strokes.
lllyasviel/control_v11p_sd15_softedge
Trained with soft edge image generation		 An image with soft edges, usually to create a more painterly or artistic effect. <img width="64" src="https://huggingface.co/lllyasviel/control_v11p_sd15_sof...
Read more

Contributors

takuma104, cmdr2, and 27 other contributors
Loading

v0.15.1: Patch Release to fix safety checker, config access and uneven scheduler

17 Apr 17:22
@patrickvonplaten patrickvonplaten
v0.15.1
92bf23a
Compare
Choose a tag to compare
v0.15.1: Patch Release to fix safety checker, config access and uneven scheduler

Fixes bugs related to missing global pooling in controlnet, img2img processor issue with safety checker, uneven timesteps and better config deprecation

Contributors

patrickvonplaten
Loading

v0.15.0 Beyond Image Generation

12 Apr 16:29
@patrickvonplaten patrickvonplaten
v0.15.0
e753454
Compare
Choose a tag to compare
v0.15.0 Beyond Image Generation

Taking Diffusers Beyond Image Generation

We are very excited about this release! It brings new pipelines for video and audio to diffusers, showing that diffusion is a great choice for all sorts of generative tasks. The modular, pluggable approach of diffusers was crucial to integrate the new models intuitively and cohesively with the rest of the library. We hope you appreciate the consistency of the APIs and implementations, as our ultimate goal is to provide the best toolbox to help you solve the tasks you're interested in. Don't hesitate to get in touch if you use diffusers for other projects!

In addition to that, diffusers 0.15 includes a lot of new features and improvements. From performance and deployment improvements (faster pipeline loading) to increased flexibility for creative tasks (Karras sigmas, weight prompting, support for Automatic1111 textual inversion embeddings) to additional customization options (Multi-ControlNet) to training utilities (ControlNet, Min-SNR weighting). Read on for the details!

🎬 Text-to-Video

Text-guided video generation is not a fantasy anymore - it's as simple as spinning up a colab and running any of the two powerful open-sourced video generation models.

Text-to-Video

Alibaba's DAMO Vision Intelligence Lab has open-sourced a first research-only video generation model that can generatae some powerful video clips of up to a minute. To see Darth Vader riding a wave simply copy-paste the following lines into your favorite Python interpreter:

import torch
from diffusers import DiffusionPipeline, DPMSolverMultistepScheduler
from diffusers.utils import export_to_video

pipe = DiffusionPipeline.from_pretrained("damo-vilab/text-to-video-ms-1.7b", torch_dtype=torch.float16, variant="fp16")
pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
pipe.enable_model_cpu_offload()

prompt = "Spiderman is surfing"
video_frames = pipe(prompt, num_inference_steps=25).frames
video_path = export_to_video(video_frames)

vader

For more information you can have a look at "damo-vilab/text-to-video-ms-1.7b"

Text-to-Video Zero

Text2Video-Zero is a zero-shot text-to-video synthesis diffusion model that enables low cost yet consistent video generation with only pre-trained text-to-image diffusion models using simple pre-trained stable diffusion models, such as Stable Diffusion v1-5. Text2Video-Zero also naturally supports cool extension works of pre-trained text-to-image models such as Instruct Pix2Pix, ControlNet and DreamBooth, and based on which we present Video Instruct Pix2Pix, Pose Conditional, Edge Conditional and, Edge Conditional and DreamBooth Specialized applications.

Ftb9VnoakAE_B7T.mp4

For more information please have a look at PAIR/Text2Video-Zero

🔉 Audio Generation

Text-guided audio generation has made great progress over the last months with many advances being based on diffusion models.
The 0.15.0 release includes two powerful audio diffusion models.

AudioLDM

Inspired by Stable Diffusion, AudioLDM
is a text-to-audio latent diffusion model (LDM) that learns continuous audio representations from CLAP
latents. AudioLDM takes a text prompt as input and predicts the corresponding audio. It can generate text-conditional
sound effects, human speech and music.

from diffusers import AudioLDMPipeline
import torch

repo_id = "cvssp/audioldm"
pipe = AudioLDMPipeline.from_pretrained(repo_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")

prompt = "Techno music with a strong, upbeat tempo and high melodic riffs"
audio = pipe(prompt, num_inference_steps=10, audio_length_in_s=5.0).audios[0]

The resulting audio output can be saved as a .wav file:

import scipy

scipy.io.wavfile.write("techno.wav", rate=16000, data=audio)

For more information see cvssp/audioldm

Spectrogram Diffusion

This model from the Magenta team is a MIDI to audio generator. The pipeline takes a MIDI file as input and autoregressively generates 5-sec spectrograms which are concated together in the end and decoded to audio via a Spectrogram decoder.

from diffusers import SpectrogramDiffusionPipeline, MidiProcessor

pipe = SpectrogramDiffusionPipeline.from_pretrained("google/music-spectrogram-diffusion")
pipe = pipe.to("cuda")
processor = MidiProcessor()

# Download MIDI from: wget http://www.piano-midi.de/midis/beethoven/beethoven_hammerklavier_2.mid
output = pipe(processor("beethoven_hammerklavier_2.mid"))

audio = output.audios[0]

📗 New Docs

Documentation is crucially important for diffusers, as it's one of the first resources where people try to understand how everything works and fix any issues they are observing. We have spent a lot of time in this release reviewing all documents, adding new ones, reorganizing sections and bringing code examples up to date with the latest APIs. This effort has been led by @stevhliu (thanks a lot! 🙌) and @yiyixuxu, but many others have chimed in and contributed.

Check it out: https://huggingface.co/docs/diffusers/index

Don't hesitate to open PRs for fixes to the documentation, they are greatly appreciated as discussed in our (revised, of course) contribution guide.

Screenshot from 2023-04-12 18-08-35

🪄 Stable UnCLIP

Stable UnCLIP is the best open-sourced image variation model out there. Pass an initial image and optionally a prompt to generate variations of the image:

from diffusers import DiffusionPipeline
from diffusers.utils import load_image
import torch

pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-2-1-unclip-small", torch_dtype=torch.float16)
pipe.to("cuda")

# get image
url = "https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/stable_unclip/tarsila_do_amaral.png"
image = load_image(url)

# run image variation
image = pipe(image).images[0]

For more information you can have a look at "stabilityai/stable-diffusion-2-1-unclip"

Fsei9kLaUAM27yZ.mp4

🚀 More ControlNet

ControlNet was released in diffusers in version 0.14.0, but we have some exciting developments: Multi-ControlNet, a training script, and upcoming event and a community image-to-image pipeline contributed by @mikegarts!

Multi-ControlNet

Thanks to community member @takuma104, it's now possible to use several ControlNet conditioning models at once! It works with the same API as before, only supplying a list of ControlNets instead of just once:

import torch
from diffusers import StableDiffusionControlNetPipeline, ControlNetModel

controlnet_canny = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", 
                                                   torch_dtype=torch.float16).to("cuda")
controlnet_pose = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-openpose", 
                                                   torch_dtype=torch.float16).to("cuda")

pipe = StableDiffusionControlNetPipeline.from_pretrained(
	"example/a-sd15-variant-model", torch_dtype=torch.float16,
	controlnet=[controlnet_pose, controlnet_canny]
).to("cuda")

pose_image = ...
canny_image = ...
prompt = ...

image = pipe(prompt=prompt, image=[pose_image, canny_image]).images[0]

And this is an example of how this affects generation:

Control Image1 Control Image2 Generated
(none)
(none)

ControlNet Training

We have created a training script for ControlNet, and can't wait to see what new ideas the community may come up with! In fact, we are so pumped about it that we are organizing a JAX Diffusers sprint with a special focus on ControlNet, where participant teams will be assigned TPUs v4-8 to work on their projects 🤯. Those are some mean machines, so make sure you join our discord to follow the event: https://discord.com/channels/879548962464493619/897387888663232554/1092751149217615902.

🐈‍⬛ Textual Inversion, Revisited

Several great contributors have been working on textual inversion to get the most of it. @isamu-isozaki made it possible to perform multitoken training, and @pies...

Read more

Contributors

kig, kashif, and 73 other contributors
Loading

ControlNet, 8K VAE decoding

03 Mar 16:27
@patrickvonplaten patrickvonplaten
v0.14.0
f20c8f5
Compare
Choose a tag to compare
ControlNet, 8K VAE decoding

🚀 ControlNet comes to 🧨 Diffusers!

Thanks to an amazing collaboration with community member @takuma104 🙌, diffusers fully supports ControlNet! All 8 control models from the paper are available for you to use: depth, scribbles, edges, and more. Best of all is that you can take advantage of all the other goodies and optimizations that Diffusers provides out of the box, making this an ultra fast implementation of ControlNet. Take it for a spin to see for yourself.

ControlNet works by training a copy of some of the layers of the original Stable Diffusion model on additional signals, such as depth maps or scribbles. After training, you can provide a depth map as a strong hint of the composition you want to achieve, and have Stable Diffusion fill in the details for you. For example:

Before After

Currently, there are 8 published control models, all of which were trained on runwayml/stable-diffusion-v1-5 (i.e., Stable Diffusion version 1.5). This is an example that uses the scribble controlnet model:

Before After

Or you can turn a cartoon into a realistic photo with incredible coherence:

ControlNet showing a photo generated from a cartoon frame

How do you use ControlNet in diffusers? Just like this (example for the canny edges control model):

from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
import torch

controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", torch_dtype=torch.float16)
pipe = StableDiffusionControlNetPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16
)

As usual, you can use all the features in the diffusers toolbox: super-fast schedulers, memory-efficient attention, model offloading, etc. We think 🧨 Diffusers is the best way to iterate on your ControlNet experiments!

Please, refer to our blog post and documentation for details.

(And, coming soon, ControlNet training – stay tuned!)

💠 VAE tiling for ultra-high resolution generation

Another community member, @kig, conceived, proposed and fully implemented an amazing PR that allows generation of ultra-high resolution images without memory blowing up 🤯. They follow a tiling approach during the image decoding phase of the process, generating a piece of the image at a time and then stitching them all together. Tiles are blended carefully to avoid visible seems between them, and the final result is amazing. This is the additional code you need to use to enjoy high-resolution generations:

pipe.vae.enable_tiling()

That's it!

For a complete example, refer to the PR or the code snippet we reproduce here for your convenience:

import torch
from diffusers import StableDiffusionPipeline

pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", revision="fp16", torch_dtype=torch.float16)
pipe = pipe.to("cuda")
pipe.enable_xformers_memory_efficient_attention()
pipe.vae.enable_tiling()

prompt = "a beautiful landscape photo"
image = pipe(prompt, width=4096, height=2048, num_inference_steps=10).images[0]

image.save("4k_landscape.jpg")

All commits

Significant community contributions

The following contributors have made significant changes to the library over the last release:

New Contributors

Full Changelog: v0.13.0...v0.14.0

Contributors

kig, takuma104, and 11 other contributors
Loading

v0.13.1: Patch Release to fix warning when loading from `revision="fp16"`

20 Feb 09:43
@patrickvonplaten patrickvonplaten
v0.13.1
8e44aa4
Compare
Choose a tag to compare
v0.13.1: Patch Release to fix warning when loading from `revision="fp16"`

Contributors

yiyixuxu, haofanwang, and 2 other contributors
Loading

Controllable Generation: Pix2Pix0, Attend and Excite, SEGA, SAG, ...

20 Feb 09:42
@patrickvonplaten patrickvonplaten
v0.13.0
b2c1e0d
Compare
Choose a tag to compare
Controllable Generation: Pix2Pix0, Attend and Excite, SEGA, SAG, ...

🎯 Controlling Generation

There has been much recent work on fine-grained control of diffusion networks!

Diffusers now supports:

  1. Instruct Pix2Pix
  2. Pix2Pix 0, more details in docs
  3. Attend and excite, more details in docs
  4. Semantic guidance, more details in docs
  5. Self-attention guidance, more details in docs
  6. Depth2image
  7. MultiDiffusion panorama, more details in docs

See our doc on controlling image generation and the individual pipeline docs for more details on the individual methods.

🆙 Latent Upscaler

Latent Upscaler is a diffusion model that is designed explicitly for Stable Diffusion. You can take the generated latent from Stable Diffusion and pass it into the upscaler before decoding with your standard VAE. Or you can take any image, encode it into the latent space, use the upscaler, and decode it. It is incredibly flexible and can work with any SD checkpoints.

Original output image 2x upscaled output image

The model was developed by Katherine Crowson in collaboration with Stability AI

from diffusers import StableDiffusionLatentUpscalePipeline, StableDiffusionPipeline
import torch

pipeline = StableDiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", torch_dtype=torch.float16)
pipeline.to("cuda")

upscaler = StableDiffusionLatentUpscalePipeline.from_pretrained("stabilityai/sd-x2-latent-upscaler", torch_dtype=torch.float16)
upscaler.to("cuda")

prompt = "a photo of an astronaut high resolution, unreal engine, ultra realistic"
generator = torch.manual_seed(33)

# we stay in latent space! Let's make sure that Stable Diffusion returns the image
# in latent space
low_res_latents = pipeline(prompt, generator=generator, output_type="latent").images

upscaled_image = upscaler(
    prompt=prompt,
    image=low_res_latents,
    num_inference_steps=20,
    guidance_scale=0,
    generator=generator,
).images[0]

# Let's save the upscaled image under "upscaled_astronaut.png"
upscaled_image.save("astronaut_1024.png")

# as a comparison: Let's also save the low-res image
with torch.no_grad():
    image = pipeline.decode_latents(low_res_latents)
image = pipeline.numpy_to_pil(image)[0]

image.save("astronaut_512.png")

⚡ Optimization

In addition to new features and an increasing number of pipelines, diffusers cares a lot about performance. This release brings a number of optimizations that you can turn on easily.

xFormers

Memory efficient attention, as implemented by xFormers, has been available in diffusers for some time. The problem was that installing xFormers could be complicated because there were no official pip wheels (or they were outdated), and you had to resort to installing from source.

From xFormers 0.0.16, official pip wheels are now published with every release, so installing and using xFormers is now as simple as these two steps:

  1. pip install xformers in your terminal.
  2. pipe.enable_xformers_memory_efficient_attention() in your code to opt-in in your pipelines.

These actions will unlock dramatic memory savings, and usually faster inference too!

See more details in the documentation.

Torch 2.0

Speaking of memory-efficient attention, Accelerated PyTorch 2.0 Transformers now comes with built-in native support for it! When PyTorch 2.0 is released you'll no longer have to install xFormers or any third-party package to take advantage of it. In diffusers we are already preparing for that, and it works out of the box. So, if you happen to be using the latest "nightlies" of PyTorch 2.0 beta, then you're all set – diffusers will use Accelerated PyTorch 2.0 Transformers by default.

In our tests, the built-in PyTorch 2.0 implementation is usually as fast as xFormers', and sometimes even faster. Performance depends on the card you are using and whether you run your code in float16 or float32, so check our documentation for details.

Coarse-grained CPU offload

Community member @keturn, with whom we have enjoyed thoughtful software design conversations, called our attention to the fact that enabling sequential cpu offloading via enable_sequential_cpu_offload worked great to save a lot of memory, but made inference much slower.

This is because enable_sequential_cpu_offload() is optimized for memory, and it recursively works across all the submodules contained in a model, moving them to GPU when they are needed and back to CPU when another submodule needs to run. These cpu-to-gpu-to-cpu transfers happen hundreds of times during the stable diffusion denoising loops, because the UNet runs multiple times and it consists of several PyTorch modules.

This release of diffusers introduces a coarser enable_model_cpu_offload() pipeline API, which copies whole models (not modules) to GPU and makes sure they stay there until another model needs to run. The consequences are:

  • Less memory savings than enable_sequential_cpu_offload, but:
  • Almost as fast inference as when the pipeline is used without any type of offloading.

Pix2Pix Zero

Remember the CycleGAN days where one would turn a horse into a zebra in an image while keeping the rest of the content almost untouched? Well, that day has arrived but in the context of Diffusion. Pix2Pix Zero allows users to edit a particular image (be it real or generated), targeting a source concept (horse, for example) and replacing it with a target concept (zebra, for example).

Input image Edited image
original edited

Pix2Pix Zero was proposed in Zero-shot Image-to-Image Translation. The StableDiffusionPix2PixZeroPipeline allows you to

  1. Edit an image generated from an input prompt
  2. Provide an input image and edit it

For the latter, it uses the newly introduced DDIMInverseScheduler to first obtain the inverted noise from the input image and use that in the subsequent generation process.

Both of the use cases leverage the idea of "edit directions", used for steering the generation toward the target concept gradually from the source concept. To know more, we recommend checking out the official documentation.

Attend and excite

Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models. Attend-and-Excite, guides the generative model to modify the cross-attention values during the image synthesis process to generate images that more faithfully depict the input text prompt. It allows creating images that are more semantically faithful with respect to the input text prompts. Thanks to community contributor @evinpinar for leading the charge to add this pipeline!

Semantic guidance

Semantic Guidance for Diffusion Models was proposed in SEGA: Instructing Diffusion using Semantic Dimensions and provides strong semantic control over image generation. Small changes to the text prompt usually result in entirely different output images. However, with SEGA, a variety of changes to the image are enabled that can be controlled easily and intuitively and stay true to the original image composition. Thanks to the lead author of SEFA, Manuel (@manuelbrack), who added the pipeline in #2223.

Here is a simple demo:

import torch
from diffusers import SemanticStableDiffusionPipeline

pipe = SemanticStableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
pipe = pipe.to("cuda")

out = pipe(
    prompt="a photo of the face of a woman",
    num_images_per_prompt=1,
    guidance_scale=7,
    editing_prompt=[
        "smiling, smile",  # Concepts to apply
        "glasses, wearing glasses",
        "curls, wavy hair, curly hair",
        "beard, full beard, mustache",
    ],
    reverse_editing_direction=[False, False, False, False],  # Direction of guidance i.e. increase all concepts
    edit_warmup_steps=[10, 10, 10, 10],  # Warmup period for each concept
...
Read more

Contributors

kashif, keturn, and 49 other contributors
Loading

v0.12.1: Patch Release to fix local files only

27 Jan 07:56
@patrickvonplaten patrickvonplaten
v0.12.1
374ec16
Compare
Choose a tag to compare
v0.12.1: Patch Release to fix local files only

Make sure cached models can be loaded in offline mode.

Contributors

patrickvonplaten
Loading

Instruct-Pix2Pix, DiT, LoRA

25 Jan 16:10
@patrickvonplaten patrickvonplaten
v0.12.0
180841b
Compare
Choose a tag to compare
Instruct-Pix2Pix, DiT, LoRA

🪄 Instruct-Pix2Pix

Instruct-Pix2Pix is a Stable Diffusion model fine-tuned for editing images from human instructions. Given an input image and a written instruction that tells the model what to do, the model follows these instructions to edit the image.

image

The model was released with the paper InstructPix2Pix: Learning to Follow Image Editing Instructions. More information about the model can be found in the paper.

pip install diffusers transformers safetensors accelerate

import PIL
import requests
import torch
from diffusers import StableDiffusionInstructPix2PixPipeline

model_id = "timbrooks/instruct-pix2pix"
pipe = StableDiffusionInstructPix2PixPipeline.from_pretrained(model_id, torch_dtype=torch.float16).to("cuda")

url = "https://huggingface.co/datasets/diffusers/diffusers-images-docs/resolve/main/mountain.png"
def download_image(url):
    image = PIL.Image.open(requests.get(url, stream=True).raw)
    image = PIL.ImageOps.exif_transpose(image)
    image = image.convert("RGB")
    return image
image = download_image(url)

prompt = "make the mountains snowy"
edit = pipe(prompt, image=image, num_inference_steps=20, image_guidance_scale=1.5, guidance_scale=7).images[0]
images[0].save("snowy_mountains.png")

🤖 DiT

Diffusion Transformers (DiTs) is a class conditional latent diffusion model which replaces the commonly used U-Net backbone with a transformer operating on latent patches. The pretrained model is trained on the ImageNet-1K dataset and is able to generate class conditional images of 256x256 or 512x512 pixels.

dit

The model was released with the paper Scalable Diffusion Models with Transformers.

import torch
from diffusers import DiTPipeline

model_id = "facebook/DiT-XL-2-256"
pipe = DiTPipeline.from_pretrained(model_id, torch_dtype=torch.float16).to("cuda")

# pick words that exist in ImageNet
words = ["white shark", "umbrella"]
class_ids = pipe.get_label_ids(words)

output = pipe(class_labels=class_ids)
image = output.images[0]  # label 'white shark'

⚡ LoRA

LoRA is a technique for performing parameter-efficient fine-tuning for large models. LoRA works by adding so-called "update matrices" to specific blocks of a pre-trained model. During fine-tuning, only these update matrices are updated while the pre-trained model parameters are kept frozen. This allows us to achieve greater memory efficiency as well as easier portability during fine-tuning.

LoRA was proposed in LoRA: Low-Rank Adaptation of Large Language Models. In the original paper, the authors investigated LoRA for fine-tuning large language models like GPT-3. cloneofsimo was the first to try out LoRA training for Stable Diffusion in the popular lora GitHub repository.

Diffusers now supports LoRA! This means you can now fine-tune a model like Stable Diffusion using consumer GPUs like Tesla T4 or RTX 2080 Ti. LoRA support was added to UNet2DConditionModel and DreamBooth training script by @patrickvonplaten in #1884.

By using LoRA, the fine-tuned checkpoints will be just 3 MBs in size. After fine-tuning, you can use the LoRA checkpoints like so:

from diffusers import StableDiffusionPipeline
import torch

model_path = "sayakpaul/sd-model-finetuned-lora-t4"
pipe = StableDiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", torch_dtype=torch.float16)
pipe.unet.load_attn_procs(model_path)
pipe.to("cuda")

prompt = "A pokemon with blue eyes."
image = pipe(prompt, num_inference_steps=30, guidance_scale=7.5).images[0]
image.save("pokemon.png")

pokemon-image

You can follow these resources to know more about how to use LoRA in diffusers:

📐 Customizable Cross Attention

LoRA leverages a new method to customize the cross attention layers deep in the UNet. This can be useful for other creative approaches such as Prompt-to-Prompt, and it makes it easier to apply optimizers like xFormers. This new "attention processor" abstraction was created by @patrickvonplaten in #1639 after discussing the design with the community, and we have used it to rewrite our xFormers and attention slicing implementations!

🌿 Flax => PyTorch

A long requested feature, prolific community member @camenduru took up the gauntlet in #1900 and created a way to convert Flax model weights for PyTorch. This means that you can train or fine-tune models super fast using Google TPUs, and then convert the weights to PyTorch for everybody to use. Thanks @camenduru!

🌀 Flax Img2Img

Another community member, @dhruvrnaik, ported the image-to-image pipeline to Flax in #1355! Using a TPU v2-8 (available in Colab's free tier), you can generate 8 images at once in a few seconds!

🎲 DEIS Scheduler

DEIS (Diffusion Exponential Integrator Sampler) is a new fast mult step scheduler that can generate high-quality samples in fewer steps.
The scheduler was introduced in the paper Fast Sampling of Diffusion Models with Exponential Integrator. More information about the scheduler can be found in the paper.

from diffusers import StableDiffusionPipeline, DEISMultistepScheduler
import torch

pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
pipe.scheduler = DEISMultistepScheduler.from_config(pipe.scheduler.config)
pipe = pipe.to("cuda")

prompt = "a photo of an astronaut riding a horse on mars"
generator = torch.Generator(device="cuda").manual_seed(0)
image = pipe(prompt, generator=generator, num_inference_steps=25).images[0
  • feat : add log-rho deis multistep scheduler by @qsh-zh #1432

Reproducibility

One can now pass CPU generators to all pipelines even if the pipeline is on GPU. This ensures
much better reproducibility across GPU hardware:

import torch
from diffusers import DDIMPipeline
import numpy as np

model_id = "google/ddpm-cifar10-32"

# load model and scheduler
ddim = DDIMPipeline.from_pretrained(model_id)
ddim.to("cuda")

# create a generator for reproducibility
generator = torch.manual_seed(0)

# run pipeline for just two steps and return numpy tensor
image = ddim(num_inference_steps=2, output_type="np", generator=generator).images
print(np.abs(image).sum())

See: #1902 and https://huggingface.co/docs/diffusers/using-diffusers/reproducibility

Important New Guides

Important Bug Fixes

  • Don't download safetensors if library is not installed: #2057
  • Make sure that save_pretrained(...) doesn't accidentally delete files: #2038
  • Fix CPU offload docs for maximum memory gain: #1968
  • Fix conversion for exotically sorted weight names: #1959
  • Fix intermediate checkpointing for textual inversion, thanks @lstein #2072

All commits

Read more

Contributors

kig, kashif, and 53 other contributors
Loading

v0.11.1: Patch release

20 Dec 16:32
@anton-l anton-l
v0.11.1
f7bb9ca
Compare
Choose a tag to compare
v0.11.1: Patch release

This patch release fixes a bug with num_images_per_prompt in the UnCLIPPipeline

Contributors

patil-suraj
Loading

v0.11.0: Karlo UnCLIP, safetensors, pipeline versions

19 Dec 17:47
@anton-l anton-l
v0.11.0
a5edb98
Compare
Choose a tag to compare
v0.11.0: Karlo UnCLIP, safetensors, pipeline versions

🪄 Karlo UnCLIP by Kakao Brain

Karlo is a text-conditional image generation model based on OpenAI's unCLIP architecture with the improvement over the standard super-resolution model from 64px to 256px, recovering high-frequency details in a small number of denoising steps.

This alpha version of Karlo is trained on 115M image-text pairs, including COYO-100M high-quality subset, CC3M, and CC12M.
For more information about the architecture, see the Karlo repository: https://github.com/kakaobrain/karlo
image

pip install diffusers transformers safetensors accelerate

import torch
from diffusers import UnCLIPPipeline

pipe = UnCLIPPipeline.from_pretrained("kakaobrain/karlo-v1-alpha", torch_dtype=torch.float16)
pipe = pipe.to("cuda")

prompt = "a high-resolution photograph of a big red frog on a green leaf."
image = pipe(prompt).images[0]

img

:octocat: Community pipeline versioning

The community pipelines hosted in diffusers/examples/community will now follow the installed version of the library.

E.g. if you have diffusers==0.9.0 installed, the pipelines from the v0.9.0 branch will be used: https://github.com/huggingface/diffusers/tree/v0.9.0/examples/community

If you've installed diffusers from source, e.g. with pip install git+https://github.com/huggingface/diffusers then the latest versions of the pipelines will be fetched from the main branch.

To change the custom pipeline version, set the custom_revision variable like so:

pipeline = DiffusionPipeline.from_pretrained(
     "google/ddpm-cifar10-32", custom_pipeline="one_step_unet", custom_revision="0.10.2"
)

🦺 safetensors

Many of the most important checkpoints now have https://github.com/huggingface/safetensors available. Upon installing safetensors with:

pip install safetensors

You will see a nice speed-up when loading your model 🚀

Some of the most improtant checkpoints have safetensor weights added now:

Batched generation bug fixes 🐛

We fixed a lot of bugs for batched generation. All pipelines should now correctly process batches of prompts and images 🤗
Also we made it much easier to tweak images with reproducible seeds:
https://huggingface.co/docs/diffusers/using-diffusers/reusing_seeds

📝 Changelog

Contributors

maruel, msiedlarek, and 22 other contributors
Loading