Hugging Face's logo

Diffusers documentation

MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation

You are viewing v0.17.1 version. A newer version v0.31.0 is available.
Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation

Overview

MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation by Omer Bar-Tal, Lior Yariv, Yaron Lipman, and Tali Dekel.

The abstract of the paper is the following:

*Recent advances in text-to-image generation with diffusion models present transformative capabilities in image quality. However, user controllability of the generated image, and fast adaptation to new tasks still remains an open challenge, currently mostly addressed by costly and long re-training and fine-tuning or ad-hoc adaptations to specific image generation tasks. In this work, we present MultiDiffusion, a unified framework that enables versatile and controllable image generation, using a pre-trained text-to-image diffusion model, without any further training or finetuning. At the center of our approach is a new generation process, based on an optimization task that binds together multiple diffusion generation processes with a shared set of parameters or constraints. We show that MultiDiffusion can be readily applied to generate high quality and diverse images that adhere to user-provided controls, such as desired aspect ratio (e.g., panorama), and spatial guiding signals, ranging from tight segmentation masks to bounding boxes.

Resources:

Available Pipelines:

Pipeline Tasks Demo
StableDiffusionPanoramaPipeline Text-Guided Panorama View Generation 🤗 Space)

Usage example 

import torch
from diffusers import StableDiffusionPanoramaPipeline, DDIMScheduler

model_ckpt = "stabilityai/stable-diffusion-2-base"
scheduler = DDIMScheduler.from_pretrained(model_ckpt, subfolder="scheduler")
pipe = StableDiffusionPanoramaPipeline.from_pretrained(model_ckpt, scheduler=scheduler, torch_dtype=torch.float16)

pipe = pipe.to("cuda")

prompt = "a photo of the dolomites"
image = pipe(prompt).images[0]
image.save("dolomites.png")

While calling this pipeline, it’s possible to specify the view_batch_size to have a >1 value. For some GPUs with high performance, higher a view_batch_size, can speedup the generation and increase the VRAM usage.

StableDiffusionPanoramaPipeline

class diffusers.StableDiffusionPanoramaPipeline

< >

( vae: AutoencoderKL text_encoder: CLIPTextModel tokenizer: CLIPTokenizer unet: UNet2DConditionModel scheduler: DDIMScheduler safety_checker: StableDiffusionSafetyChecker feature_extractor: CLIPImageProcessor requires_safety_checker: bool = True )

Parameters

  • vae (AutoencoderKL) — Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.
  • text_encoder (CLIPTextModel) — Frozen text-encoder. Stable Diffusion uses the text portion of CLIP, specifically the clip-vit-large-patch14 variant.
  • tokenizer (CLIPTokenizer) — Tokenizer of class CLIPTokenizer.
  • unet (UNet2DConditionModel) — Conditional U-Net architecture to denoise the encoded image latents.
  • scheduler (SchedulerMixin) — A scheduler to be used in combination with unet to denoise the encoded image latents. The original work on Multi Diffsion used the DDIMScheduler.
  • safety_checker (StableDiffusionSafetyChecker) — Classification module that estimates whether generated images could be considered offensive or harmful. Please, refer to the model card for details.
  • feature_extractor (CLIPImageProcessor) — Model that extracts features from generated images to be used as inputs for the safety_checker.

Pipeline for text-to-image generation using “MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation”.

This model inherits from DiffusionPipeline. Check the superclass documentation for the generic methods the library implements for all the pipelines (such as downloading or saving, running on a particular device, etc.).

To generate panorama-like images, be sure to pass the width parameter accordingly when using the pipeline. Our recommendation for the width value is 2048. This is the default value of the width parameter for this pipeline.

__call__

< >

( prompt: typing.Union[str, typing.List[str]] = None height: typing.Optional[int] = 512 width: typing.Optional[int] = 2048 num_inference_steps: int = 50 guidance_scale: float = 7.5 view_batch_size: int = 1 negative_prompt: typing.Union[str, typing.List[str], NoneType] = None num_images_per_prompt: typing.Optional[int] = 1 eta: float = 0.0 generator: typing.Union[torch._C.Generator, typing.List[torch._C.Generator], NoneType] = None latents: typing.Optional[torch.FloatTensor] = None prompt_embeds: typing.Optional[torch.FloatTensor] = None negative_prompt_embeds: typing.Optional[torch.FloatTensor] = None output_type: typing.Optional[str] = 'pil' return_dict: bool = True callback: typing.Union[typing.Callable[[int, int, torch.FloatTensor], NoneType], NoneType] = None callback_steps: typing.Optional[int] = 1 cross_attention_kwargs: typing.Union[typing.Dict[str, typing.Any], NoneType] = None ) → StableDiffusionPipelineOutput or tuple

Parameters

  • prompt (str or List[str], optional) — The prompt or prompts to guide the image generation. If not defined, one has to pass prompt_embeds. instead.
  • height (int, optional, defaults to 512 — The height in pixels of the generated image.
  • width (int, optional, defaults to 2048) — The width in pixels of the generated image. The width is kept to a high number because the pipeline is supposed to be used for generating panorama-like images.
  • num_inference_steps (int, optional, defaults to 50) — The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference.
  • guidance_scale (float, optional, defaults to 7.5) — Guidance scale as defined in Classifier-Free Diffusion Guidance. guidance_scale is defined as w of equation 2. of Imagen Paper. Guidance scale is enabled by setting guidance_scale > 1. Higher guidance scale encourages to generate images that are closely linked to the text prompt, usually at the expense of lower image quality.
  • view_batch_size (int, optional, defaults to 1) — The batch size to denoise splited views. For some GPUs with high performance, higher view batch size can speedup the generation and increase the VRAM usage.
  • negative_prompt (str or List[str], optional) — The prompt or prompts not to guide the image generation. If not defined, one has to pass negative_prompt_embeds instead. Ignored when not using guidance (i.e., ignored if guidance_scale is less than 1).
  • num_images_per_prompt (int, optional, defaults to 1) — The number of images to generate per prompt.
  • eta (float, optional, defaults to 0.0) — Corresponds to parameter eta (η) in the DDIM paper: https://arxiv.org/abs/2010.02502. Only applies to schedulers.DDIMScheduler, will be ignored for others.
  • generator (torch.Generator or List[torch.Generator], optional) — One or a list of torch generator(s) to make generation deterministic.
  • latents (torch.FloatTensor, optional) — Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image generation. Can be used to tweak the same generation with different prompts. If not provided, a latents tensor will ge generated by sampling using the supplied random generator.
  • prompt_embeds (torch.FloatTensor, optional) — Pre-generated text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, text embeddings will be generated from prompt input argument.
  • negative_prompt_embeds (torch.FloatTensor, optional) — Pre-generated negative text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, negative_prompt_embeds will be generated from negative_prompt input argument.
  • output_type (str, optional, defaults to "pil") — The output format of the generate image. Choose between PIL: PIL.Image.Image or np.array.
  • return_dict (bool, optional, defaults to True) — Whether or not to return a StableDiffusionPipelineOutput instead of a plain tuple.
  • callback (Callable, optional) — A function that will be called every callback_steps steps during inference. The function will be called with the following arguments: callback(step: int, timestep: int, latents: torch.FloatTensor).
  • callback_steps (int, optional, defaults to 1) — The frequency at which the callback function will be called. If not specified, the callback will be called at every step.
  • cross_attention_kwargs (dict, optional) — A kwargs dictionary that if specified is passed along to the AttentionProcessor as defined under self.processor in diffusers.cross_attention.

Returns

StableDiffusionPipelineOutput or tuple

StableDiffusionPipelineOutput if return_dict is True, otherwise a tuple. When returning a tuple, the first element is a list with the generated images, and the second element is a list of bools denoting whether the corresponding generated image likely represents "not-safe-for-work" (nsfw) content, according to the safety_checker`.

Function invoked when calling the pipeline for generation.

Examples:

>>> import torch
>>> from diffusers import StableDiffusionPanoramaPipeline, DDIMScheduler

>>> model_ckpt = "stabilityai/stable-diffusion-2-base"
>>> scheduler = DDIMScheduler.from_pretrained(model_ckpt, subfolder="scheduler")
>>> pipe = StableDiffusionPanoramaPipeline.from_pretrained(
...     model_ckpt, scheduler=scheduler, torch_dtype=torch.float16
... )

>>> pipe = pipe.to("cuda")

>>> prompt = "a photo of the dolomites"
>>> image = pipe(prompt).images[0]

disable_vae_slicing

< >

( )

Disable sliced VAE decoding. If enable_vae_slicing was previously invoked, this method will go back to computing decoding in one step.

enable_sequential_cpu_offload

< >

( gpu_id = 0 )

Offloads all models to CPU using accelerate, significantly reducing memory usage. When called, unet, text_encoder, vae and safety checker have their state dicts saved to CPU and then are moved to a torch.device('meta') and loaded to GPU only when their specific submodule has its forwardmethod called. Note that offloading happens on a submodule basis. Memory savings are higher than withenable_model_cpu_offload`, but performance is lower.

enable_vae_slicing

< >

( )

Enable sliced VAE decoding.

When this option is enabled, the VAE will split the input tensor in slices to compute decoding in several steps. This is useful to save some memory and allow larger batch sizes.

←Latent Diffusion PaintByExample→