Hugging Face's logo

Diffusers documentation

VersatileDiffusion

You are viewing v0.10.2 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

VersatileDiffusion

VersatileDiffusion was proposed in Versatile Diffusion: Text, Images and Variations All in One Diffusion Model by Xingqian Xu, Zhangyang Wang, Eric Zhang, Kai Wang, Humphrey Shi .

The abstract of the paper is the following:

The recent advances in diffusion models have set an impressive milestone in many generation tasks. Trending works such as DALL-E2, Imagen, and Stable Diffusion have attracted great interest in academia and industry. Despite the rapid landscape changes, recent new approaches focus on extensions and performance rather than capacity, thus requiring separate models for separate tasks. In this work, we expand the existing single-flow diffusion pipeline into a multi-flow network, dubbed Versatile Diffusion (VD), that handles text-to-image, image-to-text, image-variation, and text-variation in one unified model. Moreover, we generalize VD to a unified multi-flow multimodal diffusion framework with grouped layers, swappable streams, and other propositions that can process modalities beyond images and text. Through our experiments, we demonstrate that VD and its underlying framework have the following merits: a) VD handles all subtasks with competitive quality; b) VD initiates novel extensions and applications such as disentanglement of style and semantic, image-text dual-guided generation, etc.; c) Through these experiments and applications, VD provides more semantic insights of the generated outputs.

Tips

  • VersatileDiffusion is conceptually very similar as Stable Diffusion, but instead of providing just a image data stream conditioned on text, VersatileDiffusion provides both a image and text data stream and can be conditioned on both text and image.

*Run VersatileDiffusion*

You can both load the memory intensive “all-in-one” VersatileDiffusionPipeline that can run all tasks with the same class as shown in VersatileDiffusionPipeline.text_to_image(), VersatileDiffusionPipeline.image_variation(), and VersatileDiffusionPipeline.dual_guided()

or

You can run the individual pipelines which are much more memory efficient:

*How to load and use different schedulers.*

The versatile diffusion pipelines uses DDIMScheduler scheduler by default. But diffusers provides many other schedulers that can be used with the alt diffusion pipeline such as PNDMScheduler, LMSDiscreteScheduler, EulerDiscreteScheduler, EulerAncestralDiscreteScheduler etc. To use a different scheduler, you can either change it via the ConfigMixin.from_config() method or pass the scheduler argument to the from_pretrained method of the pipeline. For example, to use the EulerDiscreteScheduler, you can do the following:

>>> from diffusers import VersatileDiffusionPipeline, EulerDiscreteScheduler

>>> pipeline = VersatileDiffusionPipeline.from_pretrained("shi-labs/versatile-diffusion")
>>> pipeline.scheduler = EulerDiscreteScheduler.from_config(pipeline.scheduler.config)

>>> # or
>>> euler_scheduler = EulerDiscreteScheduler.from_pretrained("shi-labs/versatile-diffusion", subfolder="scheduler")
>>> pipeline = VersatileDiffusionPipeline.from_pretrained("shi-labs/versatile-diffusion", scheduler=euler_scheduler)

VersatileDiffusionPipeline

class diffusers.VersatileDiffusionPipeline

< >

( tokenizer: CLIPTokenizer image_feature_extractor: CLIPFeatureExtractor text_encoder: CLIPTextModel image_encoder: CLIPVisionModel image_unet: UNet2DConditionModel text_unet: UNet2DConditionModel vae: AutoencoderKL scheduler: typing.Union[diffusers.schedulers.scheduling_ddim.DDIMScheduler, diffusers.schedulers.scheduling_pndm.PNDMScheduler, diffusers.schedulers.scheduling_lms_discrete.LMSDiscreteScheduler] )

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. Can be one of DDIMScheduler, LMSDiscreteScheduler, or PNDMScheduler.
  • safety_checker (StableDiffusionMegaSafetyChecker) — Classification module that estimates whether generated images could be considered offensive or harmful. Please, refer to the model card for details.
  • feature_extractor (CLIPFeatureExtractor) — Model that extracts features from generated images to be used as inputs for the safety_checker.

Pipeline for text-to-image generation using Stable Diffusion.

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.)

dual_guided

< >

( prompt: typing.Union[PIL.Image.Image, typing.List[PIL.Image.Image]] image: typing.Union[str, typing.List[str]] text_to_image_strength: float = 0.5 height: typing.Optional[int] = None width: typing.Optional[int] = None num_inference_steps: int = 50 guidance_scale: float = 7.5 num_images_per_prompt: typing.Optional[int] = 1 eta: float = 0.0 generator: typing.Optional[torch._C.Generator] = None latents: 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 ) → ~pipelines.stable_diffusion.ImagePipelineOutput or tuple

Parameters

  • prompt (str or List[str]) — The prompt or prompts to guide the image generation.
  • height (int, optional, defaults to self.image_unet.config.sample_size * self.vae_scale_factor) — The height in pixels of the generated image.
  • width (int, optional, defaults to self.image_unet.config.sample_size * self.vae_scale_factor) — The width in pixels of the generated image.
  • 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.
  • negative_prompt (str or List[str], optional) — The prompt or prompts not to guide the image generation. 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, optional) — A torch generator 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.
  • 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.

Returns

~pipelines.stable_diffusion.ImagePipelineOutput or tuple

~pipelines.stable_diffusion.ImagePipelineOutput if return_dict is True, otherwise a `tuple. When returning a tuple, the first element is a list with the generated images.

Function invoked when calling the pipeline for generation.

Examples:

>>> from diffusers import VersatileDiffusionPipeline
>>> import torch
>>> import requests
>>> from io import BytesIO
>>> from PIL import Image

>>> # let's download an initial image
>>> url = "https://huggingface.co/datasets/diffusers/images/resolve/main/benz.jpg"

>>> response = requests.get(url)
>>> image = Image.open(BytesIO(response.content)).convert("RGB")
>>> text = "a red car in the sun"

>>> pipe = VersatileDiffusionPipeline.from_pretrained(
...     "shi-labs/versatile-diffusion", torch_dtype=torch.float16
... )
>>> pipe = pipe.to("cuda")

>>> generator = torch.Generator(device="cuda").manual_seed(0)
>>> text_to_image_strength = 0.75

>>> image = pipe.dual_guided(
...     prompt=text, image=image, text_to_image_strength=text_to_image_strength, generator=generator
... ).images[0]
>>> image.save("./car_variation.png")

image_variation

< >

( image: typing.Union[torch.FloatTensor, PIL.Image.Image] height: typing.Optional[int] = None width: typing.Optional[int] = None num_inference_steps: int = 50 guidance_scale: float = 7.5 negative_prompt: typing.Union[str, typing.List[str], NoneType] = None num_images_per_prompt: typing.Optional[int] = 1 eta: float = 0.0 generator: typing.Optional[torch._C.Generator] = None latents: 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 ) → StableDiffusionPipelineOutput or tuple

Parameters

  • image (PIL.Image.Image, List[PIL.Image.Image] or torch.Tensor) — The image prompt or prompts to guide the image generation.
  • height (int, optional, defaults to self.image_unet.config.sample_size * self.vae_scale_factor) — The height in pixels of the generated image.
  • width (int, optional, defaults to self.image_unet.config.sample_size * self.vae_scale_factor) — The width in pixels of the generated image.
  • 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.
  • negative_prompt (str or List[str], optional) — The prompt or prompts not to guide the image generation. 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, optional) — A torch generator 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.
  • 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.

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:

>>> from diffusers import VersatileDiffusionPipeline
>>> import torch
>>> import requests
>>> from io import BytesIO
>>> from PIL import Image

>>> # let's download an initial image
>>> url = "https://huggingface.co/datasets/diffusers/images/resolve/main/benz.jpg"

>>> response = requests.get(url)
>>> image = Image.open(BytesIO(response.content)).convert("RGB")

>>> pipe = VersatileDiffusionPipeline.from_pretrained(
...     "shi-labs/versatile-diffusion", torch_dtype=torch.float16
... )
>>> pipe = pipe.to("cuda")

>>> generator = torch.Generator(device="cuda").manual_seed(0)
>>> image = pipe.image_variation(image, generator=generator).images[0]
>>> image.save("./car_variation.png")

text_to_image

< >

( prompt: typing.Union[str, typing.List[str]] height: typing.Optional[int] = None width: typing.Optional[int] = None num_inference_steps: int = 50 guidance_scale: float = 7.5 negative_prompt: typing.Union[str, typing.List[str], NoneType] = None num_images_per_prompt: typing.Optional[int] = 1 eta: float = 0.0 generator: typing.Optional[torch._C.Generator] = None latents: 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 ) → StableDiffusionPipelineOutput or tuple

Parameters

  • prompt (str or List[str]) — The prompt or prompts to guide the image generation.
  • height (int, optional, defaults to self.image_unet.config.sample_size * self.vae_scale_factor) — The height in pixels of the generated image.
  • width (int, optional, defaults to self.image_unet.config.sample_size * self.vae_scale_factor) — The width in pixels of the generated image.
  • 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.
  • negative_prompt (str or List[str], optional) — The prompt or prompts not to guide the image generation. 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, optional) — A torch generator 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.
  • 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.

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:

>>> from diffusers import VersatileDiffusionPipeline
>>> import torch

>>> pipe = VersatileDiffusionPipeline.from_pretrained(
...     "shi-labs/versatile-diffusion", torch_dtype=torch.float16
... )
>>> pipe = pipe.to("cuda")

>>> generator = torch.Generator(device="cuda").manual_seed(0)
>>> image = pipe.text_to_image("an astronaut riding on a horse on mars", generator=generator).images[0]
>>> image.save("./astronaut.png")

VersatileDiffusionTextToImagePipeline

class diffusers.VersatileDiffusionTextToImagePipeline

< >

( tokenizer: CLIPTokenizer text_encoder: CLIPTextModelWithProjection image_unet: UNet2DConditionModel text_unet: UNetFlatConditionModel vae: AutoencoderKL scheduler: typing.Union[diffusers.schedulers.scheduling_ddim.DDIMScheduler, diffusers.schedulers.scheduling_pndm.PNDMScheduler, diffusers.schedulers.scheduling_lms_discrete.LMSDiscreteScheduler] )

Parameters

  • vqvae (VQModel) — Vector-quantized (VQ) Model to encode and decode images to and from latent representations.
  • bert (LDMBertModel) — Text-encoder model based on BERT architecture.
  • tokenizer (transformers.BertTokenizer) — Tokenizer of class BertTokenizer.
  • 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. Can be one of DDIMScheduler, LMSDiscreteScheduler, or PNDMScheduler.

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.)

__call__

< >

( prompt: typing.Union[str, typing.List[str]] height: typing.Optional[int] = None width: typing.Optional[int] = None num_inference_steps: int = 50 guidance_scale: float = 7.5 negative_prompt: typing.Union[str, typing.List[str], NoneType] = None num_images_per_prompt: typing.Optional[int] = 1 eta: float = 0.0 generator: typing.Optional[torch._C.Generator] = None latents: 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 **kwargs ) → StableDiffusionPipelineOutput or tuple

Parameters

  • prompt (str or List[str]) — The prompt or prompts to guide the image generation.
  • height (int, optional, defaults to self.image_unet.config.sample_size * self.vae_scale_factor) — The height in pixels of the generated image.
  • width (int, optional, defaults to self.image_unet.config.sample_size * self.vae_scale_factor) — The width in pixels of the generated image.
  • 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.
  • negative_prompt (str or List[str], optional) — The prompt or prompts not to guide the image generation. 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, optional) — A torch generator 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.
  • 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.

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:

>>> from diffusers import VersatileDiffusionTextToImagePipeline
>>> import torch

>>> pipe = VersatileDiffusionTextToImagePipeline.from_pretrained(
...     "shi-labs/versatile-diffusion", torch_dtype=torch.float16
... )
>>> pipe.remove_unused_weights()
>>> pipe = pipe.to("cuda")

>>> generator = torch.Generator(device="cuda").manual_seed(0)
>>> image = pipe("an astronaut riding on a horse on mars", generator=generator).images[0]
>>> image.save("./astronaut.png")

enable_attention_slicing

< >

( slice_size: typing.Union[str, int, NoneType] = 'auto' )

Parameters

  • slice_size (str or int, optional, defaults to "auto") — When "auto", halves the input to the attention heads, so attention will be computed in two steps. If "max", maxium amount of memory will be saved by running only one slice at a time. If a number is provided, uses as many slices as attention_head_dim // slice_size. In this case, attention_head_dim must be a multiple of slice_size.

Enable sliced attention computation.

When this option is enabled, the attention module will split the input tensor in slices, to compute attention in several steps. This is useful to save some memory in exchange for a small speed decrease.

disable_attention_slicing

< >

( )

Disable sliced attention computation. If enable_attention_slicing was previously invoked, this method will go back to computing attention in one step.

VersatileDiffusionImageVariationPipeline

class diffusers.VersatileDiffusionImageVariationPipeline

< >

( image_feature_extractor: CLIPFeatureExtractor image_encoder: CLIPVisionModelWithProjection image_unet: UNet2DConditionModel vae: AutoencoderKL scheduler: typing.Union[diffusers.schedulers.scheduling_ddim.DDIMScheduler, diffusers.schedulers.scheduling_pndm.PNDMScheduler, diffusers.schedulers.scheduling_lms_discrete.LMSDiscreteScheduler] )

Parameters

  • vqvae (VQModel) — Vector-quantized (VQ) Model to encode and decode images to and from latent representations.
  • bert (LDMBertModel) — Text-encoder model based on BERT architecture.
  • tokenizer (transformers.BertTokenizer) — Tokenizer of class BertTokenizer.
  • 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. Can be one of DDIMScheduler, LMSDiscreteScheduler, or PNDMScheduler.

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.)

__call__

< >

( image: typing.Union[PIL.Image.Image, typing.List[PIL.Image.Image], torch.Tensor] height: typing.Optional[int] = None width: typing.Optional[int] = None num_inference_steps: int = 50 guidance_scale: float = 7.5 negative_prompt: typing.Union[str, typing.List[str], NoneType] = None num_images_per_prompt: typing.Optional[int] = 1 eta: float = 0.0 generator: typing.Optional[torch._C.Generator] = None latents: 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 **kwargs ) → StableDiffusionPipelineOutput or tuple

Parameters

  • image (PIL.Image.Image, List[PIL.Image.Image] or torch.Tensor) — The image prompt or prompts to guide the image generation.
  • height (int, optional, defaults to self.image_unet.config.sample_size * self.vae_scale_factor) — The height in pixels of the generated image.
  • width (int, optional, defaults to self.image_unet.config.sample_size * self.vae_scale_factor) — The width in pixels of the generated image.
  • 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.
  • negative_prompt (str or List[str], optional) — The prompt or prompts not to guide the image generation. 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, optional) — A torch generator 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.
  • 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.

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:

>>> from diffusers import VersatileDiffusionImageVariationPipeline
>>> import torch
>>> import requests
>>> from io import BytesIO
>>> from PIL import Image

>>> # let's download an initial image
>>> url = "https://huggingface.co/datasets/diffusers/images/resolve/main/benz.jpg"

>>> response = requests.get(url)
>>> image = Image.open(BytesIO(response.content)).convert("RGB")

>>> pipe = VersatileDiffusionImageVariationPipeline.from_pretrained(
...     "shi-labs/versatile-diffusion", torch_dtype=torch.float16
... )
>>> pipe = pipe.to("cuda")

>>> generator = torch.Generator(device="cuda").manual_seed(0)
>>> image = pipe(image, generator=generator).images[0]
>>> image.save("./car_variation.png")

enable_attention_slicing

< >

( slice_size: typing.Union[str, int, NoneType] = 'auto' )

Parameters

  • slice_size (str or int, optional, defaults to "auto") — When "auto", halves the input to the attention heads, so attention will be computed in two steps. If "max", maxium amount of memory will be saved by running only one slice at a time. If a number is provided, uses as many slices as attention_head_dim // slice_size. In this case, attention_head_dim must be a multiple of slice_size.

Enable sliced attention computation.

When this option is enabled, the attention module will split the input tensor in slices, to compute attention in several steps. This is useful to save some memory in exchange for a small speed decrease.

disable_attention_slicing

< >

( )

Disable sliced attention computation. If enable_attention_slicing was previously invoked, this method will go back to computing attention in one step.

VersatileDiffusionDualGuidedPipeline

class diffusers.VersatileDiffusionDualGuidedPipeline

< >

( tokenizer: CLIPTokenizer image_feature_extractor: CLIPFeatureExtractor text_encoder: CLIPTextModelWithProjection image_encoder: CLIPVisionModelWithProjection image_unet: UNet2DConditionModel text_unet: UNetFlatConditionModel vae: AutoencoderKL scheduler: typing.Union[diffusers.schedulers.scheduling_ddim.DDIMScheduler, diffusers.schedulers.scheduling_pndm.PNDMScheduler, diffusers.schedulers.scheduling_lms_discrete.LMSDiscreteScheduler] )

Parameters

  • vqvae (VQModel) — Vector-quantized (VQ) Model to encode and decode images to and from latent representations.
  • bert (LDMBertModel) — Text-encoder model based on BERT architecture.
  • tokenizer (transformers.BertTokenizer) — Tokenizer of class BertTokenizer.
  • 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. Can be one of DDIMScheduler, LMSDiscreteScheduler, or PNDMScheduler.

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.)

__call__

< >

( prompt: typing.Union[PIL.Image.Image, typing.List[PIL.Image.Image]] image: typing.Union[str, typing.List[str]] text_to_image_strength: float = 0.5 height: typing.Optional[int] = None width: typing.Optional[int] = None num_inference_steps: int = 50 guidance_scale: float = 7.5 num_images_per_prompt: typing.Optional[int] = 1 eta: float = 0.0 generator: typing.Optional[torch._C.Generator] = None latents: 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 **kwargs ) → ~pipelines.stable_diffusion.ImagePipelineOutput or tuple

Parameters

  • prompt (str or List[str]) — The prompt or prompts to guide the image generation.
  • height (int, optional, defaults to self.image_unet.config.sample_size * self.vae_scale_factor) — The height in pixels of the generated image.
  • width (int, optional, defaults to self.image_unet.config.sample_size * self.vae_scale_factor) — The width in pixels of the generated image.
  • 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.
  • negative_prompt (str or List[str], optional) — The prompt or prompts not to guide the image generation. 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, optional) — A torch generator 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.
  • 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.

Returns

~pipelines.stable_diffusion.ImagePipelineOutput or tuple

~pipelines.stable_diffusion.ImagePipelineOutput if return_dict is True, otherwise a `tuple. When returning a tuple, the first element is a list with the generated images.

Function invoked when calling the pipeline for generation.

Examples:

>>> from diffusers import VersatileDiffusionDualGuidedPipeline
>>> import torch
>>> import requests
>>> from io import BytesIO
>>> from PIL import Image

>>> # let's download an initial image
>>> url = "https://huggingface.co/datasets/diffusers/images/resolve/main/benz.jpg"

>>> response = requests.get(url)
>>> image = Image.open(BytesIO(response.content)).convert("RGB")
>>> text = "a red car in the sun"

>>> pipe = VersatileDiffusionDualGuidedPipeline.from_pretrained(
...     "shi-labs/versatile-diffusion", torch_dtype=torch.float16
... )
>>> pipe.remove_unused_weights()
>>> pipe = pipe.to("cuda")

>>> generator = torch.Generator(device="cuda").manual_seed(0)
>>> text_to_image_strength = 0.75

>>> image = pipe(
...     prompt=text, image=image, text_to_image_strength=text_to_image_strength, generator=generator
... ).images[0]
>>> image.save("./car_variation.png")

enable_attention_slicing

< >

( slice_size: typing.Union[str, int, NoneType] = 'auto' )

Parameters

  • slice_size (str or int, optional, defaults to "auto") — When "auto", halves the input to the attention heads, so attention will be computed in two steps. If "max", maxium amount of memory will be saved by running only one slice at a time. If a number is provided, uses as many slices as attention_head_dim // slice_size. In this case, attention_head_dim must be a multiple of slice_size.

Enable sliced attention computation.

When this option is enabled, the attention module will split the input tensor in slices, to compute attention in several steps. This is useful to save some memory in exchange for a small speed decrease.

disable_attention_slicing

< >

( )

Disable sliced attention computation. If enable_attention_slicing was previously invoked, this method will go back to computing attention in one step.

←Dance Diffusion VQ Diffusion→