Hugging Face's logo

Diffusers documentation

Latent Diffusion

Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

Latent Diffusion

Latent Diffusion was proposed in High-Resolution Image Synthesis with Latent Diffusion Models by Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, Björn Ommer.

The abstract from the paper is:

By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a guiding mechanism to control the image generation process without retraining. However, since these models typically operate directly in pixel space, optimization of powerful DMs often consumes hundreds of GPU days and inference is expensive due to sequential evaluations. To enable DM training on limited computational resources while retaining their quality and flexibility, we apply them in the latent space of powerful pretrained autoencoders. In contrast to previous work, training diffusion models on such a representation allows for the first time to reach a near-optimal point between complexity reduction and detail preservation, greatly boosting visual fidelity. By introducing cross-attention layers into the model architecture, we turn diffusion models into powerful and flexible generators for general conditioning inputs such as text or bounding boxes and high-resolution synthesis becomes possible in a convolutional manner. Our latent diffusion models (LDMs) achieve a new state of the art for image inpainting and highly competitive performance on various tasks, including unconditional image generation, semantic scene synthesis, and super-resolution, while significantly reducing computational requirements compared to pixel-based DMs.

The original codebase can be found at CompVis/latent-diffusion.

Make sure to check out the Schedulers guide to learn how to explore the tradeoff between scheduler speed and quality, and see the reuse components across pipelines section to learn how to efficiently load the same components into multiple pipelines.

LDMTextToImagePipeline

class diffusers.LDMTextToImagePipeline

< >

( vqvae: typing.Union[diffusers.models.autoencoders.vq_model.VQModel, diffusers.models.autoencoders.autoencoder_kl.AutoencoderKL] bert: PreTrainedModel tokenizer: PreTrainedTokenizer unet: typing.Union[diffusers.models.unets.unet_2d.UNet2DModel, diffusers.models.unets.unet_2d_condition.UNet2DConditionModel] 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.
  • tokenizer (BertTokenizer) — A BertTokenizer to tokenize text.
  • unet (UNet2DConditionModel) — A UNet2DConditionModel 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.

Pipeline for text-to-image generation using latent diffusion.

This model inherits from DiffusionPipeline. Check the superclass documentation for the generic methods implemented for all pipelines (downloading, 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: typing.Optional[int] = 50 guidance_scale: typing.Optional[float] = 1.0 eta: typing.Optional[float] = 0.0 generator: typing.Union[torch._C.Generator, typing.List[torch._C.Generator], NoneType] = None latents: typing.Optional[torch.Tensor] = None output_type: typing.Optional[str] = 'pil' return_dict: bool = True **kwargs ) → ImagePipelineOutput or tuple

Parameters

  • prompt (str or List[str]) — The prompt or prompts to guide the image generation.
  • height (int, optional, defaults to self.unet.config.sample_size * self.vae_scale_factor) — The height in pixels of the generated image.
  • width (int, optional, defaults to self.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 1.0) — A higher guidance scale value encourages the model to generate images closely linked to the text prompt at the expense of lower image quality. Guidance scale is enabled when guidance_scale > 1.
  • generator (torch.Generator, optional) — A torch.Generator to make generation deterministic.
  • latents (torch.Tensor, 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 is generated by sampling using the supplied random generator.
  • output_type (str, optional, defaults to "pil") — The output format of the generated image. Choose between PIL.Image or np.array.
  • return_dict (bool, optional, defaults to True) — Whether or not to return a ImagePipelineOutput instead of a plain tuple.

Returns

ImagePipelineOutput or tuple

If return_dict is True, ImagePipelineOutput is returned, otherwise a tuple is returned where the first element is a list with the generated images.

The call function to the pipeline for generation.

Example:

>>> from diffusers import DiffusionPipeline

>>> # load model and scheduler
>>> ldm = DiffusionPipeline.from_pretrained("CompVis/ldm-text2im-large-256")

>>> # run pipeline in inference (sample random noise and denoise)
>>> prompt = "A painting of a squirrel eating a burger"
>>> images = ldm([prompt], num_inference_steps=50, eta=0.3, guidance_scale=6).images

>>> # save images
>>> for idx, image in enumerate(images):
...     image.save(f"squirrel-{idx}.png")

LDMSuperResolutionPipeline

class diffusers.LDMSuperResolutionPipeline

< >

( vqvae: VQModel unet: UNet2DModel scheduler: typing.Union[diffusers.schedulers.scheduling_ddim.DDIMScheduler, diffusers.schedulers.scheduling_pndm.PNDMScheduler, diffusers.schedulers.scheduling_lms_discrete.LMSDiscreteScheduler, diffusers.schedulers.scheduling_euler_discrete.EulerDiscreteScheduler, diffusers.schedulers.scheduling_euler_ancestral_discrete.EulerAncestralDiscreteScheduler, diffusers.schedulers.scheduling_dpmsolver_multistep.DPMSolverMultistepScheduler] )

Parameters

A pipeline for image super-resolution using latent diffusion.

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

__call__

< >

( image: typing.Union[torch.Tensor, PIL.Image.Image] = None batch_size: typing.Optional[int] = 1 num_inference_steps: typing.Optional[int] = 100 eta: typing.Optional[float] = 0.0 generator: typing.Union[torch._C.Generator, typing.List[torch._C.Generator], NoneType] = None output_type: typing.Optional[str] = 'pil' return_dict: bool = True ) → ImagePipelineOutput or tuple

Parameters

  • image (torch.Tensor or PIL.Image.Image) — Image or tensor representing an image batch to be used as the starting point for the process.
  • batch_size (int, optional, defaults to 1) — Number of images to generate.
  • num_inference_steps (int, optional, defaults to 100) — The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference.
  • eta (float, optional, defaults to 0.0) — Corresponds to parameter eta (η) from the DDIM paper. Only applies to the DDIMScheduler, and is ignored in other schedulers.
  • generator (torch.Generator or List[torch.Generator], optional) — A torch.Generator to make generation deterministic.
  • output_type (str, optional, defaults to "pil") — The output format of the generated image. Choose between PIL.Image or np.array.
  • return_dict (bool, optional, defaults to True) — Whether or not to return a ImagePipelineOutput instead of a plain tuple.

Returns

ImagePipelineOutput or tuple

If return_dict is True, ImagePipelineOutput is returned, otherwise a tuple is returned where the first element is a list with the generated images

The call function to the pipeline for generation.

Example:

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

>>> # load model and scheduler
>>> pipeline = LDMSuperResolutionPipeline.from_pretrained("CompVis/ldm-super-resolution-4x-openimages")
>>> pipeline = pipeline.to("cuda")

>>> # let's download an  image
>>> url = (
...     "https://user-images.githubusercontent.com/38061659/199705896-b48e17b8-b231-47cd-a270-4ffa5a93fa3e.png"
... )
>>> response = requests.get(url)
>>> low_res_img = Image.open(BytesIO(response.content)).convert("RGB")
>>> low_res_img = low_res_img.resize((128, 128))

>>> # run pipeline in inference (sample random noise and denoise)
>>> upscaled_image = pipeline(low_res_img, num_inference_steps=100, eta=1).images[0]
>>> # save image
>>> upscaled_image.save("ldm_generated_image.png")

ImagePipelineOutput

class diffusers.ImagePipelineOutput

< >

( images: typing.Union[typing.List[PIL.Image.Image], numpy.ndarray] )

Parameters

  • images (List[PIL.Image.Image] or np.ndarray) — List of denoised PIL images of length batch_size or NumPy array of shape (batch_size, height, width, num_channels).

Output class for image pipelines.

< > Update on GitHub

←Latent Consistency Models Latte→