Diffusers documentation


You are viewing main version, which requires installation from source. If you'd like regular pip install, checkout the latest stable version (v0.28.0).
Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started


RePaintScheduler is a DDPM-based inpainting scheduler for unsupervised inpainting with extreme masks. It is designed to be used with the RePaintPipeline, and it is based on the paper RePaint: Inpainting using Denoising Diffusion Probabilistic Models by Andreas Lugmayr et al.

The abstract from the paper is:

Free-form inpainting is the task of adding new content to an image in the regions specified by an arbitrary binary mask. Most existing approaches train for a certain distribution of masks, which limits their generalization capabilities to unseen mask types. Furthermore, training with pixel-wise and perceptual losses often leads to simple textural extensions towards the missing areas instead of semantically meaningful generation. In this work, we propose RePaint: A Denoising Diffusion Probabilistic Model (DDPM) based inpainting approach that is applicable to even extreme masks. We employ a pretrained unconditional DDPM as the generative prior. To condition the generation process, we only alter the reverse diffusion iterations by sampling the unmasked regions using the given image information. Since this technique does not modify or condition the original DDPM network itself, the model produces high-quality and diverse output images for any inpainting form. We validate our method for both faces and general-purpose image inpainting using standard and extreme masks. RePaint outperforms state-of-the-art Autoregressive, and GAN approaches for at least five out of six mask distributions. GitHub Repository: this http URL.

The original implementation can be found at andreas128/RePaint.


class diffusers.RePaintScheduler

< >

( num_train_timesteps: int = 1000 beta_start: float = 0.0001 beta_end: float = 0.02 beta_schedule: str = 'linear' eta: float = 0.0 trained_betas: Optional = None clip_sample: bool = True )


  • num_train_timesteps (int, defaults to 1000) — The number of diffusion steps to train the model.
  • beta_start (float, defaults to 0.0001) — The starting beta value of inference.
  • beta_end (float, defaults to 0.02) — The final beta value.
  • beta_schedule (str, defaults to "linear") — The beta schedule, a mapping from a beta range to a sequence of betas for stepping the model. Choose from linear, scaled_linear, squaredcos_cap_v2, or sigmoid.
  • eta (float) — The weight of noise for added noise in diffusion step. If its value is between 0.0 and 1.0 it corresponds to the DDIM scheduler, and if its value is between -0.0 and 1.0 it corresponds to the DDPM scheduler.
  • trained_betas (np.ndarray, optional) — Pass an array of betas directly to the constructor to bypass beta_start and beta_end.
  • clip_sample (bool, defaults to True) — Clip the predicted sample between -1 and 1 for numerical stability.

RePaintScheduler is a scheduler for DDPM inpainting inside a given mask.

This model inherits from SchedulerMixin and ConfigMixin. Check the superclass documentation for the generic methods the library implements for all schedulers such as loading and saving.


< >

( sample: Tensor timestep: Optional = None ) torch.Tensor


  • sample (torch.Tensor) — The input sample.
  • timestep (int, optional) — The current timestep in the diffusion chain.



A scaled input sample.

Ensures interchangeability with schedulers that need to scale the denoising model input depending on the current timestep.


< >

( num_inference_steps: int jump_length: int = 10 jump_n_sample: int = 10 device: Union = None )


  • num_inference_steps (int) — The number of diffusion steps used when generating samples with a pre-trained model. If used, timesteps must be None.
  • jump_length (int, defaults to 10) — The number of steps taken forward in time before going backward in time for a single jump (“j” in RePaint paper). Take a look at Figure 9 and 10 in the paper.
  • jump_n_sample (int, defaults to 10) — The number of times to make a forward time jump for a given chosen time sample. Take a look at Figure 9 and 10 in the paper.
  • device (str or torch.device, optional) — The device to which the timesteps should be moved to. If None, the timesteps are not moved.

Sets the discrete timesteps used for the diffusion chain (to be run before inference).


< >

( model_output: Tensor timestep: int sample: Tensor original_image: Tensor mask: Tensor generator: Optional = None return_dict: bool = True ) RePaintSchedulerOutput or tuple


  • model_output (torch.Tensor) — The direct output from learned diffusion model.
  • timestep (int) — The current discrete timestep in the diffusion chain.
  • sample (torch.Tensor) — A current instance of a sample created by the diffusion process.
  • original_image (torch.Tensor) — The original image to inpaint on.
  • mask (torch.Tensor) — The mask where a value of 0.0 indicates which part of the original image to inpaint.
  • generator (torch.Generator, optional) — A random number generator.
  • return_dict (bool, optional, defaults to True) — Whether or not to return a RePaintSchedulerOutput or tuple.


RePaintSchedulerOutput or tuple

If return_dict is True, RePaintSchedulerOutput is returned, otherwise a tuple is returned where the first element is the sample tensor.

Predict the sample from the previous timestep by reversing the SDE. This function propagates the diffusion process from the learned model outputs (most often the predicted noise).


class diffusers.schedulers.scheduling_repaint.RePaintSchedulerOutput

< >

( prev_sample: Tensor pred_original_sample: Tensor )


  • prev_sample (torch.Tensor of shape (batch_size, num_channels, height, width) for images) — Computed sample (x_{t-1}) of previous timestep. prev_sample should be used as next model input in the denoising loop.
  • pred_original_sample (torch.Tensor of shape (batch_size, num_channels, height, width) for images) — The predicted denoised sample (x_{0}) based on the model output from the current timestep. pred_original_sample can be used to preview progress or for guidance.

Output class for the scheduler’s step function output.

< > Update on GitHub