r""" Instantiate a PyTorch diffusion pipeline from pretrained pipeline weights. The pipeline is set in evaluation mode (`model.eval()

r""" Returns: `torch.device`: The torch device on which the pipeline is located.

r""" Performs Pipeline dtype and/or device conversion. A torch.dtype and torch.device are inferred from the arguments of `self.to(*arg

Create a 1D, 2D, or 3D convolution module.

r""" Returns: `torch.device`: The torch device on which the pipeline is located.

Make a standard normalization layer. :param channels: number of input channels. :return: an nn.Module for normalization.

r""" Returns: `torch.device`: The torch device on which the pipeline is located.

r""" Offloads all models to CPU using accelerate, reducing memory usage with a low impact on performance. Compared to `enable_sequenti

Create a linear module.

Imagenet Superresolution Dataloader Performs following ops in order: 1. crops a crop of size s from image either as random o

:param x: img of size (bs, c, h, w) :return: n img crops of size (n, bs, c, kernel_size[0], kernel_size[1])

Zero out the parameters of a module and return it.

Unwraps a model.

Perform backward process given list of time steps. Args: latents: Latents at time timesteps[0].

Evaluate a function without caching intermediate activations, allowing for reduced memory at the expense of extra compute in the backward pas