A residual block that can optionally change the number of channels. :param channels: the number of input channels. :param emb_channels:

A sequential module that passes timestep embeddings to the children that support it as an extra input.

An attention block that allows spatial positions to attend to each other. Originally ported from here, but adapted to the N-d case. http

A downsampling layer with an optional convolution. :param channels: channels in the inputs and outputs. :param use_conv: a bool determin

An upsampling layer with an optional convolution. :param channels: channels in the inputs and outputs. :param use_conv: a bool determini

A module which performs QKV attention and splits in a different order.

Adapted from CLIP: https://github.com/openai/CLIP/blob/main/clip/model.py

A module which performs QKV attention. Matches legacy QKVAttention + input/ouput heads shaping

The full UNet model with attention and timestep embedding. :param in_channels: channels in the input Tensor. :param model_channels: base

The half UNet model with attention and timestep embedding. For usage, see UNet.

Define different GAN objectives. The GANLoss class abstracts away the need to create the target label tensor that has the same size as the in

This operator get pre-defined mask and return masked image.

Predict x_start and calculate mean value

A diffusion process which can skip steps in a base diffusion process. :param use_timesteps: a collection (sequence or set) of timesteps from

A UNetModel that performs super-resolution. Expects an extra kwarg `low_res` to condition on a low-resolution image.

Any module where forward() takes timestep embeddings as a second argument.