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.

Log using `Weights and Biases`.

Utilities for training and sampling diffusion models. Ported directly from here, and then adapted over time to further experimentation. h

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

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

Dumps key/value pairs into TensorBoard's numeric format.

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

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

Which type of output the model predicts.

What is used as the model's output variance. The LEARNED_RANGE option has been added to allow the model to predict values between FIXED_S

A distribution over timesteps in the diffusion process, intended to reduce variance of the objective. By default, samplers perform unbia

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

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