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

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

Zero out the parameters of a module and return it.

Create a linear module.

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

Create sinusoidal timestep embeddings. :param timesteps: a 1-D Tensor of N indices, one per batch element. These may be

generate images, then save and log to tensorboard

Rescale `noise_cfg` according to `guidance_rescale`. Based on findings of [Common Diffusion Noise Schedules and Sample Steps are Flawed](http

Zero out the parameters of a module and return it.