A single linear layer which does a 1x1 conv

A logging filter to add color to certain log levels.

r"""Creates a criterion that measures Learned Perceptual Image Patch Similarity (LPIPS). Arguments: net_type (str): the network type

to match AttnBlock usage

Defines a PatchGAN discriminator as in Pix2Pix --> see https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/blob/master/models/networks.py

r""" A conditional 2D UNet model that takes a noisy sample, conditional state, and a timestep and returns a sample shaped output. This mo

The output of [`UNet2DConditionModel`]. Args: sample (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):

Implements a pytorch variant of Adan Adan was proposed in Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep M