Conv Layer used in StyleGAN2 Discriminator. Args: in_channels (int): Channel number of the input. out_channels (int): Channel num

Equalized Linear as StyleGAN2. Args: in_channels (int): Channel number of the input. out_channels (int): Channel number of the ou

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

The model can behave as an encoder (with only self-attention) as well as a decoder, in which case a layer of cross-attention is added between

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

A noise sampler backed by a torchsde.BrownianTree. Args: x (Tensor): The tensor whose shape, device and dtype to use to generate

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks). From: https://github.com/huggingface/pytorch-image-model

Scaled LeakyReLU. Args: negative_slope (float): Negative slope. Default: 0.2.

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

Equalized Linear as StyleGAN2. Args: in_channels (int): Size of each sample. out_channels (int): Size of each output sample.

Subclass torch's LayerNorm to handle fp16.

Conv Layer used in StyleGAN2 Discriminator. Args: in_channels (int): Channel number of the input. out_channels (int): Channel numb

r"""Image to Patch Embedding Args: img_size (int): Image size. Default: 224. patch_size (int): Patch token size. Default: 4.

Residual block recommended in: http://torch.ch/blog/2016/02/04/resnets.html

Residual Dense Block style: 5 convs The core module of paper: (Residual Dense Network for Image Super-Resolution, CVPR 18) Modified o

Transformer block for image-like data. First, project the input (aka embedding) and reshape to b, t, d. Then apply standard transform

Style conv. Args: in_channels (int): Channel number of the input. out_channels (int): Channel number of the output. kerne

Style conv. Args: in_channels (int): Channel number of the input. out_channels (int): Channel number of the output. kernel

Style conv used in StyleGAN2. Args: in_channels (int): Channel number of the input. out_channels (int): Channel number of the outp

Upsample, FIR filter, and downsample (smooth version). Args: resample_kernel (list[int]): A list indicating the 1D resample kernel

Upsample module. Args: scale (int): Scale factor. Supported scales: 2^n and 3. num_feat (int): Channel number of intermediate fea

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

A wrapper around torchsde.BrownianTree that enables batches of entropy.

Convolutional upsampling layer. It uses bilinear upsampler + Conv. Args: in_channels (int): Channel number of the input. out_chann

DPM-Solver. See https://arxiv.org/abs/2206.00927.

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

Equalized Linear as StyleGAN2. Args: in_channels (int): Size of each sample. out_channels (int): Size of each output sample.

Modulated Conv2d used in StyleGAN2. There is no bias in ModulatedConv2d. Args: in_channels (int): Channel number of the input.

Modulated Conv2d used in StyleGAN2. There is no bias in ModulatedConv2d. Args: in_channels (int): Channel number of the input.

Modulated Conv2d used in StyleGAN2. There is no bias in ModulatedConv2d. Args: in_channels (int): Channel number of the input.

r"""Image to Patch Embedding Args: img_size (int): Image size. Default: 224. patch_size (int): Patch token size. Default: 4.

r"""Image to Patch Embedding Args: img_size (int): Image size. Default: 224. patch_size (int): Patch token size. Default: 4.

r"""Image to Patch Unembedding Args: img_size (int): Image size. Default: 224. patch_size (int): Patch token size. Default: 4.

r"""Image to Patch Unembedding Args: img_size (int): Image size. Default: 224. patch_size (int): Patch token size. Default: 4.

r"""Image to Patch Unembedding Args: img_size (int): Image size. Default: 224. patch_size (int): Patch token size. Default: 4.

Residual Swin Transformer Block (RSTB). Args: dim (int): Number of input channels. input_resolution (tuple[int]): Input resolutio

Residual block with bilinear upsampling/downsampling. Args: in_channels (int): Channel number of the input. out_channels (int): Ch

Residual block with upsampling. Args: in_channels (int): Channel number of the input. out_channels (int): Channel number of the ou

To RGB from features. Args: in_channels (int): Channel number of input. num_style_feat (int): Channel number of style features.

To RGB from features. Args: in_channels (int): Channel number of input. num_style_feat (int): Channel number of style features.

To RGB (image space) from features. Args: in_channels (int): Channel number of input. num_style_feat (int): Channel number of styl

Vision Transformer A PyTorch impl of : `An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale` - https://arxiv.org/