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

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

Subclass torch's LayerNorm to handle fp16.

Reduce feature maps into a single edge map

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

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

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

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

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

Base class for all image autoencoders that we train, like VQGAN or AutoencoderKL (we also restore them explicitly as special cases for legacy

Compact Dilation Convolution based Module

Compact Spatial Attention Module

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

A DiT block with gated adaptive layer norm (adaLN) conditioning.

from https://github.com/facebookresearch/ConvNeXt-V2/blob/3608f67cc1dae164790c5d0aead7bf2d73d9719b/models/utils.py#L105

r""" A basic Transformer block. Parameters: dim (`int`): The number of channels in the input and output. num_attention_heads

MLP as used in Vision Transformer, MLP-Mixer and related networks

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

The output of [`BrushNetModel`]. Args: up_block_res_samples (`tuple[torch.Tensor]`): A tuple of upsample activations at

The output of [`BrushNetModel`]. Args: up_block_res_samples (`tuple[torch.Tensor]`): A tuple of upsample activations at

The revised embedding layer to support external embeddings. This design of this class is inspired by https://github.com/AUTOMATIC1111/stable-