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

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

Transformer block for image-like data in temporal axis. First, reshape to b, t, d. Then apply standard transformer action. Finally, r

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

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

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

https://github.com/evelinehong/Transformer_Relative_Position_PyTorch/blob/master/relative_position.py

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

Uses the CLIP transformer encoder for text (from huggingface)

Uses the T5 transformer encoder for text

to match AttnBlock usage

to match AttnBlock usage

Uses xformers efficient implementation, see https://github.com/MatthieuTPHR/diffusers/blob/d80b531ff8060ec1ea982b65a1b8df70f73aa67c/src/diffu

Uses xformers efficient implementation, see https://github.com/MatthieuTPHR/diffusers/blob/d80b531ff8060ec1ea982b65a1b8df70f73aa67c/src/diffu

Transformer block for image-like data in temporal axis. First, reshape to b, t, d. Then apply standard transformer action. Finally, r

Uses the OpenCLIP transformer encoder for text

Uses the OpenCLIP vision transformer encoder for images

Uses the OpenCLIP vision transformer encoder for images

Projection Model

main class

Adapted from modelscope: https://github.com/modelscope/modelscope/blob/master/modelscope/models/multi_modal/video_synthesis/unet_sd.py

Transformer block for image-like data in temporal axis. First, reshape to b, t, d. Then apply standard transformer action. Finally, r

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

Adapted from modelscope: https://github.com/modelscope/modelscope/blob/master/modelscope/models/multi_modal/video_synthesis/unet_sd.py

Adapted from modelscope: https://github.com/modelscope/modelscope/blob/master/modelscope/models/multi_modal/video_synthesis/unet_sd.py

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

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

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