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.

Normlize image by given mean and std.

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 wrapper for CompVis diffusion models.

Can be used in place of safety checker. Use responsibly and at your own risk.

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

An attention block that allows spatial positions to attend to each other. Originally ported from here, but adapted to the N-d case. https

Feature fusion block.

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

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

Feature fusion block.

An attention block that allows spatial positions to attend to each other. Originally ported from here, but adapted to the N-d case. https

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

Interpolation module.

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

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

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

Prepare sample for usage as network input.

A module which performs QKV attention and splits in a different order.

A module which performs QKV attention and splits in a different order.

Residual convolution module.

Residual convolution module.

Resize sample to given size (width, height).

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

Adapted from CLIP: https://github.com/openai/CLIP/blob/main/clip/model.py

Uses a pretrained BERT tokenizer by huggingface. Vocab size: 30522 (?)

Construct the embeddings from word and position embeddings.

Construct the embeddings from word and position embeddings.