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.

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

Uses the CLIP transformer encoder for text (from huggingface)

Pre-trained network with all channels equally weighted by default

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

A named tuple describing a ResNet block.

Uses the CLIP image encoder. Not actually frozen... If you want that set cond_stage_trainable=False in cfg

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

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

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

returns a pair of (image, caption)

Calculate pairwise distances between vectors. Adapted from https://github.com/kynkaat/improved-precision-and-recall-metric/blob/f60f25e5ad93

Uses the T5 transformer encoder for text

to match AttnBlock usage

A helper for comparing manifolds of feature vectors. Adapted from https://github.com/kynkaat/improved-precision-and-recall-metric/blob/f60f2

A module which performs QKV attention. Matches legacy QKVAttention + input/ouput heads shaping

Computes and stores the average and current value

Uses the BERT tokenizr model and add some transformer encoder layers

Uses the CLIP image encoder.

needed for (image, caption, segmentation) pairs

returns a pair of (image, caption)

returns a pair of (image, caption)

returns a pair of (image, caption)

The half UNet model with attention and timestep embedding. For usage, see UNet.