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

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

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

Normlize image by given mean and std.

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

Feature fusion block.

Interpolation module.

Prepare sample for usage as network input.

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).

Uses the CLIP transformer encoder for text (from huggingface)

Uses the T5 transformer encoder for text

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

Network for monocular depth estimation.

Network for monocular depth estimation.

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

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

r"""Collects the scalars broadcasted by `report()` and `report0()` and computes their long-term averages (mean and standard deviation) over us