Diffusion model with a Transformer backbone.

r""" Default processor for performing attention-related computations.

r""" A cross attention layer. Parameters: query_dim (`int`): The number of channels in the query. cross_attention

r""" A feed-forward layer. Parameters: dim (`int`): The number of channels in the input. dim_out (`int`, *optional*): The num

Track a series of values and provide access to smoothed values over a window or the global series average.

A DiT block with adaptive layer norm zero (adaLN-Zero) conditioning.

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

The Transformer model introduced in Flux. Reference: https://blackforestlabs.ai/announcing-black-forest-labs/ Parameters: patch

The final layer of DiT.

Attention processor used typically in processing the SD3-like self-attention projections.

r""" Processor for implementing scaled dot-product attention (enabled by default if you're using PyTorch 2.0).

r""" A Transformer block following the MMDiT architecture, introduced in Stable Diffusion 3. Reference: https://arxiv.org/abs/2403.03206

Utilities for training and sampling diffusion models. Original ported from this codebase: https://github.com/hojonathanho/diffusion/blob/

Embeds class labels into vector representations. Also handles label dropout for classifier-free guidance.

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

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

A diffusion process which can skip steps in a base diffusion process. :param use_timesteps: a collection (sequence or set) of timesteps from

Embeds scalar timesteps into vector representations.

r""" The Flux pipeline for text-to-image generation. Reference: https://blackforestlabs.ai/announcing-black-forest-labs/ Args: t

Which type of output the model predicts.

What is used as the model's output variance. The LEARNED_RANGE option has been added to allow the model to predict values between FIXED_S

A distribution over timesteps in the diffusion process, intended to reduce variance of the objective. By default, samplers perform unbias