Diffusion model with a Transformer backbone. DiT_XL_2(**kwargs): DiT(depth=28, hidden_size=1152, patch_size=2, num_heads=16, **kwargs)

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

The final layer of DiT.

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

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