Concept
Diffusion Transformer (DiT)
A Diffusion Transformer (DiT) is a diffusion model that uses a transformer, rather than the usual convolutional U-Net, as the network that predicts the denoising step. It was introduced by Peebles and Xie (2023) for image generation, and the recipe carries over to any domain…
The rest of “Diffusion Transformer (DiT)” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.
Log in to unlock→