AI Foundationspredict · compress · act

concepts → Architecture

Architecture

Diffusion transformer

also called DiT

frontieras of 2026-092 connections

a transformer as the image denoiser, usually trained with flow matching

Where it sits

The prism has six jobs across and eight layers down. Its primary cell isrepresent × L1. Hatched cells cannot exist — a GPU does not learn, an institution does not infer.

What must come first — and what it unlocks

Left to right is reading order, derived from the prerequisite_of edges. Nothing here is hand-ordered: the diagram is the graph.

nothing comes first — this is a starting pointDiffusion transformernothing depends on it yet — a leaf in the reading order

Where to read it

The chapter that introduces it, and any chapter that uses it again.

53Image Modelsact 11 · Beyond Text

Where it comes from

paperScalable Diffusion Models with TransformersWilliam Peebles, Saining Xie · 2023

Every connection

All 2 edges touching this node, grouped by relation family — the sections above are highlights from this list. Colours match the relation families inthe atlas.

Flow · 1
usesTransformerArchitecture
Lineage · 1
improves onDiffusion modelArchitecture

This page is a projection of one node in src/data/concepts.ts. It has no prose file of its own — 230 declared edges produce all 236 of these pages. Edit an edge and both endpoints change.