AI Foundationspredict · compress · act

concepts → Architecture

Architecture

Latent diffusion

timeless2 connectionsdraft

run the diffusion steps in a small squeezed space, then decode back to pixels

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.

Diffusion modelLatent diffusionnothing depends on it yet — a leaf in the reading order

Before it: Diffusion model

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

paperHigh-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, Björn Ommer · 2022

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.

Structure · 1
is an instance ofDiffusion modelArchitecture
Order · 1
requiresDiffusion 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.