RESEARCH PAPERYear 2022

High-Resolution Image Synthesis With Latent Diffusion Models

Robin Rombach; Andreas Blattmann; Dominik Lorenz; Patrick Esser; Björn Ommer

Classification

View four quadrants
Major category
Components of WAMs
Architecture
Not applicable
Prediction paradigm
Not applicable
Source review status
Verified from primary sources

Category review. Latent Diffusion provides the learned perceptual autoencoder plus conditional latent-denoising architecture that later video backbones reuse. The spatial encoder/decoder and conditioned latent generator are concrete representation/backbone building blocks, distinct from downstream WAM systems. Reading evidence

AT A GLANCE

Contribution

A contribution summary has not been added yet.

Abstract

An abstract has not been added yet.

Affiliations

Not listed in the collection.

BibTeX