Skip to content
TL;DR
Run the diffusion denoising process in the compressed latent space of a pretrained autoencoder instead of in pixel space. Cuts compute by an order of magnitude and enables text-to-image at home.
BACKLOG · WORK IN PROGRESS

This paper is being written.

The metadata and shape of this page are stable, but the body content isn't ready yet. We'll publish it once it meets the bar of teaching something new with worked examples and real tools.