How physics can improve image-generating AI

T ODAY’S BEST image-generating artificial-intelligence (AI) models are remarkable. Ask OpenAI’s DALL-E 3, or its counterparts Midjourney and Stable Diffusion, to draw a penguin sipping on a vodka martini on the French Riviera and they will do so with aplomb. Ask them to replicate it in the style of Rembrandt or Caravaggio and they will speedily oblige.

These abilities all depend on a family of physics-inspired algorithms known as diffusion models. For now, they reign supreme. But that may not always be the case. A team of physicists and computer scientists at the Massachusetts Institute of Technology (MIT) has been taking inspiration from the laws of nature to come up with a series of increasingly sophisticated algorithms that can generate higher-quality images faster, and with smaller training data sets, than diffusion models.

This article appeared in the Science & technology section of the print edition under the headline “Painting by numbers”

Discover stories from this section and more in the list of contents

They can also stop it from happening

Dark energy could break it apart

More rigorous experiments could improve those odds

They can also stop it from happening

Dark energy could break it apart

More rigorous experiments could improve those odds

Practise with an augmented-reality headset

From plant biology to superconductor physics the country is at the cutting edge

And anthropoexceptionalism takes another tumble

A source: www.economist.com/science-and-technology/2024/06/20/how-physics-can-improve-image-generating-ai