Subscribe now

Technology

Showing AI just 1000 extra images reduced AI-generated stereotypes

Researchers made an AI image generator produce less offensive images by feeding it a tiny amount of additional training data

By Chris Stokel-Walker

2 April 2024

Stable Diffusion is an AI image generator

T. Schneider/Shutterstock

AI image generators can be made more culturally sensitive and accurate by feeding them just a small number of photographs provided by people living in countries around the world.

The images used to train these artificial intelligence systems “are mostly about the Western world”, says Jean Oh at Carnegie Mellon University in Pennsylvania. As a result of this kind of limited training, generative AI image creators, such as Stable Diffusion, often misrepresent or stereotype non-Western cultures.

Sign up to our weekly newsletter

Receive a weekly dose of discovery in your inbox! We'll also keep you up to date with New Scientist events and special offers.

Sign up

To continue reading, subscribe today with our introductory offers

View introductory offers

No commitment, cancel anytime*

Offer ends 2nd of July 2024.

*Cancel anytime within 14 days of payment to receive a refund on unserved issues.

Inclusive of applicable taxes (VAT)

or

Existing subscribers

Sign in to your account