OpenAI creates Dall-E, an AI that can create art from basic descriptionsLeigh Mc Gowranon April 15, 2022 at 09:55 Silicon RepublicSilicon Republic


Researchers at the AI start-up OpenAI have created a new system that can create realistic images and art from simple word descriptions.

OpenAI said the AI system – named DALL-E – is able to understand the relationship between an image and words used to describe it.

“It uses a process called “diffusion,” which starts with a pattern of random dots and gradually alters that pattern towards an image when it recognizes specific aspects of that image,” OpenAI said in a blog post.

The AI company said it created the first version of DALL-E last year. Its second version was released this year and creates “more realistic and accurate images with 4x greater resolution”.

The website shows various examples of what DALL-E is able to create through simple adjustments in text. Once a description is added, the AI system creates multiple images based on how it interprets the text.

One user shared a batch of images that were created by the AI system on Twitter, including “teddy bears working on new AI research on the moon in the 1980s”.

teddy bears working on new AI research on the moon in the 1980s

— Critter (@BecomingCritter) April 6, 2022

The AI can take an original image and create multiple variations that are inspired by the first. OpenAI said this system can also make realistic edits to existing images from a “natural language caption”, adding or removing specific elements while taking factors such as shadows and textures into account.

In a comparison evaluation in the project’s study, the new version of DALL-E was preferred over the original by almost 89pc in terms of photorealism and around 71pc for caption matching.

Concerns of misuse

While the abilities of Dall-E are impressive, concerns have been raised that this sort of technology could help people spread disinformation online, through the use of authentic looking fake images.

“You could use it for good things, but certainly you could use it for all sorts of other crazy, worrying applications, and that includes deep fakes,” Arizona State University Prof Subbarao Kambhampati told The New York Times.

OpenAI said Dall-E 2 is not available to the public as it is currently testing the limitations and capabilities with select users, to “develop and deploy AI responsibly”.

Some of the safety mitigations OpenAI said it has worked on include preventing offensive images from being created by minimising exposure and adding specific filters to prevent misuse by users.

10 things you need to know direct to your inbox every weekday. Sign up for the Daily Brief, Silicon Republic’s digest of essential sci-tech news.

The post OpenAI creates Dall-E, an AI that can create art from basic descriptions appeared first on Silicon Republic.

Leave a Comment