OpenAI's new DALL-E model turns your words into photorealistic images
The San Francisco-based AI research lab OpenAI has unveiled the second version of DALL-E, its AI-powered text-to-image generator that can create photorealistic art pieces based on simple text descriptions.
- Introduced first in January 2021 by OpenAI, DALL-E is a portmanteau of the names of Spanish surrealist artist Salvador Dalí and Pixar’s WALL-E.
- The second version is much faster than the first, and it can produce higher resolution images as well as edit existing photos.
- While it is not currently available to the general public, researchers can sign up for a preview today, and OpenAI plans to make it available to third-party developers via an API at a later date. DALL-E has the potential to become a game-changer, especially for graphic designers and app developers.
The neural network produces some remarkable results already and is bound to get better. For example, OpenAI employee Aris Konstantinidis used DALL-E to create artwork of “bandana-wearing pandas riding motorcycles in the desert.”
Other times I just want to ride in the desert with my panda motorcycle crew. If you see a bunch of pandas wearing red bandanas, that's us! Say hello :)
— Aris Konstantinidis (@ariskonstant) April 6, 2022
Generated with DALL-E 2. #dalle #openai pic.twitter.com/UdW0U8WSzt