The new and improved version of the AI comes with improved capabilities, greater comprehension, and can generate images in higher resolution.
Back in January 2021, OpenAI introduced DALL-E, a cool neural networks-powered tool capable of creating any image from text input. Now, a year after the release of the tool, the team introduced DALL-E 2, a new and improved system that can generate more realistic and accurate images with better resolution.
Much like its predecessor, the new AI system can create realistic images and art from a description in natural language. Thanks to the improvements to the tool's comprehension, DALL-E 2 is capable of creating concepts, attributes, and styles that were never seen before and/or impossible to see IRL. What's more, DALL-E 2 can make realistic edits to existing images from a natural language caption. It can add and remove elements while taking shadows, reflections, and textures into account.
"DALL-E 2 has learned the relationship between images and the text used to describe them. 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," comments the team.