DALL-E 2 was the AI art generator we never knew we needed
DALL-E is a system that has been around for years, but its successor, DALL-E 2, was launched this year.
DALL-E and DALL-E 2 are machine-learning models created by OpenAI to produce images from language descriptions. These text-to-image descriptions are known as prompts. The system could generate realistic images just from a description of the scene. DALL-E is a neural network algorithm that creates accurate pictures from short phrases provided by the user. It comprehends language through textual descriptions and from “learning” information provided in its datasets by users and developers.
Text-to-image art creation
DALL-E can be used to generate unique images based on words provided by the creators and artists. DALL- E 2 can do the same, but with upgraded features. It uses the algorithm within the words and places them in a series of vectors or text-to-image descriptions. Then, the AI creates an original image from the generic representation it was presented with from its datasets, based on text added by the user creating the art.
DALL-E was announced in January 2021. In July 2022, DALL-E entered a beta phase, or initial development and testing stage, sending invitations to one million people on its waitlist. In Sept. 2022, OpenAI removed the waitlist for DALL-E, allowing users to sign up for the software immediately.
DALL-E 2 creates images of higher resolution
Although both DALL-E, announced in January 2021, and DALL-E 2, revealed in April this year, are models created by OpenAI, the difference lies in the number of parameters, allowing DALL-E 2 to create even better images than DALL-E. This is done by generating higher-resolution images. DALL-E uses 12-billion parameters, while DALL-E 2 works on 3.5-billion parameters, with an additional 1.5 billion parameters to enhance the resolution.
DALLE-2 creates images of higher resolution, although it uses less parameters than its predecessor. The AI system has also learned the relationship between the pictures and text used to describe them in a process also known as diffusion. In the method, there is usually a pattern of dots that gradually alters itself toward an image when it recognizes aspects of that image.
The system can expand images beyond what’s in the original photo, called outpainting, creating new compositions from old images. It has four times greater resolution than DALL-E.
Additional features in DALL-E 2
DALL-E 2 is an innovative AI system that was released in 2022. It allows users to create original images from text descriptions. It also allows users to expand images beyond the original art composition. Creators have the ability to make edits to existing images, where they can add or remove parts of a picture, while not affecting realistic shadows and textures. DALL-E 2 also lets users create different images using the same concept of the original, but with variations.
The AI-generated art by DALL-E 2 is more detailed than the original DALL-E. It also has additional capabilities, making it innovative and more advanced than its predecessor.
This is number 16 in Interesting Engineering's series showcasing the best innovations of 2022. Check back to discover more about groundbreaking AI, unique solar panels, new 3D printing methods, and much more.
A new study joins the body of research showing that being bilingual, knowing more than one language, slows down the negative effects of aging on the brain.