More than a million people are now using the AI image-maker, and many of them asked for a tool extending the aspect ratio of images.
Since it was announced in April, the text-to-image AI tool DALL-E 2 has been wowing artists, researchers, and media types its high-quality images. Now, four months later, developer OpenAI is giving DALL-E 2 a new trick: the ability to extend the original images it creates beyond their original borders in logical and creative ways.
The new feature, which OpenAI calls “outpainting,” could be useful to graphic designers who need to create multiple sizes and shapes of a particular image to present in different contexts. A movie promo image, for instance, might require a perfectly square shape in one context, and a tall rectangular shape in another. For the latter, new art is required to fill in the extra space.
DALL-E 2 creates original 1024 X 1024-pixel images based on a keyword descriptions entered by the user. It can also make images based on objects and styles it sees in other images. For example, it might be given a street art image of a mouse alongside an art deco version, then combine elements of the two styles into an original picture of the rodent. It also has editing capabilities, meaning a user can erase a section of a generated image and then tell DALL-E to add a specific object or style in that area. For instance, if designer doesn’t like the expressionist red roses in the foreground of an image, they can erase them and ask DALL-E to put photorealistic white orchids there instead.
