DALL-E can now use AI to extend images as a human artist might

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.