DALL-E can now help you imagine what’s outside the frame of famous paintings

A new function has been added to the DALL-E model that lets the system generate new visuals that expand the borders of any picture.

You can see how DALL-E, with the help of human prompting, "Imagines" what's outside the frame of Johannes Vermeer's portrait "Girl with a Pearl Earring." The system is able to mimic the shadows and highlights of the original by using limited information provided by the portrait.

You can see how the artist had to expand the image in small sections at a time in order to get the result she wanted. The fact that the system isn't generating these extensions alone is worth highlighting. Humans are required to describe the new images.

Many DALL-E users have been playing with the feature to see what lies outside the frames of famous images. For my favorite example, scroll down to the bottom.

Outpainting doesn't really expand the basic functions of text-to-image artificial intelligence systems, but it does show how OpenAI will likely position itself in the market for these systems by making user experience a key selling point.

Like DALL-E prior to this update, many text-to-image models require a lot of manual fiddling. DALL-E will be able to differentiate itself from the growing competition of smaller but comparable systems by making out painting easy.

More than a million people are currently given access to the DALL-E website. 50 free image generations are given to each user in the first month. 115 additional image generations can be purchased for 15 dollars.

Out painting can be used to answer some of life's greatest mysteries, such as "what if the Quaker Oats guy was a busty barmaid?" It's no longer Wonder no more.