In Brief
Google's DeepMind team has developed a way for their AI to be able to create images from sentences. The more detailed the sentence, the more detailed the resulting image will be.

The folks at Google’s DeepMind are hard at work bringing the world the latest developments in artificial intelligence (AI). Their latest breakthrough shows that their AI is capable of creating photorealistic pictures from human input in the form of sentences.

This is the latest development in the use of AI to do some truly amazing things with pictures. In February, Google Brain scientists developed a way to “enhance” photographs much like the way you might see in a science fiction movie like Blade Runner or a network procedural like one of the many CSIs. Using PixelCNN, the machine was able to turn low-resolution photos into high-resolution ones with an impressive approximation.

Now that same technology is being used to turn text into pictures. The researchers found that a more detailed prompt would deliver better results than a less detailed one. For example, the prompt of “A yellow bird with a black head, orange eyes, and an orange bill” returned a highly detailed image. The algorithm is able to pull from a collection of images and discern concepts like birds and human faces and create images that are significantly different than the images it “learned” from.