Microsoft creates AI that draws a picture based on text input

Microsoft researchers published a paper about a new AI agent they call the drawing bot. The algorithm draws images pixel by pixel, based on nothing more than the text input of a user. Basically, you tell this thing to draw a bird, specify the color and some other aspects and the drawing bot will generate an image from scratch. It is the most advanced text-to-image system currently in existence.

The new artificial intelligence technology under development in Microsoft’s research labs is programmed to pay close attention to individual words when generating images from caption-like text descriptions. This deliberate focus produced a nearly three-fold boost in image quality compared to the previous state-of-the-art technique for text-to-image generation, according to results on an industry standard test reported in a research paper posted on arXiv.org.

The technology, which the researchers simply call the drawing bot, can generate images of everything from ordinary pastoral scenes, such as grazing livestock, to the absurd, such as a floating double-decker bus. Each image contains details that are absent from the text descriptions, indicating that this artificial intelligence contains an artificial imagination.

Pretty interesting stuff, you can learn more at the Microsoft Blog.