By early 2015, neural networks had mastered the art of 'image-to-text' and could create natural language captions for images. Flipping this process, and turning text into image, was a much more complex challenge. 19-year old prodigy Elman Mansimov's alignDRAW model solved this problem, a breakthrough that marked a new era of human-machine collaboration.

In his seminal paper, ‘Generating Images from Captions with Attention‘, Mansimov led a team of researchers at Toronto University to create a model that didn’t simply pull existing images from databases, like a search engine would, but rather to generate completely unique scenarios that had no parallel in reality. They tested it by requesting it to produce visuals of unheard scenarios, such as “a toilet seat sits open in the grass field” or “a green school bus parked in a parking lot”.