Thomas is a writer at TNW. He covers the full spectrum of European tech, with a particular focus on deeptech, startups, and government polic Thomas is a writer at TNW. He covers the full spectrum of European tech, with a particular focus on deeptech, startups, and government policy.
Google has released a prototype AI app that turns your sketches into fantastical monsters — with varying degrees of success.
The Big G developed the Chimera Painter to produce an endless stream of creatures for a fantasy card game in which the different monsters battle.
The system is powered by generative adversarial networks (GANs), which create new content by pitting two neural networks against each other: a generator that creates new images and a discriminator that attempts to identify which of the designs have been artificially created.
The tool’s creators trained the GANs on thousands of computer-generated creature images, each of which was paired with a “segmentation map” showing its body parts.
[Read: Neural’s market outlook for artificial intelligence in 2021 and beyond]
This enabled the model to generate new monsters from new drawings of different body parts.
You can try the tool out for yourself by heading to the Chimera Painter website. You can use it to customize the pre-loaded designs, import your own images, or generate new ones in the app, as I did to create this beautiful flying rabbit:
“It is our hope that these GAN models and the Chimera Painter demonstration tool might inspire others to think differently about their art pipeline,” the app’s creators wrote in a blog post. “What can one create when using machine learning as a paintbrush?”
Not much, if my own appalling efforts are anything to go by. But more talented artists may find more creative value in AI’s brush strokes.
Get the TNW newsletter
Get the most important tech news in your inbox each week.