Meta, formerly known as Facebook, has developed a new Artificial Intelligence (AI)-based research concept that will let people use text and simple sketches to generate digital imagery.
The concept called ‘Make-A-Scene’ will enable new forms of AI-powered creative expression while putting creators and their visions at the centre of the process, the social media giant wrote in a blogpost.
“Make-A-Scene empowers people to create images using text prompts and freeform sketches. Prior image-generating AI systems typically used text descriptions as input, but the results could be difficult to predict,” Meta said.
The concept demonstrates how people can use both text and simple drawings to convey their visions with greater specificity using a variety of elements.
It also captures the scene layout to enable nuanced sketches as input. It can also generate its own layout with text-only prompts, if that’s what the creator chooses.
The model focuses on learning key aspects of the imagery that are more likely to be important to the creator, like objects or animals.
“As a visual artist, you sometimes just want to be able to create a base composition by hand, to draw a story for the eye to follow, and this allows for just that,” said Sofia Crespo, an AI artist.
Crespo used Make-A-Scene to create new hybrid creatures. Using its freeform drawing capabilities, she found that she could begin to create quickly across new ideas.
“Through projects like Make-A-Scene, we’re continuing to explore how AI can expand creative expression. We’re making progress in this space, but this is just the beginning,” Meta said.
The company said it will continue to push the boundaries of what’s possible using this new class of generative creative tools to build methods for more expressive messaging in 2D, mixed reality and virtual worlds.