Meta’s Make-A-Scene Lets Users Turn Ideas and Sketches into Digital Art


meta unveiled new ai research tool

Meta, the group that owns Facebook, Instagram, WhatsApp and other products and services aimed at helping communities and businesses do more together through technology and immersive experiences, has unveiled Make-A-Scene.

Meta’s Make-A-Scene Lets Users Turn Ideas and Sketches into Digital Art

Make-A-Scene is an AI research tool which uses sketches and text to generate digital imagery and artwork.

The Make-A-Scene system utilizes text prompts and input drawings to create new visual interpretations.

Empowering creativity for small business users

In today’s highly competitive, global business environment, creativity is crucial. The growing prominence and sophistication of Artificial Intelligence (AI) is simplifying the creative process. By utilizing AI technology, businesses can produce new creative assets and modify existing ones efficiently and at scale.

From cropping images to frame subjects, to generating better image descriptions, automated software, for example, is being used by many small business users to aid the visual appeal of imagery and make visual assets more accessible.

Text-to-Image Generation

Enabling to create procedurally generated art that is manufactured from both human and computer imaginations, text-to-image generation is an in-demand algorithm process right now.

Following from the likes of Google’s Imagen and OpenAI’s Craiyon, Meta has developed its own AI image generation engine.

Believing it is not enough for an AI system to just generate content, Make-A-Scene takes the potential for users to push creative expression forward by empowering users to build immersive worlds in the metaverse and create high digital art.

Describing the new AI tool as “empowering”, Meta says:

“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. For example, the text input “a painting of a zebra riding a bike” might not reflect exactly what you imagined; the bicycle might be facing sideways, or the zebra could be too large or small.

“With Make-A-Scene, this is no longer the case. It demonstrates how people can use both text and simple drawings to convey their visions with greater specificity using a variety of elements.”

Through ‘exploratory AI research concept,’ aka Make-A-Scene, Meta allows users to combine user-created sketches to text-based image generation. They can also dictate the image’s overall composition.

To develop the technology further, Meta shared its Make-A-Scene demo with several prominent artists. After using the tool, Sophia Crespo, an AI artist, said that with its freeform drawing capabilities, she found she could begin to create quickly across new ideas.

“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 Crespo.

The Make-A-Scene app is not available to the public as yet.

Image: Depositphotos


More in: Comment ▼

Gabrielle Pickard-Whitehead Gabrielle Pickard-Whitehead is a professional freelance writer and journalist based in the United Kingdom. Since 2006, Gabrielle has been writing articles, blogs and news pieces for a diverse range of publications and sites. You can read "Gabrielle’s blog here.".

Comments are closed.