Meta's new AI tool can turn text into videos

Meta has developed a tool to use text to create artsy videos.

Facebook's parent company has created a new artificial intelligence (AI) system called Make-A-Video, which is part of the company's work with technology to create new content using text prompts.

In a blog post, the company said: "Make-A-Video builds on Meta AI’s recent progress in

generative technology research and has the potential to open new opportunities for creators and artists.

"The system learns what the world looks like from paired text-image data and how the world moves from video footage with no associated text.

"As part of our continued commitment to open science, we’re sharing details in a research paper and plan to release a demo experience."

Meta explained that "generative AI is pushing creative expression" as pepole get access to tools allowing them to "quickly and easily create new content".

They continued: "With just a few words or lines of text, Make-A-Video can bring imagination to life and create one-of-a-kind videos full of vivid colors, characters, and landscapes.

"The system can also create videos from images or take existing videos and create new ones that are similar."

Meanwhile, Meta noted they are being "thoughtful" when it comes to building "new generative AI systems like this".

They said: "Make-A-Video uses publicly available datasets, which adds an extra level of transparency to the research.

"We are openly sharing this generative AI research and results with the community for their feedback, and will continue to use our

responsible AI framework to refine and evolve our approach to this emerging technology."

It follows projects like OpenAI's Dall-E service which turns text prompts into visual arts, and Google's own AI programme which takes text prompts and turns them into images.

© BANG Media International