Meta introduces text-to-video AI tool that creates 16-second clips

Meta, Facebook’s parent company, on Friday unveiled a new artificial intelligence tool that allows users to create 16-second videos based on text prompts. The new tool, called Movie Gen, pits Meta against companies like OpenAI in a battle for text-to-video AI capabilities.

Movie Gen allows users to create clips based on what they type in the text prompt. If you typed “A fluffy gray and white koala bear surfs a yellow board” like Meta gave as an example on his blog, here’s a screenshot of what you would get:

Users can also create images and audio using Movie Gen’s text prompts.

However, if you’re keen to take advantage of Mark Zuckerberg’s new AI feature, you’ll have to wait a bit. According to Bloomberg, Movie Gen is only available to some of the company’s employees and “external partners, including some filmmakers.” Meta plans a full rollout of Movie Gen in 2025, with the feature coming to a few apps including Facebook and Instagram.

The company praised itself for Movie Gen’s realistic images and videos, saying it “outperforms similar models in the industry when rated by humans on these tasks.”

It’s also an increasingly crowded industry. OpenAI’s text-to-video tool Sora can create clips up to 60 seconds long, and Google introduced Veo, its own text-to-video tool, earlier this year. A number of startups are also on this corner, such as Stability AI, a London-based company that added James Cameron to its board just last month.

The filmmaker touted text-to-video tools as the “next wave” of creativity that will “open up new opportunities for artists to tell stories in ways we could never have imagined.”

The post Meta Unveils Text-to-Video AI Tool That Creates 16-Second Clips appeared first on TheWrap.