Meta introduces the text-to-video and sound generator “Movie Gen”.

A screenshot of a short video created with Metas Movie Gen, with a watermark at the bottom left | Photo credit: Meta

Meta introduced its text-to-video and sound generator Movie Gen, which uses generative AI to create video clips of up to 16 seconds at a rate of 16 frames per second and high-fidelity audio at up to 45 seconds.

“Using a text prompt, we can leverage a common model optimized for both text-to-image and text-to-video to create high-quality, high-resolution images and videos. This 30B parameter transformer model is capable of producing videos of up to 16 seconds at a rate of 16 frames per second,” Meta said in a blog post.

Some tasks the models can perform include text-to-video synthesis, video personalization, video editing, video-to-audio generation and text-to-audio generation, Meta said in its research report.

Movie Gen allows you to create video clips and edit them using text prompts. In addition to creating and enhancing soundtracks, it can also convert photos of a person into a short video clip. The company released hyper-realistic clips of a baby hippo swimming, a child running across a beach, and a video clip of a man conducting a science experiment in a photo.

Although the technology is not yet widely available, Meta suggested that in the future, its users across all social media platforms would be able to create their own videos or edit their multimedia content before sharing it.

“Through a collaborative approach, we want to ensure we develop tools that help people increase their inherent creativity in ways they may never have thought possible. “Imagine animating a day in the life video to share on Reels and editing it using text prompts, or creating a custom animated birthday greeting for a friend and sending it to them on WhatsApp,” Meta said.

There are still widespread concerns about the potential of AI-powered video generation and its possible impact on individual privacy, artist copyright and child safety.