Meta has introduced a groundbreaking generative artificial intelligence model that enables users to create short videos with sound from text prompts and photos. The announcement was made on Friday, showcasing what the tech giant is calling “Meta Movie Gen.”
Meta hailed this development as a significant advancement in the realm of AI, aimed at facilitating video and audio generation. The company plans to gather feedback from filmmakers and creators as it progresses towards making this innovative video-generating AI available to the public, although no specific release date has been provided.
In a post, Meta emphasized that while generative AI offers many exciting possibilities, it should not be seen as a replacement for artists and animators.
According to Meta, the model allows users to generate custom videos of up to 16 seconds long, incorporating clips based on personal photographs through simple text prompts. “Our model achieves state-of-the-art results when it comes to creating personalized videos that preserve human identity and motion,” the company stated.
Imagining potential applications, Meta suggested users could create a “day in the life” video to share on Reels or design a customized animated birthday greeting to send via WhatsApp.
Movie Gen marks the third phase of AI-powered video generation at Meta, highlighting the company’s ongoing efforts in this field. However, the rise of AI-generated tools for crafting realistic videos has raised concerns over the potential misuse of “deepfakes,” which could exploit individuals’ likenesses without consent.