Meta has created a generative AI video tool that will allow its users to create and edit video as well as audio based on text prompts. The feature, called Movie Gen and touted by the company in a Friday blog post, can even create video footage from an uploaded photo of someone.
Movie Gen won't be available to Meta's large number of users on platforms such as Facebook and Instagram until next year at the earliest. So far, it's been tested internally and by a small number of filmmakers, the company said. Meta shared a research paper for Movie Gen in which the company says its model will produce high-quality 1080p HD videos with different aspect ratios and synchronized audio.
The video feature is Meta's latest announcement in the AI realm. Facebook users can already generate AI stickers, and the company has said it wants to roll out more AI chatbot features on platforms like Instagram. Meta is even adding AI features to its Ray-Ban smart glasses. But as it moves into AI-generated video, Meta will be competing with companies such as OpenAI and Google, two tech giants that have already debuted AI video models.
Meta touted Movie Gen's features with a series of videos and stills in its blog post. Movie Gen's features include Perzonalized Video, which will take a still photo of a person and create full-motion videos based on that image. Movie Gen will also use text prompts to edit AI videos on the fly; props such as pompons, for instance, could be added to a video with a text request.
In addition to its video features, Movie Gen will also be able to create sound effects and full soundtracks, Meta said.