Meta announces Movie Gen, an AI video and audio creator

Meta has developed a generative AI video tool that allows its users to create and edit video and audio files based on text input. The feature, called Movie Gen, can even create video footage from a person’s uploaded photo.

Movie Gen won’t be available to the large number of meta users on platforms like Facebook and Instagram until next year at the earliest. The company said it is currently being tested internally and by a small number of filmmakers. Meta has published 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 sound.

The video feature is Meta’s latest announcement in the AI ​​space. Facebook users can already generate AI stickers and the company has announced plans to introduce more AI chatbot features on platforms like Instagram. The company is even adding AI functions to its Ray-Ban smart glasses. But on the path to AI-generated videos, Meta will compete with companies like OpenAI and Google, two tech giants that have already launched AI video models.

The company promoted Movie Gen’s features with a series of videos and still images in its blog post, including “Perzonalized Video,” which takes a still image of a person and creates full-motion videos based on that image. It also uses text prompts to edit AI videos on the fly. In an example used by the company, props such as pom-poms could be added to a video with a text request.

In addition to its video capabilities, Movie Gen will also be able to create sound effects and full soundtracks, Meta said.