Meta launched generative AI video editing across its Meta AI app, Meta.AI website, and the Edits app. Users can now transform short videos with preset AI prompts that change outfits, locations, styles, and more. The feature is live in the US and over a dozen other countries.
The AI tool is based on Meta’s Movie Gen models. Full text-prompt video editing is coming later this year. Right now, users upload videos and pick from 50+ preset prompts to edit up to 10 seconds for free temporarily.
Prompts let you turn footage into vintage comic book illustrations, video games with neon battle gear, or dreamy sparkly moods. Edited videos can be shared directly to Facebook, Instagram, or Meta’s Discover feed. 
The feature targets creators and casual users alike, aiming to simplify video edits and boost creative experimentation.
“We built this feature so that everyone can experiment creatively and make fun, interesting videos to share with their friends, family and followers. Whether you’re reimagining a favorite family memory or finding new ways to entertain your audience, our video editing feature can help. We also think it can transform the way creators make content on our platforms, so we worked with creators to understand which prompts would appeal to their audiences, and because our video editing feature is built into the Edits app, it can become a seamless part of the creative process.”
Meta’s generative AI timeline stretches back to 2022 with Make-A-Scene models for images, audio, video, and 3D animation. Diffusion-based Llama Image models improved quality across formats. Last year, Movie Gen combined these to generate and edit videos from text inputs.
“Now, we’re using this research to bring our first generative AI video editing feature to market, so you can express yourself through video, connect with others and bring your best ideas to life.”
