Today, we’re launching a generative AI video editing feature across the Meta AI app, the Meta.AI website and the Edits app to help you bring your creative ideas to life. You’ll now be able to easily edit your short-form videos using a variety of preset AI prompts that can transform your outfit, location, style and more. It’s available in the US and more than a dozen countries around the world
Inspired by our Movie Gen models, this new feature is just the first step toward our goal of bringing you AI video generation and editing across our apps and products. Later this year, you’ll be able to edit videos alongside Meta AI with your own text prompts to make your video edits exactly as you imagine them.
Video Editing for Everyone
Our new AI video editing feature is intuitive and easy to use, so anyone can make high-quality video edits without video-editing expertise. First, upload a video to the Meta AI app, the Meta.AI website or Edits app. Then, explore more than 50 editing prompts you can use to transform 10 seconds of your video for free for a limited time.
Once you’ve chosen a preset prompt, Meta AI will edit your video to match the selected scenario. You can turn your video into a graphic novel, and see yourself reimagined as a vintage comic book illustration. Or change the lighting of a video you captured on a rainy Seattle day to create a dreamy mood with shimmery sparkles, pearlescent blur and soft focus. Or you can turn your video into a video game, complete with fluorescent lighting and battle clothing.
From Edits and the Meta AI app, you can share your edited videos directly to Facebook and Instagram. In the Meta AI app and Meta.AI web, you can share your edited videos directly to the Discover feed.
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 Journey to AI Media Generation
Today’s launch is a result of our continued effort to push AI video generation forward by conducting and sharing essential AI research. In 2022, we created the Make-A-Scene models, which enabled the creation of image, audio, video and 3D animation. Then, with the advent of diffusion models, we were able to create the Llama Image foundation models, allowing for the generation of higher quality images and videos, and instruction-based image and video editing. Last year, we combined all of these modalities to create Movie Gen, a model that can produce custom videos and sounds, and edit existing videos based on simple 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.
