Meta has unveiled its latest AI research project, Meta Movie Gen, which aims to revolutionize how content creators produce videos, images, and audio using simple text inputs.
The new tool allows users to generate high-quality videos, edit existing ones, and even create personalized content—just by typing in commands. This is essentially Meta’s version of OpenAI’s similar AI video creation service, Sora, which was unveiled earlier this year.
With Movie Gen, a text prompt will be able to generate a video up to 16 seconds long, at 16 fps. You can also create personalized videos based on a picture of someone you provide and result will be centred around that person.
The AI-powered Movie Gen also allows for video editing, such as adding, removing or replacing objects in a video, or by changing the background or style, just with text instructions.
Beyond video, the AI tool can create audio of up to 45 seconds that includes sound effects and background music, all synced up. As for how this works, Meta says Movie Gen involves advanced AI models trained on a mix of licensed and publicly available data.
Right now Movie Gen isn’t available for the public just yet. Meta says the AI tool is in its R&D phase and will continue to be refined based on feedback from filmmakers and creators. But based on the initial sample videos of Movie Gen, it looks to be pretty impressive for a 1.0 reveal.
Want to see more of our stories on Google?
P.S. Want to keep this site truly independent? Support us by buying us a beer, treating us to a coffee, or shopping through Amazon here. Links in this post are affiliate links, so we earn a tiny commission at no charge to you. Thanks for supporting independent Canadian media!
I wonder what the definition of "licensed" and "publicly available" data mean under Meta..
It means they stole most if not all of it.