Metas AI journey would inevitably take it into the budding realm of AI video.
Movie Gen can create audio, making itthe most capable deep fake generator weve seen yet.
Everybodys getting in on the AI-generated video space.
Meta’s Movie Gen videos also incorporate a small watermark, though it doesn’t matter currently since you can’t use it.© Screenshot: Meta
Already this year,Microsofts VASA-1andOpenAIs Sorapromised realistic videos generated from simple text prompts.
Despite being teased back in February, Sora has yet to see the light of day.
The video editing suite seems especially novel.
Meta says it used the prompt: “A fluffy koala bear surfs. It has a grey and white coat and a round nose. The surfboard is yellow. The koala bear is holding onto the surfboard with its paws. The koala bear’s facial expression is focused. The sun is shining.” © Gif: Meta
It works on generated video as well as real-world captures.
Meta showed how you could also take pictures of people and drop them into generated movies.
The audio generator is currently limited to 45 seconds, so it wont score entire movies.
At least, it wont be just yet.
And no, sorry, you cant use it yet.
In itswhitepaperdiscussing Movie Gen, Meta said the whole software suite is made up of multiple foundation models.
The audio generator is a 13B parameter foundation model that can do both video-to-audio and text-to-audio.
In all likelihood, some part of the data set hascome from Facebook users videos.
Meta also uses the photos you take with theMeta Ray-Bansmart glasses to train its AI models.
You cant use Movie Gen yet.
Independent darling A24 has recentlyworked with VC firmsspecializing in AI, with some tied to OpenAI.
News from the future, delivered to your present.
Meta Pissed Off Everyone With Poorly Redacted Docs
Meta is being very transparent on accident.
Elon Musk and Jack Dorsey, too.
