Tech giant Meta has announced its new artificial intelligence model, ‘Movie Gen’, for generating realistic video and audio from text prompts.
Competing with OpenAI’s Sora, it will be coming to Instagram next year, giving consumers an easy and straightforward way to generate videos for the platform.
How does Movie Gen work?
In a research paper that explains their new AI model, Meta has clarified that the Movie Gen model has been trained for both text-to-image and text-to-video tasks. When prompted, it will generate several colored images that serve as a frame for the video.
Interestingly, Meta’s new model is not only capable of generating new videos but also of editing existing ones.
Movie Gen can reportedly produce high definition (1080p) of videos of up to 16 seconds at 16 frames per second (FPS). Meta claims that its new model has learned real-world visuals by “watching” videos and will be able to reason about object motion, camera motion, subject-object interaction, and more.
It is also capable of producing corresponding audio using video-to-audio and text-to-audio techniques.
Additionally, Meta’s CEO Mark Zuckerberg shared a video sample created by the AI model where he’s seen doing his leg press sessions in several settings, made possible by their new AI app.
“Every day is leg day with Meta’s new MovieGen AI model that can create and edit videos,” he wrote.
View this post on Instagram
While Meta hasn’t revealed the consumer pricing of the AI model, users will be able to gain more clarity once it’s available.
Download Meta’s research paper for more information here.
Leave feedback about this