How AI can turn your home video into a Hollywood blockbuster

Want to star in an animated film as an anthropomorphic animal version of yourself? Runway’s AI video creation platform has a new AI tool to do just that. The new Act-One feature may make motion-capture suits and manual computer animation unnecessary to match live action.

Act-One streamlines what is usually a long process for facial animation. All you need is a video camera facing an actor and able to capture their face as they perform.

The AI fueling Act-One reworks the facial movements and expressions from the inputted video to fit an animated character. Runway claims even the most nuanced emotions are visible through micro-expressions, eyeliners, and other facets of the performance. Act-One can even produce multi-character dialogue scenes, which Runway suggests are difficult for most generative AI video models.

To produce one, a single actor performs multiple roles, and the AI animates the different performances mapped onto different characters in one scene as though they are talking to each other.

That’s a far cry from the laborious traditional animation requirements and makes animation far more accessible to creators with limited budgets or technical experience. Not that it’s always going to match the skills of talented teams of animators with big movie budgets, but the relatively low barrier of entry might let amateurs and those with limited resources have the chance to play with character designs that are still realistic in portraying emotions, all without breaking the bank or missing deadlines. You can see some demonstrations below.

Animated Runway

Act-One is, in some ways, an enhancement for Runway’s video-to-video feature within its Gen-3 Alpha model. But while…