Ovi: Twin backbone cross-modal fusion for audio-video generation

How long until we see blockbuster movies produced by a guy in his basement for <$1000?

Soon as the video models can keep characters consistent across scenes. It could take months of prompting to get each scene, but regular movies have long shooting timelines too. If we ever get to instant movie, thought to scene, then movies will die since people will just daydream through the AI.

I can see soap-opera-style, video-manga becoming a thing, where you get 5x20 minute episodes a week, and an ai-generated 30 min super cut of the week's "events" every saturday. What if DragonBallZ, but new episodes drop every morning before your morning commute? And for $30 a month you can do a choose your own adventure where at the end of each episode, the story splits off and you get an alternate history version, but conveniently rejoins the main story by the end of the week.

Three years ago we had a live streaming autogen-seinfeld twitch stream; some kind of coherent story telling via AI doesn't seem beyond reach today, the tools just haven't fully matured yet.