Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

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

github.com

Post reply on HN
Print view View original

21–30 of 122 posts

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

#21

Post by hadlock »

ivape wrote: post #10
amelius wrote: post #8

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.

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

#24

Post by roarcher »

jonwinstanley wrote: post #19
roarcher wrote: post #14

Earlier quoted context omitted.

Never. I've seen people instantly go from liking a static image to disliking it upon learning it was AI generated. The same applies to other kinds of media. No matter how "good" it is, knowing that it was created by an unfeeling algorithm ruins it for most people.

This is defo true until the moment it gets so good people can't tell.

Gonna be pretty hard to pass off a whole movie as real when none of the "actors" exist.

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

#25

Post by jonplackett »

roarcher wrote: post #14
amelius wrote: post #8

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

Never. I've seen people instantly go from liking a static image to disliking it upon learning it was AI generated. The same applies to other kinds of media. No matter how "good" it is, knowing that it was created by an unfeeling algorithm ruins it for most people.

I read a while ago that big scientific ideas take about 50 years to be accepted. Which basically means they are never accepted. The people who disagree just get old and die.

Younger generation who grow up with AI will just think it’s normal, like we think being connected to the internet via a rectangle you keep in your pocket is normal.

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

#27

Post by alexpotato »

christophilus wrote: post #12
marstall wrote: post #3

mindblowing - but still in the uncanny valley. and I guess it's cute that many of the characters live in a world where AI has caused an apocolypse, but is that really the message they want to lead with?

To be fair, a lot of movies in theaters have uncanny valleys. A lot of CGI feels that way to me.

The limits of CGI have gotten so good that if you are noticing the CGI, it's b/c someone skimped on the budget for the particular movie where you saw the uncanny valley.

(Of course, excluding the obvious "that guy just knocked down a building!" CGI)

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

#28

Post by jayd16 »

ivape wrote: post #10
amelius wrote: post #8

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.

People can daydream for free now.

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

#29

Post by roarcher »

danielbln wrote: post #18
roarcher wrote: post #14

Earlier quoted context omitted.

Never. I've seen people instantly go from liking a static image to disliking it upon learning it was AI generated. The same applies to other kinds of media. No matter how "good" it is, knowing that it was created by an unfeeling algorithm ruins it for most people.

Never is a long time. The resistance will erode.

"People will like AI movies because it's inevitable"

Circular reasoning. If you can't answer WHY people should come to like AI movies, then you have nothing to say.

Post reply on HN