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

Photos, movies, animation, recorded music, computer games, CGI props in movies, CGI characters in movies were all denounced as "not real art", until good counter-examples appeared.

AI is but a tool; if there is an artist using them, real art can be created, as with any other tool.

Photos initially captured poorly but were still more affordable than paying a master painter, animation give life to static images, recordings allow listeners to play music without the need to attend, CGI makes for cheaper or infeasible reproductions. For all the cases where technology was adopted, it improved over what we had.

So far, Ai generated videos, and arguably photos seem to only please wishful thinkers, or untalented artists dreaming to make it.

I don't imply the tech will never get to the tipping point, but it so far provides so little value we are either many years to go, or it just won't happen.

Let's be an optimist. It will eventually get there. I doubt for any of parallels you made billions of people hammered daily by overblown posts about the upcoming revolution.

The reasons for critiques have a lot to do with promotion fatigue. Hyperboles eventually exhaust their impact.