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

Make-A-Video: AI system that generates videos from text

makeavideo.studio

Post reply on HN
Print view View original

41–50 of 399 posts

Re: Make-A-Video: AI system that generates videos from text

#41

Post by wslh »

VoodooJuJu wrote: post #12

A lot of people saying it's over for traditional movie-making - lmao. I look at these and see nothing but uncanny valley artifacts, and I don't think it will improve much from here. It's like self-driving cars. They use almost very effective statistical models, certainly better than our previous models, but they never seem to shake off that "almost" and become truly effective.

If this technology (or its future iterations) is not enough you can always combine this with your movie cuts. This lowers the resources/bar needs for creative people and obviously also for the uncreative ones.

Re: Make-A-Video: AI system that generates videos from text

#43

Post by psychomugs »

I'm very interested in what will come out of this new (sub)medium. By virtue of video being a collaborative medium, I never feel like I'm getting a message from a singular consciousness like I do from less resource-intensive mediums like books (I know that book editors exist, but the medium has less filters to pass through compared to large products like movies). I could see this substantively lowering the barrier of entry for video and enabling a lot of new stories to be told.

Re: Make-A-Video: AI system that generates videos from text

#44

Post by Filligree »

londons_explore wrote: post #13
tmjdev wrote: post #3

This looks like the video equivalent of Dall-E 1. Hard to believe how far we've come so quickly. The paper talks about "pseudo 3D attention layers" that are used in place of temporal attention layers for each dimension due to memory consumption. It seems like AI research is vastly outpacing GPU development.

Indeed - it's not hard from a research point of view - it's hard from a compute perspective because adding one more dimension requires hundreds of times more compute. Even then, these videos are only like 50 frames long - and a real movie you would want to be hundreds of thousands of frames long.

So you need to optimise on compressed version, not the whole thing. What they’re doing right now is akin to a human trying to hold an entire picture - or entire movie - in their head all at once.

We can’t do it. AIs can sort of do it.

Latent diffusion models already demonstrated that operating on a compressed representation gives far better results, faster, but I don’t think we’re anywhere near the limit for what’s possible there. It’s no coincidence that this is how humans work.

Re: Make-A-Video: AI system that generates videos from text

#46

Post by Xelynega »

fasteddie31003 wrote: post #4

I'm rooting for this tech. Hopefully this will get modern movies out of their low risk reboot loop since it will be cheaper to make a movie that have new story lines that are commercially untested. I'd be happy to watch a movie that doesn't look AAA, but has compelling writing and makes me think. Or maybe I'll just stick to books.

I don't think modern movies are stuck in a "low risk reboot loop" because of the cost to produce, it's because of the potential profit.

Why spend money on a film with new IP and ideas that you're not sure will be popular when the data science team has already worked with marketing to figure out exactly what movie will sell well?

Good luck finding your movie with compelling and thought provoking writing in the big pile of movies produced by comittee to show up above yours in discovery algorithms.

Re: Make-A-Video: AI system that generates videos from text

#47

Post by hackerlight »

VoodooJuJu wrote: post #12

A lot of people saying it's over for traditional movie-making - lmao. I look at these and see nothing but uncanny valley artifacts, and I don't think it will improve much from here. It's like self-driving cars. They use almost very effective statistical models, certainly better than our previous models, but they never seem to shake off that "almost" and become truly effective.

This tech went from nothing to beating a human artist in an art competition in a few years, and yet you say "I don't think it will improve much". So, I disagree.

Re: Make-A-Video: AI system that generates videos from text

#48

Post by ZetaZero »

VoodooJuJu wrote: post #12

A lot of people saying it's over for traditional movie-making - lmao. I look at these and see nothing but uncanny valley artifacts, and I don't think it will improve much from here. It's like self-driving cars. They use almost very effective statistical models, certainly better than our previous models, but they never seem to shake off that "almost" and become truly effective.

Right and wrong.

It's not over for traditional moving-making. It would be decades before the software and hardware could surpass. But it will improve tremendously, just like computers do for nearly everything.

Re: Make-A-Video: AI system that generates videos from text

#49

Post by EmilyHughes »

RupertEisenhart wrote: post #35
rmah wrote: post #18

Earlier quoted context omitted.

That what we're seeing is really reality is the simpler explanation. Because the alternative is that what we see is a simulation ... inside another reality that has full complexity. Which increases the overall complexity. Thus, Occam's Razor says what we see is likely real and not a simulation.

Check out the original simulation argument paper[0]. The issue is, if we think we are heading to a world in which we can do simulations, it becomes increasingly likely that we are in one of those (presumably very many) worlds, rather than in the one world that existed before the advent of such simulations. [0] https://www.simulation-argument.com/simulation.pdf

Sounds good because it seems like it explains what our reality is, but it really doesn't. It just pushes the fundamental problem up X simulations into the supposed "real reality". It also assumes that simply simulating a universe would generate consciouss beings which nobody knows the answer to, but my guess is that it would not.

Re: Make-A-Video: AI system that generates videos from text

#50

Post by lm28469 »

bottlepalm wrote: post #14

I don’t want to think reality is a simulation, but wouldn’t our everyday experience being generated by a neural network be far far simpler to achieve than a universe of infinite minuscule atoms all interacting.. like ozcam’s razor is pointing towards our lives being a realistic dream. Like in 10 years you could plug this tech into high end VR and get a prompted reality dynamically generated that would be indistinguis…

ozcam’s razor is a human made concept, the universe doesn't obey human laws, it's the opposite

> Like in 10 years you could plug this tech into high end VR and get a prompted reality dynamically generated that would be indistinguishable from our own.

They said that 10 years ago about VR and it still is dog shit

Post reply on HN