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

261–270 of 399 posts

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

#261

Post by WheelsAtLarge »

maxov wrote: post #179
slhomme wrote: post #121

As an owner of a Video Production studio, this kind of tech is blowing my mind and makes me equally excited and scared. I can see how we could incorporate such tools in our workflows, and at the same time I'm worried it'll be used to spam the internet with thousands and thousands of souless generated videos, making it even harder to look through the noise. A fun related experiment, I thought it was fun to see what ki…

I love this! But after trying it a few times I got this result :). So fascinating. https://thismoviedoesnotexist.org/movie/the-terminator Brings up the age-old question of how much the learning in these models is just memorization. Though in cases like these it’s hard to tell.

There are only so many stories to tell. The Terminator is a rehash of so many other previous stories. The real art is in putting it together so that it seems new and fresh and gets people exited about it. The Terminator 1920s style looks interesting.

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

#262

Post by anigbrowl »

antegamisou wrote: post #26
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.

> A lot of people saying it's over for traditional movie-making - lmao. The groups supporting such absurd claims largely boil down to: - Money-driven researchers in the applied AI field. Those are the people that spam popular ML conferences with barely novel contributions other than some minor tweaks on code from their previous papers. - People unable to critically think and evaluate the significant limitations of SO…

On your second point, a few years ago the SOTA was Google's Deep Dream.

I agree with your deeper criticism, though preferential attachment/ranking is very much How Humans Do Things. You could do a much improved citation system by expanding the time dimension and looking at papers that were unpopular at first and then attracted wide interest later.

Of course, academics also have a tendency to over-cite (because they don't want to be rejected for inadequate literature review), so there are incentives to cite a bunch of research whose premises or conclusions you hope to overturn.

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

#263

Post by ThisIsMyAltFace »

danso wrote: post #178

It's funny that in terms of popular culture, we've all but accepted that Star Trek's Holodeck-type fantasy creation is something that will/should exist in a "proper" future. Yet all the intermediary technology to get there -- AI-generated visuals would be among the first such steps -- still makes most of us feel a little uncomfortable at first glance.

Because it's Star Trek technology without Star Trek society, and in fact anti-Star Trek society.

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

#264

Post by anigbrowl »

wokwokwok wrote: post #82
iamsaitam wrote: post #66

Earlier quoted context omitted.

It will definitely improve from here onward. On the other hand, I agree that it's a ridiculous thing to say that traditional movie-making is over. There's so much involved in making a movie, so much happenstance from the actors performances in a specific environment. You will never be able to get this in AI.. you might get some sort of mimicry, but the comparison is futile.. a movie isn't just a sequence of changing…

I think it’s more complex than that. What you’re going to see is a race to the bottom, the same as with claymation films and 3d. It will suddenly require a lot less (expensive, highly trained) people to make the same films. You’ll still need expensive highly trained people to do it, but with different skills and a lot less of them can do a lot more a lot more quickly. …and that means that some studios will make bad,…

Accurate, no notes.

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

#265

Post by Atheros »

hiidrew wrote: post #254
slhomme wrote: post #121

As an owner of a Video Production studio, this kind of tech is blowing my mind and makes me equally excited and scared. I can see how we could incorporate such tools in our workflows, and at the same time I'm worried it'll be used to spam the internet with thousands and thousands of souless generated videos, making it even harder to look through the noise. A fun related experiment, I thought it was fun to see what ki…

I think some refer to this as the dead internet theory, e.g. AI content creation becomes the majority of media on the internet instead of humans posting (may be wrong in my explanation but think that's the premise). It's scary to think about it but seems plausible—like if someone can make an app with Tiktok-like ubiquity of only AI content. Although to your point I imagine there will be so much nonsensical noise that…

People like interacting with other people, not bots. If a few individuals start to feel like they're interacting with too many bots, they'll retreat into small private silos. The human-to-bot ratio on public forums then drops. Then more people realize that they're just talking to bots and further and further it goes until practically no humans are left. That's the dead internet theory.

I really don't think it applies to us in this context though because I think that a decent number of humans don't care whether some content is AI generated. Furry porn is all hand-drawn and people still like it despite it not being real.

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

#266

Post by ilaksh »

mach1ne wrote: post #96
tpmx wrote: post #8

Earlier quoted context omitted.

In case anyone else had problems finding it - it's at the bottom of the page: https://makeavideo.studio/assets/a_golden_retriever_eating_i... (webp) That grasp though. These things still feel a bit like e.g. Google/GCP services to me: Super appealing at first glance, quite close to what you want, but somehow never quite there. Maybe they'll asymptotically get there, eventually? Perhaps that statistical model can't re…

It may be that it's the deep learning tech which will never quite get there. GPT-3 has similar shortcomings in its mimicry. We're 95% there, I guess, but may never quite reach 100%.

On the home page of HN at the moment is something like GPT but much better. It's at character.ai

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

#267

Post by WheelsAtLarge »

slhomme wrote: post #121

As an owner of a Video Production studio, this kind of tech is blowing my mind and makes me equally excited and scared. I can see how we could incorporate such tools in our workflows, and at the same time I'm worried it'll be used to spam the internet with thousands and thousands of souless generated videos, making it even harder to look through the noise. A fun related experiment, I thought it was fun to see what ki…

Cool toy. One of the most useful side effects of AI right now is idea generation. Market this as an idea generator for movies and such and people will eat it up. Try posting it on the entertainment focused area of Twitter and people will go nuts for it.

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

#268

Post by ilaksh »

5350-uiop-1130 wrote: post #68

Wonder if all these things will bring about a kind of cambrian explosion of creativity. Imagine a future of Prompt Wizards, who are able to coax the AI to generate things in a very specific way. Although we would probably need a much greater level of human curation. The way algorithms curate on youtube and spotify just doesn't really hit the spot. Perhaps stability and Dall-e already kind of showed that the value is…

Think about 25 or 30 or 50 years down the line. More interesting than the next couple of years. Speculate a bit.

After Neuralink and a few other companies torture enough poor monkeys, they eventually figure out how to create high bandwidth brain computer interfaces.

We go through a few more paradigm shifts in computing and get 10000-1000000 X or more performance increase. Metaverse protocols have advanced to allow for seamless integration of simulated persons and environments across multiple clusters.

The software continues to improve.

What you could get is a simulated realm with simulated AI characters living their own lives. But groups of real people are plugged directly in to the simulation and can influence it with their thoughts. There may be some sort of rules to ensure a certain level of stability. But basically you just think "there should be a storm today" and maybe visualize some strong winds. And then it happens in their world.

So at that point we become Gods.

I am probably getting carried away because I am tired.

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

#269

Post by anigbrowl »

bottlepalm wrote: post #70
Xelynega wrote: post #32

Earlier quoted context omitted.

The leap from "generating a frame" to "generating a video" is not as big as the leap from where we are now to a 'perfect' image synthesis engine(which would be required to get rid of artifacts). The much more likely scenario IMO is that people get used to the artifacts and notice them less.

There is something with the AI needing to have a ‘sense’ for the world the scene exists in so longer videos can be created that are coherent. Currently we’ve only seen long videos that have no consistency and jump around a lot like an acid trip.

Yep, we're in a real hype cycle.

A good path forward is to fuse these image-element compositing tools with some of the 3d scene inference ones. So you start out with 'giant fish riding in a golf cart, using its tail to steer', then give that as ground truth to a modeling tool that figures out a fish and a wheeled vehicle well enough to reference some canonical examples with detailed shape and structure, the idea of weight etc. Then you build a new model with those and do some physics simulation (while maintaining a localized constraint of unreality that allows the fish to somehow stay in the seat of the golf cart).

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

#270

Post by anigbrowl »

permo-w wrote: post #222
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.

> A lot of people saying it's over for traditional movie-making who is saying that?

Me, film-industry vet.

You'll see an excellent mostly- or all-AI feature within 5-10 years. There will be terrible ones before that, maybe 2-3 years. The first really good one will be enjoyed on its own merits, ad the artificiality of it will come to light after it has gained popularity.

Post reply on HN