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

121–130 of 399 posts

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

#121

Post by slhomme »

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 kind of movies AI would generate, so I created a "This Movie Does Not Exist" website[1] that auto generates fake movies (movie posters + synopsis). It basically uses GPT-3 to generate some story plots, and then uses that as a prompt (with in-between steps) for Stable Diffusion. Results may vary, but it definitely surprises sometimes with movies that look and sound amazing!

[1] This Movie Does Not Exist: https://thismoviedoesnotexist.org/

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

#123

Post by soheil »

bottlepalm wrote: post #102
soheil wrote: post #55

Earlier quoted context omitted.

If you're assuming each atom is independent of other atoms then yes. But if you believe the universe is deterministic and atoms are just following the laws of physics then you can think of the universe as nothing more than a computer with electrons instead of atoms just floating around.

It’d be simpler to say there are no atoms, just a neural net fed into your senses making you think that there are atoms. The neural net itself is built on a much simpler substrate in an external universe.

And what exactly are your senses and your brain made out of?

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

#124

Post by MichaelCollins »

liuliu wrote: post #62
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.

Their video training set is still small (10M + 10M). A lot of the interpolation artifacts seems come from the model haven't acquired enough real-world understanding of "natural" movements (looking at the horse running and the sail-boat examples). I suspect scaling this up to 10x would have much less artifacts. Reading the paper, it seems to be the "right" approach (separating temporal / spatial for both convolution a…

The horse leg motion in these examples is really poor. But to be fair, horse legs are very difficult for human animators too, generally necessitating the use of reference photos to get it right. The first time somebody got a series of photographs showing a horse in motion caused quite a stir: https://en.wikipedia.org/wiki/The_Horse_in_Motion

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

#125

Post by tmjdev »

Filligree wrote: post #44
londons_explore wrote: post #13

Earlier quoted context omitted.

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 p…

I am curious if there has been any research on temporal attention in humans. I'm not sure how you'd quantify it. But in myself I know that I'm constantly predicting where something will be or what it will look like based on how it did a second ago. It's probably the root of reflexes.

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

#127

Post by mitchdoogle »

MichaelCollins wrote: post #75
squidbeak wrote: post #59

Earlier quoted context omitted.

This is a good example of the most abject type of Luddism: telling yourself that a fast-developing tech you happen to dislike is already at or near the limit of its potential and that defects you notice now will be there forever.

The Luddites were a labor rights movement reacting to the new shifting power dynamic of centralized production owned by a few, in an era with virtually no safety and worker rights regulations. How would you feel if your career evaporated and you were forced to choose between starvation and sending your children to work in a textile factory where they get maimed by the machines they're told to crawl into and repair? Y…

Whatever their motivation, their ire is misguided and selfish. Is the world supposed to just sit and around and never innovate or try to become more productive? So people can have a job doing work better done by machines? I don't think so. The Luddites and any such analogs today are focused on the wrong thing - they should not attack new technology or the companies and individuals using them, but rather campaign for better social safety net from the government.

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

#128

Post by sixQuarks »

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…

For those who are scared about this technology, it’s good to look at what AI has done to Chess.

The best chess seems to be when AI is used along with humans. I think image and video AI will best be exploited when human input is also taken into account.

There is still something special about human creativity, I think AI will just be another tool to expand that. At least, in the short term I would say 10 years perhaps. AI will probably one day take over all aspects of creativity and humans won’t be able to contribute.

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

#129

Post by skocznymroczny »

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…

Reminds me of South Park when Cartman was pretending to be a robot and was made to invent movie prompts

"Adam Sandler is like, in love with some girl, but then it turns out that the girl is actually a Golden Retriever. Or something.""

Post reply on HN