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

61–70 of 399 posts

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

#61

Post by mikepurvis »

criddell wrote: post #16
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.

> I don't think it will improve much from here That's a bold prediction. Why do you think that? The first thing I thought was the exact opposite. This isn't very good, but it's only version 1. Motion pictures are less than 150 years old. In another 150 years I bet virtual filmmaking will progress a lot.

Absolutely, particularly if you see this as simply another tool in the belt, like how Jurassic Park's thirty year old special effects absolutely stand the test of time because of them being a convincing mix of early CGI and puppetry.

It's not hard to imagine that this kind of thing could end up doing a lot of the heavy lifting for things like background scenes in the future, opening up the kind of stuff we saw in The Mandalorian, Game of Thrones, and the LOTR film trilogy to increasingly lower and lower budget productions.

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

#62

Post by liuliu »

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 and attention). Thus, I am optimistic what remains is to scale it up.

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

#63

Post by trention »

squidbeak wrote: post #59
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 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.

You will find plenty of comments in this very thread that are the most abject type of !Luddism.

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

#65

Post by scifibestfi »

"Our research takes the following steps to reduce the creation of harmful, biased, or misleading content."

"Our goal is to eventually make this technology available to the public, but for now we will continue to analyze, test, and trial Make-A-Video to ensure that each step of release is safe and intentional."

Are they really going to do a replay of OpenAI and Stable Diffusion? Deja vu coming soon.

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

#66

Post by iamsaitam »

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.

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 pixels.

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

#67

Post by mrandish »

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

While these early versions are primitive, as a traditional filmmaker I think in a couple years these technologies will creatively empower visual storytellers in exciting new ways. The key will be developing interfaces which allow us to engage, direct and constrain the AI to help us achieve specific goals.

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

#68

Post by 5350-uiop-1130 »

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 not so much in the physical act of creating, but more-so in the ability to express something that the AI can represent and which can connect with you.

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

#69

Post by JieJie »

Xelynega wrote: post #32
bottlepalm wrote: post #20

Earlier quoted context omitted.

It’s been like a month since people were saying this tech would be too hard to apply to video.

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.

No post body was provided.

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

#70

Post by bottlepalm »

Xelynega wrote: post #32
bottlepalm wrote: post #20

Earlier quoted context omitted.

It’s been like a month since people were saying this tech would be too hard to apply to video.

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.
Post reply on HN