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

Imagen Video: high definition video generation with diffusion models

imagen.research.google

Post reply on HN
Print view View original

71–80 of 500 posts

Re: Imagen Video: high definition video generation with diffusion models

#71

Post by SpaceManNabs »

alchemist1e9 wrote: post #69
SpaceManNabs wrote: post #56

Earlier quoted context omitted.

Top two comments are creatives wondering about their future jobs. Ai ethicists have brought up concerns regarding intentional misuse like misinformation. The technology is super cool. Cat is out of the bag. Just like we couldn't really make cryptography illegal, this stuff shouldn't be either. But I dislike how everyone is pretending that AI ethicists and others are completely unfounded just because it is popular to…

It’s impressive that the small videos are generated this way but the videos themselves are obviously ML generated as they are distorted, a lot like the other art, you can kinda tell it’s the computer. I’m not seeing the ethical issues. I mean cameras disrupted lots of jobs. In general that’s what all technology does everyday. What’s different about this technology?

If you don't see the ethical challenges, then you are choosing not to see them. If you are truly interested, the paper has a good section on it and some sources.

> I mean cameras disrupted lots of jobs.

Yes, this technology can be used to augment human creativity. It is difficulty to see how disruptive these tools could be, as of now. But it is pretty clear that they are somewhat different than previous programmer as an artist models.

Re: Imagen Video: high definition video generation with diffusion models

#72

Post by visarga »

jstummbillig wrote: post #59
Keyframe wrote: post #53

Earlier quoted context omitted.

What happened to volume of web and graphic designers when templates+wordpress hit them?

A lot of additional work, because the industry was growing like crazy in tandem.

Exactly. We have a blindspot, we can't imagine second and higher order effects of a new technology. So we're left with first order effects which seem pessimistic for jobs.

Re: Imagen Video: high definition video generation with diffusion models

#73

Post by jasonjamerson »

minimaxir wrote: post #6
jasonjamerson wrote: post #5

The most exciting thing about this to me is the possibility of doing photogrammetry from the frames and getting 3D assets. And then if we can do it all in real time...

There's a bunch of NERF tools that can get pretty close to good 3D assets from static images already.

Yeah, I've been starting to explore those. Its all crashing together quickly.

Re: Imagen Video: high definition video generation with diffusion models

#74

Post by mmastrac »

forgotusername6 wrote: post #60
mmastrac wrote: post #11

This appears to understand and generate text much better. Hopefully just a few years to a prompt of "4k, widescreen render of this Star Trek: TNG episode".

At the rate this is going we are only a few years from generating a new TNG episode

I always wanted to know more about the precursors

Re: Imagen Video: high definition video generation with diffusion models

#75

Post by jasonjamerson »

Rumudiez wrote: post #19
jasonjamerson wrote: post #5

The most exciting thing about this to me is the possibility of doing photogrammetry from the frames and getting 3D assets. And then if we can do it all in real time...

you can already do this, just not in real time yet. You can upload frame sequences to Polycam's website for example, but there are several services out there which do the same thing

With this you can do it with things that don't exist. I'm excited to explore the creative power of Stable Diffusion as a 3D asset generator.

Re: Imagen Video: high definition video generation with diffusion models

#76

Post by astrange »

joshcryer wrote: post #31
J5892 wrote: post #10

Earlier quoted context omitted.

Insane, terrifying, incredible, etc. We're rapidly stumbling into the future of media. Who would've imagined a year ago that trivial AI image generation would not only be this advanced, but also this pervasive in the mainstream. And now video is already this good. We'll have full audio/video clips within a month.

Audio is the next thing that Stability AI is dropping, then video. In a few months you'll be able to conjure up anything you want if you have a few GPU cores. Pretty incredible.

I won’t be impressed until it can generate smells.

Re: Imagen Video: high definition video generation with diffusion models

#77

Post by Vecr »

monological wrote: post #36

What everyone is missing is that these AI image/video generators lack _taste_. These tools just regurgitate a mishmash of images from it's training set, without any "feeling". What you're going to tell me that you can train them to have feeling? It's never going to happen.

You can put your taste into it with prompt engineering and cherry picking with limited effort, for Stable Diffusion you can look for prompts people came up with online quite easily and merge/change them pretty much however you want. Might have to disable the content filters and run it on your own hardware though.

Re: Imagen Video: high definition video generation with diffusion models

#78

Post by rcpt »

spoonjim wrote: post #62
jeffbee wrote: post #29

Earlier quoted context omitted.

When you animate a horse, does it have 5 legs with weird backwards joints? If not, your job is probably safe for now.

Think about where this stuff was 2 years ago and then think about where it will be 2 years from now.

Relationships between objects has been a problem with computer vision for a long time.

10 years ago: https://karpathy.github.io/2012/10/22/state-of-computer-visi...

Now: https://arxiv.org/pdf/2204.13807

Given that this is what makes photos and videos interesting I think it's still a while before artists are automated.

Re: Imagen Video: high definition video generation with diffusion models

#79

Post by HolySE »

monological wrote: post #36

What everyone is missing is that these AI image/video generators lack _taste_. These tools just regurgitate a mishmash of images from it's training set, without any "feeling". What you're going to tell me that you can train them to have feeling? It's never going to happen.

> This bourgeoisie -- the middle class that is neither upper nor lower, neither so aristocratic as to take art for granted nor so poor it has no money to spend in its pursuit -- is now the group that fills museums, buys books and goes to concerts. But the bourgeoisie, which began to come into its own in the 18th century, has also left a long trail of hostility behind it ... Artistic disgust with the bourgeoisie has been a defining theme of modern Western culture. Since Moliere lambasted the ignorant, nouveau riche bourgeois gentleman, the bourgeoisie has been considered too clumsy to know true art and love (Goethe), a Philistine with aggressively unsubtle taste (Robert Schumann) and the creator of a machine-obsessed culture doomed to be overthrown by the proletariat (Marx and Engels).

- "Class Lessons: Who's Calling Whom Tacky?; The Petite Charm of the Bourgeoisie, or, How Artists View the Taste of Certain People", Edward Rothstein, The New York Times

This article also discusses a painting called "The Most Wanted" which was drawn based off a survey posed to ordinary people about what they wanted to see in a painting. "A mishmash of images from it's training set," if you will.

Claiming that others lack taste seems to be a common refrain--only this time, instead of a reaction to a subset of the human population gnawing away at the influence of another subset of humans, it's to yet another generation of machines supplanting human skill.

Re: Imagen Video: high definition video generation with diffusion models

#80

Post by martythemaniak »

I am finally going to be able to bring my 2004-era movie script to life! "Rosenberg and Goldstein go to Hot Dog Heaven" is about the parallel night Harold and Kumar's friends had and how they ended up at Hot Dog Heaven with Cindy Kim.
Post reply on HN