Live data from Hacker News

Imagen Video: high definition video generation with diffusion models

imagen.research.google

191–200 of 500 posts

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

#191

Can anyone comment on how advanced https://phenaki.video/index.html is? They have an example at the bottom of a 2 minute long video generated from a series of prompts (i.e. a story) which seems more advanced than Google or Meta's recent examples? It didn't get many comments on HN when it was posted.

Phenaki is also from Google and they say they are actively working on combining them

https://twitter.com/doomie/status/1577715163855171585

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

#192

I’m going to post an Ask HN about what am I supposed to do when I’m “disrupted”. I work in film / video / CG where the bread and butter is short form advertising for Youtube, Instagram and TV. It’s painfully obvious that in 1 year the job might be exceedingly more difficult than it is now.

I first predicted this tech 5 years ago, but I thought it was 15 years out. What I just said is beginning to happen with pretty much everything. There's a third sentence, but if I write it 10 people will gainsay me. If I omit it, there's a better chance that 10 people will write it for me.

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

#193
post #182

Google continues to blow my mind with these models, but I think their ethics strategy is totally misguided and will result in them failing to capture this market. The original Google Search gave similarly never-before-seen capabilities to people, and you could use it for good or bad - Google did not seem to have any ethical concerns around, for example, letting children use their product and come across NSFW content…

I will say, I've enjoyed playing with stable diffusion, I've been impressed with the explosion of tools built around it, and the stuff people are creating ... But all the stuff about bias in data is true. It really likes to render white people, unless you really specifically tell it something else ... in which case, you may receive an exaggerated stereotype. It seems to like producing younger adults. If all stock pho…

I've only had awesome experiences with Midjourney when it comes to generating non-white prompts. Here's some examples I did last month: https://imgur.com/a/6jitj73

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

#194
post #186

Earlier quoted context omitted.

The term "creative" is so pretentious, as if only content generation involves creativity. Your post reminds me of all the photographers that said digital photography would remain niche and never replace film. The current models are toys made by small groups. It's not hard to imagine AI generated film being much more compelling when the entire industry of engineers and "creatives" refine and evolve the ecosystem to ta…

Why is it any more pretentious than “developer” or “engineer”? Also businesses don’t always go for cheaper. They go for maximum ROI. I’ve worked on tons of marvel films for example, and I quite well know where AI fits and speeds things up. I also know where client studios will pay a pretty penny for more art directed results rather than going for the cheapest vendor.

"Engineer" usage is quite broad. Developer, less so, but you do see it with housing, device manufacturers, social programs, etc as well, and it's not relegated only to software, despite widespread usage. But you'll never hear anyone call a software engineer or device manufacturer a "creative".

Re: cheaper vs ROI, I agree, that was basically the point I was trying to get across.

I do understand your point and think it will be a long while before auto-generated content becomes mainstream, but it it's entirely possible and reasonable to expect within our near term lifetimes.

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

#195

Earlier quoted context omitted.

Personally, I find it infuriating that Google seems to believe they are the arbiters of morality and truth simply because some of their predecessors figured out good internet search and how to profitably place ads. Google has no special claim to be able to responsibly use these models just because they are rich.

>Google has no special claim to be able to responsibly use these models Well, they do have the "special claim" of inventing the model and not owing its release to anyone.

First, that isn't a claim of any kind regarding responsible use. If a child is the first one to discover a gun in the woods, that is no kind of claim that the child will use the gun responsibly. Second, Google's invention builds off of public research that was made available to them. They just choose to keep their iterations private.

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

#196
post #188

Google continues to blow my mind with these models, but I think their ethics strategy is totally misguided and will result in them failing to capture this market. The original Google Search gave similarly never-before-seen capabilities to people, and you could use it for good or bad - Google did not seem to have any ethical concerns around, for example, letting children use their product and come across NSFW content…

>You can't type any prompt that's "unsafe", you can't generate images of people, there are so many stupid limitations that the product is practically useless other than niche scenarios Imagen and Imagen Video is not released to the public at all. You might be confusing it with OpenAI's models.

They are probably confusing OpenAI with DeepMind, which is owned by Google.

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

#197

Earlier quoted context omitted.

Procedurally generated games can be quite fun, if AI content gets good enough, why wouldn't you want to watch it?

Because anything that an AI can produce, no matter how "intrinsically" good, becomes trivial, tedious and with zero value (both economic and general).

That's a weird sentiment. If you can concede that it could be "intrinsically" good, then why do you care where it came from?

It reminds me of part of the book trilogy Three Body Problem, where these aliens create human culture better than humans (in the humans' own perspective, in the book) by decoding and analyzing our radio waves to then make content. It feels to me much the same here where an unknown entity creates media, and we might like it regardless of who actually made it.

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

#198
post #182

Google continues to blow my mind with these models, but I think their ethics strategy is totally misguided and will result in them failing to capture this market. The original Google Search gave similarly never-before-seen capabilities to people, and you could use it for good or bad - Google did not seem to have any ethical concerns around, for example, letting children use their product and come across NSFW content…

I will say, I've enjoyed playing with stable diffusion, I've been impressed with the explosion of tools built around it, and the stuff people are creating ... But all the stuff about bias in data is true. It really likes to render white people, unless you really specifically tell it something else ... in which case, you may receive an exaggerated stereotype. It seems to like producing younger adults. If all stock pho…

Of course there are issues with bias. But those issues are just reflections of the world. Their solution is not a technical one.

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

#199

We're about a week into text-to-video models and they're already this impressive. Insane to imagine what the future holds in this space.

>We're about a week into text-to-video models It's at the very least 5 years old: https://arxiv.org/abs/1710.00421

There's a significant quality difference however if you look at the generated samples in the paper. Imagen Video is leagues ahead. The progress is still quite drastic

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

#200

Earlier quoted context omitted.

Procedurally generated games can be quite fun, if AI content gets good enough, why wouldn't you want to watch it?

Because anything that an AI can produce, no matter how "intrinsically" good, becomes trivial, tedious and with zero value (both economic and general).

Imagine you’re watching a show, it’s really funny and you’re enjoying it. You’re streaming it, but you’d probably have paid a few dollars to rent it back in the Blockbuster days. You’re then told that the show was produced by an AI. Do you suddenly lose interest because you don’t want to watch something produced by an AI? Or is your hypothesis that an AI could never produce a show that you liked to that degree?

If you mean the former, then I frankly think you’re an outlier and lots of people would have no problem with that. If you mean the latter, then I guess we’ll just have to wait and see. We’re certainly not there yet, but that doesn’t mean that it’s impossible. I’ve definitely read stories that were produced by an AI and preferred it to a lot of fiction that was written by humans!

Post reply on HN