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

201–210 of 500 posts

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

#201

Post by evouga »

faeriechangling wrote: post #138
throwaway23597 wrote: post #113

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’ve heard a lot of “data is the new oil” talk and the inevitability of google’s dominance yet I’m inclined to agree with you. Stable diffusion was a big wakeup call where it was clear how much value freedom and creativity really had. The ethics problem is an artifact of googles model of trying to keep their AI under lock and key and carefully controlled and opaque to outsiders in how the sausage gets made and what i…

> History will remember them as villains.

Interesting analogy. Google, like the priests, is acting out of mix of good intentions (protecting the public from perceived dangers) and self-interest (maintaining secular power, vs. a competitive advantage in the AI space). In the case of the priests, time has shown that their good intentions were misguided. I have a pretty hard time believing that history will be as unkind towards those who tried to protect minorities from biased tech, though of course that's impossible to judge in the moment.

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

#202

Post by shakingmyhead »

visarga wrote: post #136
torginus wrote: post #106

Earlier quoted context omitted.

This whole holier-than-thou moralizing strikes me as trying to steer the conversation away from the real issue, which came into spotlight with Stable Diffusion - one of authorship/violating the IP rights of artists, who now have come down in force against their would be tech overlords who are in the process or repackaging and reselling their work. This forced ideological posturing of 'if we give it to the plebes, the…

> repackaging and reselling their work. It's not their work unless it's identical, but in practice generated images are substantially different. Drawing in the style of is not copying, it's creative and it also depends on the "dialogue" with the prompter to get to the right image. The artist names added to the prompts act more like landmarks in the latent space, they are a useful shortcut to specifying the style. If…

It’s not your work unless it’s identical is not how existing copyright law works so not sure why it would be how these things should be treated. Not to mention that moving around copies of the dataset itself is itself making copies that ARE identical…

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

#203

Post by trention »

gbear605 wrote: post #200
trention wrote: post #184

Earlier quoted context omitted.

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 yo…

You may want to familiarize yourself with this thought experiment and think how a slightly modified version applies to AIs and their output: https://en.wikipedia.org/wiki/Experience_machine

As to whether I am an outlier: Hundreds of thousands of people worldwide watch Magnus Carlsen. How many have watched AlphaZero play chess when it came about and how many watch it when it ceased to be a novelty?

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

#204

Post by andreyk »

simonw wrote: post #86
aero-glide2 wrote: post #12

"We have decided not to release the Imagen Video model or its source code until these concerns are mitigated" Okay then why even post it in the first place? What exactly is Google going to do with this model?

It's a research activity. Google and Meta and Microsoft all have research teams working on AI. Putting out papers like this helps keep their existing employees happy (since they get to take credit for their work) and helps attract other skilled employees as well.

Yep. The people who build Imagen are researchers, not engineers, and these announcements are accompanied by papers describing the results as a means of sharing ideas/results with the academic community. Pretty weird to me how so many in this thread don't seem to remember that.

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

#205

Post by jupp0r »

What's the business value of publishing this research in the first place vs keeping it private? Following this train of thought will lead you to the answer to your implied question.

Apart from that - they publish the paper and anybody can reimplement and train the same model. It's not trivial but it's also completely feasible to do for lots of hobbyists in the field in a matter of a few days. Google doesn't need to publish a free use trained model themselves and associate that with their brand.

That being said, I agree with you, the "ethics" of imposing trivially bypassable restrictions on these models is silly. Ethics should be applied to what people use these models for.

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

#206

Post by baron816 »

kranke155 wrote: post #15

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.

Quite the opposite: you’re going to be in even higher demand and will make more money.

Yes, it will be possible for one person to do the work of many, but that just means each person becomes more valuable.

It’s also a law in economics that supply often drives demand, and that’s definitely the case in your field. Companies and individuals will want even more of what you want. It’s not like laundry detergent (one can only consume so much of that). There’s almost no limit to how much of what you supply that people could consume.

The way I see it, your output could multiply 100 fold. You could build out large, complex projects that used to take massive teams all by yourself, and in a fraction of the time. Companies can than monetize that for consumers.

AI is just a tool. Software engineers got rich when their tools got better. More engineers entered the field, and they just kept getting richer. That’s because the value of each engineer increased as they became more productive, and that value helped drive demand.

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

#207

Post by iso1337 »

pwython wrote: post #193
abeppu wrote: post #182

Earlier quoted context omitted.

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

The fact that white is the default is already problematic.

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

#208

Post by Kiro »

throwaway23597 wrote: post #113

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…

What previous models are you actually referring to? OpenAI/Dall-E has these restrictions but they are not Google.

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

#209

Post by kertoip_1 »

alphabetting wrote: post #2

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.

How is it possible that all of them just started to appear at the same time? Is it possible that those models were designed and trained in a last few weeks? Has some "magic key" to content generation been just unexpectedly discovered? Or the topic became trendy and everyone is just publishing what they've got so far, so they hope to benefit from media attention?
Post reply on HN