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

221–230 of 500 posts

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

#221

Post by TigeriusKirk »

trention wrote: post #162
ALittleLight wrote: post #135

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.

It's trained on our data, and so its release is in fact owed to us.

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

#222

Post by throwaway743 »

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?

Likely to show to shareholders that they're keeping up with trends and competitors

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

#223

Post by kajecounterhack »

ALittleLight wrote: post #135
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…

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.

It's not that they are arbiters of morality and truth -- it's that they have a _responsibility_ to do the least harm. They spent money and time to train these models, so it's also up to them to see that they aren't causing issues by making such things widely available.

They won't be using the models they train to commit crimes, for example. Someone who gets access to their best models may very well do that. It'd be really funny (lol, no) if Google's abuse team started facing issues because people are making more robust fake user accounts...by using google provided models.

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

#224

Post by ALittleLight »

kajecounterhack wrote: post #223
ALittleLight wrote: post #135

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.

It's not that they are arbiters of morality and truth -- it's that they have a _responsibility_ to do the least harm. They spent money and time to train these models, so it's also up to them to see that they aren't causing issues by making such things widely available. They won't be using the models they train to commit crimes, for example. Someone who gets access to their best models may very well do that. It'd be r…

Ahh, how silly of me. Here I was thinking that Google kept their models private because they were hoping to monetize them. But now that you say it, it's obvious that this is just Google being morally responsible. Thanks Google!

I'm sorry to be sarcastic. I generally try not to be, but I just can't fathom the level of naivete required to think that mega-corps act out of their moral responsibility rather than their profit-interest.

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

#225

Post by kajecounterhack »

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…

It's not as simple as this. Google Search came without Safe Search & other guards at first because _implementing privacy & age controls is hard_. It's a second-order product after the initial product. Bad capabilities (e.g. cyberstalking) are side-effects of a product that "organizes the world's information and makes it universally accessible and useful," and if anything, over time Google has sought build in more safety.

It's 2022 and we can be more thoughtful. Yes there are tradeoffs between unleashing new capabilities quickly vs being thoughtful and potentially conservative in what is made publicly available. I don't think it's bad that Google makes those tradeoffs.

FWIW Google open sources _tons_ of models that aren't LLMs / diffusion models. It's just that LLMs & powerful generative models have particular ethical considerations that are worth thinking about (hopefully something was learned from the whole Timnit thing).

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

#226

Post by nearbuy »

torginus wrote: post #106
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?

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…

DALL-E image of Mickey Mouse: https://openart.ai/discovery/generation-arxwmypmw7v5zpxeik1y...

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

#227

Post by dagmx »

y04nn wrote: post #214
dagmx wrote: post #115

I’ll be honest, as someone who worked in the film industry for a decade, this thread is depressing. It’s not the technology, it’s all the people in these comments who have never worked in the industry clamouring for its demise. One could brush it off as tech heads being over exuberant, but it’s the lack of understanding of how much fine control goes into each and every shot of a film that is depressing. If I, as a cr…

What about adding this feature to your creative workflow, for fast prototyping. I've played with DALL-E, I'm not able to paint but I was able to generate good looking paintings and it felt amazing, like getting new power, I felt like Neo when he learn martial art in The Matrix. And I realized that AI may be the new bicycle of the mind, like the personal computers and internet changed our way to work, think and live,…

Oh yes definitely they’re great tools in the toolbox. We already use lots of ML powered tooling to speed things up so I have no beef with that.

I just don’t agree with the swathes of people saying this replaces artists.

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

#228

Post by mgdlbp »

hammock wrote: post #210

Off topic: What is the "Hello World" of these AI image/video generators? Is there a standard prompt to feed it for demo purposes?

How about roundtripping “Bad Apple but the lyrics are describing what happens in the video”? (https://www.youtube.com/watch?v=ReblZ7o7lu4)

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

#229

Post by blagie »

evouga wrote: post #201
faeriechangling wrote: post #138

Earlier quoted context omitted.

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…

My experience is that corporations use self-serving pseudoethical arguments all the time. "We'd like to keep this proprietary.... Ummmm.. DEI! We can't release it due to DEI concerns!"

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

#230

Post by operator-name »

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.

A 1 year timespan seems deeply optimistic. Creativity is still hugely important, as is communicating with clients.

From what I see, these technologies have just lowered the bar for everyone to create someone, but creating something good still takes thought, time, effort and experience, especially in the advertising space.

AI in the near term is never going to be able to translate client requirements either. The feedback cycle, iterations, managing client expectations, etc.

Post reply on HN