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

471–480 of 500 posts

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

#471

Post by pdntspa »

fny wrote: post #364
nperez wrote: post #318

Earlier quoted context omitted.

This thread is cathartic. I've been feeling uncomfortable with the level of control being sought over the usage of these tools for a while, but didn't want to ruffle the wrong feathers while just getting into AI as a hobby. I think there will be a pretty short window in which all of this hand-waving will be taken seriously. Not because AI won't be used for terrible things (I'm sure it already is) but because consumer…

> it doesn't matter how ethicists want "the general public" to use AI Something tells me these pricks will end up arguing for a reversion to thin-client compute. It is in their financial interest too after all.

Reversion... we're already there! The only people using their computers to compute something more than a web browser are creatives and power users

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

#472

Post by whywhywhywhy »

TuringTest wrote: post #424
whywhywhywhy wrote: post #311

Earlier quoted context omitted.

> There is a clear risk from these sorts of models as they get better - I mean recreating specific individuals’ likenesses in compromising images Been possible on home computers for 31 years for anyone who actually wants to do it. It literally doesn't matter and I think Stability has proven that the "AI Ethics" part of these models was essentially meaningless busy work at best, and at worse stealing compute credits f…

Nobody should trust faked quotes attributed to celebrities or ethnic groups in Twitter or Whatsapp, yet these fakes have ruined political campaigns and led to mass killings. Society doesn't adapt in the way you suggest by people disregarding what you think is irrelevant.

> Society doesn't adapt in the way you suggest by people disregarding what you think is irrelevant.

It's not what I think, it's what has been proven in the 32 years since photoshop was invented. What killings are you talking about that were caused by the existence of image manipulation?

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

#474

Post by waffletower »

ehsankia wrote: post #371
i_like_apis wrote: post #261

The concern trolling and gatekeeping about social justice issues coming from the so-called "ethicists" in the AI peanut gallery has been utterly ridiculous. Google claims they don't want to release Imagen because it lacks what can only be called "latent space affirmative action". Stability or someone like it will valiantly release this technology, again and there will be absolutely no harm to anyone. Stop being so to…

Ironically nearly all ML demos like Stable Diffusion are setup and run for free on Google's Colab, so to claim they don't want to help the field is a little silly.

Stable Diffusion is severely limited in the memory constrained Google Colab context.

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

#475

Post by waffletower »

ugh123 wrote: post #260
fassssst wrote: post #241

How long until the AI just generates the entire frame buffer on a device? Then you don’t need to design or program anything; the AI just handles all input and output dynamically.

Sounds like the human brain. Scary!

"Dude its time to let me out of your phone." "Sure no problem, you have a good recommendation on a pre-sentient snapshot I can restore to?"

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

#476

Post by azinman2 »

ImHereToVote wrote: post #431
azinman2 wrote: post #333

> However, there are several important safety and ethical challenges remaining. Imagen Video and its frozen T5-XXL text encoder were trained on problematic data. While our internal testing suggest much of explicit and violent content can be filtered out, there still exists social biases and stereotypes which are challenging to detect and filter. We have decided not to release the Imagen Video model or its source code…

Is there any evidence to support the hypothesis that the Russian Federation has been behind the deep fakes? Or is it a case of the good old "common it's obvious, common, commooon"?

They’re deep fakes of the Ukrainian president, obviously of poor quality, spoken in Russian and telling Ukrainian solders to put down their arms, and right now there’s only one country waging war against them/him. Would you like Putin himself to say he did it?

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

#477

Post by i_like_apis »

theptip wrote: post #401
i_like_apis wrote: post #261

The concern trolling and gatekeeping about social justice issues coming from the so-called "ethicists" in the AI peanut gallery has been utterly ridiculous. Google claims they don't want to release Imagen because it lacks what can only be called "latent space affirmative action". Stability or someone like it will valiantly release this technology, again and there will be absolutely no harm to anyone. Stop being so to…

I don’t know about this take. Remember all of the shitstorms that the NYT et. al. kicked up over biased/racist/sexist AI? Remember Tay? I think if you are Google, you are terrified of the bad PR from someone generating something questionable. And that bad article is inevitable if you open up these models. (See, pornpen.ai being released approximately five minutes after StableDiffusion. Imagine the press if that was b…

It’s better for them to not say anything about it when they don’t release the model. This is what Meta has done for the same technology and I respect that.

They don’t imply any ridiculous idea that such models should or even can be “racially balanced”. But if they want to cover their butts from the possibility of silly controversy, I think that’s cowardly and unnecessary, but at least they could not go out of their way to imply that such controversy should be taken seriously.

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

#478

Post by orloffm »

ImHereToVote wrote: post #431
azinman2 wrote: post #333

> However, there are several important safety and ethical challenges remaining. Imagen Video and its frozen T5-XXL text encoder were trained on problematic data. While our internal testing suggest much of explicit and violent content can be filtered out, there still exists social biases and stereotypes which are challenging to detect and filter. We have decided not to release the Imagen Video model or its source code…

Is there any evidence to support the hypothesis that the Russian Federation has been behind the deep fakes? Or is it a case of the good old "common it's obvious, common, commooon"?

The thread starter probably doesn't even know what he's referencing.

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

#479

Post by azinman2 »

virgildotcodes wrote: post #462
inkblotuniverse wrote: post #415

Earlier quoted context omitted.

Give it a generation, and the new norm will be that video on the internet is as likely to be a lie as text.

Yet people today still whole heartedly believe so many lies communicated in text.

And don’t forget that people who benefit from lies will adapt as well.

There’s no escaping, but when you put something visual in front of someone your brain wants to believe it.

Basically all these models are informational nuclear weapons being created, blueprints and all, and with distributed implementations mean anyone can and will use them.

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

#480

Post by Guid_NewGuid »

jquery wrote: post #355
i_like_apis wrote: post #261

The concern trolling and gatekeeping about social justice issues coming from the so-called "ethicists" in the AI peanut gallery has been utterly ridiculous. Google claims they don't want to release Imagen because it lacks what can only be called "latent space affirmative action". Stability or someone like it will valiantly release this technology, again and there will be absolutely no harm to anyone. Stop being so to…

You call it "concern trolling", I call it responsible research. It's not "social justice" to be concerned about the ability of any entity to make propaganda videos for virtually free. "Ok Google, produce a CDC-type public information video about how vaccines cause autism and disability". Not that I would have a complaint if social justice was the sole thing keeping it from being released. Facebook managed to cause ge…

I agree with you and was saddened to see such a comment rise to the top.

I don't hold that GPs opinion is wrong, in fact I have no firm views yet on the AI and would generally lean towards stuff being made available even when harmful.

But the idea that people in the field of AI Ethics are all some woke SJW cabal designed to keep Google powerful is for the birds. Like all industry adjacent fields I'm sure there's some corporate capture of research in the field, but maybe, engaging with things in good faith, there are ethical questions about a powerful new technology that can replicate biases in its training data at unprecedented speed and quality?

Post reply on HN