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

321–330 of 500 posts

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

#321

Post by moyix »

rch wrote: post #255
gamegoblin wrote: post #8

Earlier quoted context omitted.

Emad (founder of Stability AI) has said they already have video model training underway, as well as text and audio. Exciting times.

And copilot-like code, possibly Q1 2023.

Salesforce CodeGen (particularly the 16B-multi and 16B-mono models) is pretty good already and can be used with FauxPilot [1] to get an open Copilot-like experience with local compute :) I am also very excited about the upcoming BigCode project though, which is maybe what you're thinking of?

Disclaimer: I am naturally biased since I made FauxPilot ;)

[1] https://github.com/moyix/fauxpilot

[2] https://www.bigcode-project.org/

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

#322

Post by atty »

sbierwagen wrote: post #296
atty wrote: post #266

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 (or even worse, video). We’re not at that point yet, but these things are getting better fast, so it’s only a matter of time. The problem is that there’s no way to mitigate those risks except to keep the model behind an inference-only API, or not release it at all - as soon a…

>There is a clear risk from these sorts of models as they get better - I mean recreating specific individuals’ likenesses in compromising images And the risk behind that is...? If you drill down with such claims the core is always "someone might use this to lie online" and the proposed solution every single time is: more surveillance. End anonymity. Have a Facebook account required to use the internet. Real name and…

I strongly suspect you’ve never been on the end of an internet doxxing/hate brigade if you can’t imagine how this could be used to make someone’s life a living hell.

I’ll explain again that I think they can be used for bad actions, and also that they should still be released, because the benefits will outweigh the negatives. It does not hurt to admit that some things can be dangerous when used in nefarious ways. No one suggests we ban kitchen knives even though they are lethal, because their utility is massive, and outweighs their danger. In much the same way these models have extreme utility, that almost certainly outweighs their potential negatives.

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

#323

Post by i_like_apis »

atty wrote: post #266
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…

There is a clear risk from these sorts of models as they get better - I mean recreating specific individuals’ likenesses in compromising images (or even worse, video). We’re not at that point yet, but these things are getting better fast, so it’s only a matter of time. The problem is that there’s no way to mitigate those risks except to keep the model behind an inference-only API, or not release it at all - as soon a…

I agree. Convincing fake content will eventually make us doubt our own history, let alone news media and current events. That concerns me, but I don’t think holding this tech back helps.

But those aren’t the issues they claim are concerning to them. It’s just stupid identity politics. They want their model to lie to us about the world and say things like everyone is equally likely to any attribute. They have a “reality” problem apparently.

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

#324

Post by cercatrova »

fragmede wrote: post #139
gamegoblin wrote: post #50

Earlier quoted context omitted.

"Stable Diffusion" is a particular brand from the company Stability AI that is famously open sourcing all of their models.

Pedantically, Stable Diffusion v1.4 is the one model where weights were open sourced and released. Stable Diffusion v1.5, announced September 8th and live on their API, was to be released in "a week or two" but still has yet to be released to the general public. https://discord.com/channels/1002292111942635562/10022921127...

Even more pedantically, SD weights are in fact not open source, they're under a source available license.

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

#325

Post by colordrops »

atty wrote: post #266
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…

There is a clear risk from these sorts of models as they get better - I mean recreating specific individuals’ likenesses in compromising images (or even worse, video). We’re not at that point yet, but these things are getting better fast, so it’s only a matter of time. The problem is that there’s no way to mitigate those risks except to keep the model behind an inference-only API, or not release it at all - as soon a…

> recreating specific individuals’ likenesses in compromising images (or even worse, video). We’re not at that point yet

Yes we are. There have been papers coming out on this tech for years now, with even the south park people doing videos using it.

https://www.youtube.com/watch?v=9WfZuNceFDM

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

#327

Post by AndrewUnmuted »

colordrops wrote: post #149
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…

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…

No post body was provided.

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

#328

Post by stillsut »

fzysingularity wrote: post #278

What's next? Dreamfusion Video = Imagen Video (this) + Dreamfusion ( https://dreamfusion3d.github.io/ ) Fundamentally, I think we have all the pieces based on this work and Dreamfusion to make it work. From the looks of it, there's a lot of SSR (spatial SR) and TSR (temporal SR) going on at multiple levels to upsample (spatially) and smoothen (temporally) images that won't be needed for NERFs. What's impressive is th…

I think 3D is going to be really important because I see Generative-AI as the killer app for VR/AR.

As it stands, it's very difficult to invest the budget for a dev studio (dozens of high skill people) to build a "VR movie" when the format is so unknown and unpopular. But with generative AI, an indie dev could create their own professionally produced virtual world movie. It's these creatives and risk takers that will find what types of things VR needs to become more popular.

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

#329

Post by hackerlight »

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…

A piece generated by Midjourney beat human artists in a competition judged by human artists. So there's good evidence to think these jobs are going to be replaced to a decent extent.

Human artists will still exist, it's just going to be democratized. Sort of like the impact of social media on traditional news journalists.

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

#330

Post by hackerlight »

user- wrote: post #43

This sort of AI related work seems to be accelerating at an insane speed recently. I remember being super impressed by AI Dungeon and now in the span of a few months we have got DALLE-2 , Stable Diffussion, Imagen, that one AI powered video editor, etc. Where do we think we will be at in 5 years??

GPT-4 is rumored to be coming in a few months.
Post reply on HN