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

171–180 of 500 posts

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

#171

Post by dotsam »

CobrastanJorji wrote: post #132
ugh123 wrote: post #102

These are baby steps towards what I think will be the eventual "disruption" to the film and tv industry. Directors will simply be able to write a script/prompt long enough and detailed enough for something like Imagen (or it's successors) to convert into a feature-length show. Certainly we're very, very far away from that level of cinematic detail and crispness. But I believe that is where this leads... complete with…

I feel like this is very similar to those people who say "have you seen GPT-3? Soon there will be no programmers anymore and all of the code will be generated," and it's wrong for the same reasons. Can GPT-3 generate good code from vague prompts? Yes, it's surprisingly, sometimes shockingly good at it. Is it ever going to be a replacement for programmers? No, probably not. Same here. This tool's great grandchild is n…

> This tool's great grandchild is never going to take a rough idea for a movie and churn out a blockbuster film.

What about the tool's nth child though? I think saying it will never do it is a bit much, given what we know about human ingenuity and economic incentives.

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

#172

Post by visarga »

HolySE wrote: post #79
monological wrote: post #36

What everyone is missing is that these AI image/video generators lack _taste_. These tools just regurgitate a mishmash of images from it's training set, without any "feeling". What you're going to tell me that you can train them to have feeling? It's never going to happen.

> This bourgeoisie -- the middle class that is neither upper nor lower, neither so aristocratic as to take art for granted nor so poor it has no money to spend in its pursuit -- is now the group that fills museums, buys books and goes to concerts. But the bourgeoisie, which began to come into its own in the 18th century, has also left a long trail of hostility behind it ... Artistic disgust with the bourgeoisie has b…

The more developed the artistic taste, the lower one's opinion of other tastes.

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

#173

Post by armchairhacker »

I really like these videos because they're trippy.

Someone should work on a neural net to generate trippy videos. It would probably be much easier than realistic videos (esp. because these videos are noticeably generated from obvious to subtle).

Also is nobody paying attention to the fact that they got words correct? At least "Imagen Video". Prior models all suck at word order

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

#174

Post by Thaxll »

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.

It won't be ready anytime soon imo, looks impressive but who can use that? 512*512 of bad quality, weird looking AI with those moving part that you find everywhere in AI generated art etc ...

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

#175

Post by astrange »

croddin wrote: post #89
astrange wrote: post #76

Earlier quoted context omitted.

I won’t be impressed until it can generate smells.

You joke, but that is in the works as well (would require special hardware though) https://ai.googleblog.com/2022/09/digitizing-smell-using-mol...

Oh, it wasn’t really a joke. Didn’t know they were working on it though - I’ve always thought wanted to see use of all the senses in UIs, especially VR.

Plus then maybe we could get a computer to tell us what thioacetone smells like without actually having to experience it.

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

#176

Post by CuriouslyC »

oceanplexian wrote: post #112
boh wrote: post #84

Earlier quoted context omitted.

There's a huge gap between "that's pretty cool" and a feature length film. People want to create specific stories with specific scenes in specific places that look a specific way. A "Couple kissing in the rain " prompt isn't going to produce something people are going to pay to see. It's more likely that you're still going to be filming/editing/animating but will have an AI layer on top that produces extra effects or…

I actually think it's the opposite, AI will probably be writing the stories and humans might occasionally film a few scenes. ~95% of TV shows and movies are cookie-cutter content, with cookie-cutter acting and production values, with the same hooks and the same tropes regurgitated over and over again. Heck they can't even figure out how to make new IP so they keep making reruns of the same old stuff like Star Wars, M…

AI might take an outline and write dialogue/descriptions/etc, but it's not going to be generating the story or creating the characters. They might use AI to tune what people come up with (ala "market research") but there will still be a human that can be blamed or celebrated at the creative helm.

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

#177

Post by CuriouslyC »

trention wrote: post #163
oceanplexian wrote: post #112

Earlier quoted context omitted.

I actually think it's the opposite, AI will probably be writing the stories and humans might occasionally film a few scenes. ~95% of TV shows and movies are cookie-cutter content, with cookie-cutter acting and production values, with the same hooks and the same tropes regurgitated over and over again. Heck they can't even figure out how to make new IP so they keep making reruns of the same old stuff like Star Wars, M…

Why would I want to watch AI-generated content?

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

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

#179

Post by seanwilson »

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.

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

#180

Post by hindsightbias »

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…

We will see a combinatorial explosion of centuries of experience in the hands of any creator. They’ll select the artistic model desired - a Peckinpah-Toland-Dykstra-Woo plug-in will render a good enough masterpiece.

Christopher Nolan has already proven we’ll take anything as long as the score is ok - dark screen, mumbling lines, incoherent plotlines…

Post reply on HN