Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Meta Movie Gen

ai.meta.com

Post reply on HN
Print view View original

641–650 of 1001 posts

Re: Meta Movie Gen

#641

Post by ein0p »

pk-protect-ai wrote: post #333

It is really amazing how consistent this model is in demo videos about world object details over time. This spatial comprehension is really spooky and super amazing at the same time. I hope Meta will release this model with open weights and open code, as they have done for the LLaMA models.

Problem is, the moment they release weights someone will fine tune it to generate porn, including CP. So I wouldn’t hold my breath for the weights release - no legal dept will sign off on something with this much fallout potential.

Re: Meta Movie Gen

#642

Post by stavros »

jsheard wrote: post #556
jetrink wrote: post #450

Earlier quoted context omitted.

A friend who lives in North Carolina sent me a video of the raging floodwaters in his state- at least that's what the superimposed text claimed it was. When I looked closer, it was clearly an Indian city filled with Indian people and Indian cars. He hadn't noticed anything except the flood water. It reminded me of that famous selective attention test video[1]. I won't ruin it for those who haven't seen it, but it's a…

For the entire duration of the Russia/Ukraine war "combat footage" that is actually from the video game ARMA 3 has gone viral fairly regularly, and now exactly the same thing is happening with Israel/Iran.

It's kind of sad that we don't even need AI to create misinformation, the bar for what people will fall for is really low.

Re: Meta Movie Gen

#643

Post by jcims »

changing1999 wrote: post #589
wantsanagent wrote: post #544

Earlier quoted context omitted.

Imagine you've had an idea bouncing around in your head, or even an emotion, for a long time and you've never been able to express it. Then one day you push a button and a piece of art captures what you've been feeling perfectly. It's not the craft that drives attachment in this case but the emotional resonance of something that you think should exist finally existing.

AI mentioned above is not at the level of capturing and expressing ideas or emotions beyond "a sad rock song about a breakup". Try guiding it to express any clearly formed musical idea. Author's attachment is to a large degree based on the false notion that they somehow contributed to the creation process. The generic, frigid, un-interesting "product" that is produced by said AI is why no one other than the prompter…

This is a tad overwrought. There is a creative process, but it’s much more akin to simple producing rather than composing.

My point wasn’t to debate the merit of generated music, it was simply to highlight the effect I described.

Re: Meta Movie Gen

#644

Post by causal »

causal wrote: post #162
diggan wrote: post #22

Earlier quoted context omitted.

> Any chance of this being released open weights? Considering that Facebook/Meta releases blog posts titled "Open Source AI Is the Path Forward" but then refuses to actually release any Open Source AI, I'm guessing the answer is a hard "No". They might release it under usage restrictions though, like they did with Llama, although probably only the smaller versions, to limit the output quality.

They have released a ton of open source? Llama 3 includes open training code, datasets, and models. Not to mention open-sourcing the foundation of most AI research today, pytorch.

Past the edit window - want it to be higher up that only the model architecture is shared, no training scripts, as diggan correctly points out.

Re: Meta Movie Gen

#645

Post by changing1999 »

jcims wrote: post #643
changing1999 wrote: post #589

Earlier quoted context omitted.

AI mentioned above is not at the level of capturing and expressing ideas or emotions beyond "a sad rock song about a breakup". Try guiding it to express any clearly formed musical idea. Author's attachment is to a large degree based on the false notion that they somehow contributed to the creation process. The generic, frigid, un-interesting "product" that is produced by said AI is why no one other than the prompter…

This is a tad overwrought. There is a creative process, but it’s much more akin to simple producing rather than composing. My point wasn’t to debate the merit of generated music, it was simply to highlight the effect I described.

It's not closer to producing that it is to composing. In fact, I would say it's closer to composing in the sense that you can at least add lyrics and pick a genre.

Production requires specifying very precise requirements, which the current gen AI is unable to follow. Even at the most fuzzy production level like "a song with strings and a choir", Suno will generate something completely irrelevant. And if you will try to go deeper -- use a classic Moog synth line in the chorus -- don't expect to generate something meaningful.

I won't argue that in the most broad sense, prompt engineering is a creative process. Picking which shoes to wear to work is also a creative process. My argument is that this has barely anything to do with the process of music composition or production. You can literally reuse the same prompt to generate an image or a poem.

Re: Meta Movie Gen

#646

Post by rolux »

CuriouslyC wrote: post #108
adamc wrote: post #57

Earlier quoted context omitted.

I'm not. The likelihood that such movies (for example) would have anything significant to say about being human seems very low. If one watches movies, reads books, etc. just to pass the time, maybe this would be some kind of boon. But for those of us looking for meaningful commentary on life, looking to connect with other human beings, this would be some circle of hell. It's some kind of solipsism.

That doesn't follow at all. If I come up with a meaningful story and use AI to generate clips and stich them together to tell it, that's real art. If you disagree with that, you're basically saying La Jetee isn't art, which would be a hard sell.

If La Jetee was just some photos stitched together plus meaningful narration, then of course, you could use AI-generated photos.

But would AI be able to quote Vertigo, like La Jetee does? Doesn't art, at least to some degree, require intent (including all intentional subversions of that intent dogma, of course)?

Re: Meta Movie Gen

#647

Post by Loughla »

TrackerFF wrote: post #6

All the vids have that instantly recognizable GenAI "sheen", for the lack of a better word. Also, I think the most obvious giveaway are all the micro-variations that happen along the edges, which give a fuzzy artifact.

The ATV turning in mid air was a giveaway as well. Physics seems to be a basic problem for these type of videos.

Re: Meta Movie Gen

#648

Post by Seanambers »

ynniv wrote: post #640
jsheard wrote: post #556

Earlier quoted context omitted.

For the entire duration of the Russia/Ukraine war "combat footage" that is actually from the video game ARMA 3 has gone viral fairly regularly, and now exactly the same thing is happening with Israel/Iran.

The willingness of people to believe that combatants are wearing cinematic body cams for no tactical reason can only be matched by their willingness to assume people meticulously record every minute of their lives just so they can post a once-in-a-lifetime event on TikTok. Who even needs AI generated videos when you can just act out absurdity and pretend it's real?

As far as I know, most of the viral stuff has been active air defence CWIS and the like which can be hard to discern.

There's a morbid path from the grainy Iraq war and earlier shaky footage, through IS propaganda which at the time had basically the most intense combat footage ever released to the Ukraine war. Which took it to the morbid end conclusion of endless drone video deaths and edited clips 30+ mins long with day long engagements and defending.

And yes, to answer your belief that there is none - there is loads of "cinematic body cam footage out there now".

Re: Meta Movie Gen

#649

Post by jonplackett »

turblety wrote: post #127

Why do these video generation ones never become usable to the public. Is it just they had to create millions of videos and cherry pick only a handful of decent generations? Or is it just so expensive there's no business model for it? My mind instantly assumes it a money thing and they're just wanting to charge millions for it, therefore out of reach for the general public. But then with Meta's whole stance on open ai…

KlingAI is pretty good - but only 5 second clips for their v 1.5 model which is much better than 1.0

I made this with it (after training a Flux Lora on myself)

https://vm.tiktok.com/ZGdJ6uSh1/

Also interesting - blog post from someone who actually got to use Sora https://www.fxguide.com/fxfeatured/actually-using-sora/

TLDR; it’s still quite frustrating to use

Re: Meta Movie Gen

#650

Post by terminatornet »

does anyone have an example of an AI generated video that's more than 10 seconds long that doesn't look like garbage? All of these tools seem to generate a weirdly zooming shot of something that turns a little bit and that's about it.

Anything longer than a single clip is just a bunch of these clips stitched together.

Post reply on HN