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

211–220 of 1001 posts

Re: Meta Movie Gen

#211

Post by adamc »

mathgeek wrote: post #150
adamc wrote: post #61

Earlier quoted context omitted.

I wouldn't be. How is any of this going to lead to meaningful art? I don't think you get "The Green Mile" from something like this.

We already exist in a world where most of the revenue for film companies comes from formulaic productions. Studio execs certainly worry about how they are going to create profits in addition to any concerns about the qualitative cultural value of the films.

Even formulaic movies from hollywood have directors and actors doing a million things the AI will do randomly unless you tell it otherwise.

Re: Meta Movie Gen

#212

Post by cjenkins »

adamc wrote: post #61
mywacaday wrote: post #54

Earlier quoted context omitted.

Are we only a few years away from one person/small group made movies where the dialog, acting, location and special effects can be tweaked endlessly for a relatively low cost. If I was a studio exec I'd be worried.

I wouldn't be. How is any of this going to lead to meaningful art? I don't think you get "The Green Mile" from something like this.

Looking back on history I think this will lead to meaningful art (and tons and tons of absolute garbage!).

The printing press led to publishing works being reachable by more people so we got tons of garbage but we also got those few individual geniuses that previously wouldn't have been able to get their works out.

I see similarities in indie video/PC games recently too. Once the tech got to the point that an individual or small group could create a game, we got tons of absolute garbage but also games like Cave Story and Stardew Valley (both single creators IIRC).

Anything that pushes the bar down on the money and effort needed to make something will result in way more of it being made. It also hopefully makes it possible for those rare geniuses to give us their output without the dilution of having to go through bigger groups first.

I'm also excited from the perspective that this decouples skills in the creative process. There have to be people out there with tremendous story telling and movie making skills who don't have the resources/connections to produce what they're capable of.

Re: Meta Movie Gen

#213

Post by Mistletoe »

lairv wrote: post #80
mywacaday wrote: post #54

Earlier quoted context omitted.

Are we only a few years away from one person/small group made movies where the dialog, acting, location and special effects can be tweaked endlessly for a relatively low cost. If I was a studio exec I'd be worried.

I'm not sure, I see a common pattern with autonomous vehicle, text to image, llms: the last 10% are hard to achieve

If we judge from AI writing, we can extrapolate what an AI movie would be like. I cannot imagine reading an AI book. It would look and smell like a book but nothing of value or new insight would be inside. Michael Bay might be very interested.

Re: Meta Movie Gen

#214

Post by ToucanLoucan »

riskable wrote: post #172
adamc wrote: post #61

Earlier quoted context omitted.

I wouldn't be. How is any of this going to lead to meaningful art? I don't think you get "The Green Mile" from something like this.

> How is any of this going to lead to meaningful art? Nearly all the movies that go to theaters aren't "meaningful art". Not only that but what's meaningful to you isn't necessarily what's meaningful to others. If someone can get their own personal "Godzilla VS The Iron Giant" crossover made into a feature-length film it will be meaningful to them .

> Nearly all the movies that go to theaters aren't "meaningful art".

No but what they are is expensive, flashy, impressive productions which is the only reason people are comfortable paying upwards of $25 each to see them. And there's no way in the world that an AI movie is going to come anywhere close to the production quality of Godzilla vs Kong.

And like, yeah, their example videos at the posted link are impressive. How many attempts did those take? Are they going to be able to maintain continuity of a character's appearance from one shot to the next to form a coherent visual structure? How long can these shots be before the AI starts tripping over itself and forgetting how arms work?

Re: Meta Movie Gen

#215

Post by adamc »

zarzavat wrote: post #138
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.

I wouldn't be so sure. AI can ingest far more information about humans than a human ever could. It has read our stories and understands our languages. AI might have more to say about humans than we do ourselves. Of course AI can never truly experience being human, it has no emotions, but it is excellent at mimicry and it can certainly provide a meaningful outside perspective. Is there anything to say about humanity t…

Every new novel of any merit shows that there is. And the world keeps changing. The experience of being human keeps changing.

Nothing AI has yet done has demonstrated anything at the level of art or mastery. I guess I'm unconvinced that throwing a million stories into the blender and synthesizing is going to produce a compelling one.

Re: Meta Movie Gen

#216

Post by spookie »

Workaccount2 wrote: post #79
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.

It's my understanding that the AI sheen is done on purpose to give people a "tell". It is totally possible right now to at least generate images with no discernible tell.

> It is totally possible right now to at least generate images with no discernible tell.

I have yet to find examples of this

Re: Meta Movie Gen

#217

Post by bnj »

spacebanana7 wrote: post #77
adamc wrote: post #61

Earlier quoted context omitted.

I wouldn't be. How is any of this going to lead to meaningful art? I don't think you get "The Green Mile" from something like this.

I'd love to see what'd happen if someone dumped the entire text of the Silmarillion or the Hobbit into one of these models. Assuming context windows and output capacity become large enough.

Especially primed by all the lord of the rings movies, for example; I could see the studio taking all the archived footage, camera angles, all the extra data that was generated in the creation of the films and feeding that into something like this model to create all kinds of interesting additional material.

Re: Meta Movie Gen

#218

Post by ratedgene »

cs702 wrote: post #35

Impressive. It's only going to get better, faster, cheaper, easier.[a] Sooner than anyone could have expected, we'll be able to ask the machines: "Turn this book into a two-hour movie with the likeness of [your favorite actor/actress] in the lead role." Sooner than anyone could have expected, we'll be able to have immersive VR experiences that are crafted to each person. Sooner than anyone could have expected, we won…

We are super cooked! I love the future!!!!

Re: Meta Movie Gen

#219

Post by dyauspitr »

consteval wrote: post #180
dyauspitr wrote: post #95

Earlier quoted context omitted.

You’ll never be able to tell them apart.

It depends on how shallow your understanding of media is. I'm sure this can be used to create entertaining movies that are fun and wacky. I don't think it can create impactful movies.

I think that’s an extremely short sited perspective. There isn’t much that separates a “fun and wacky” movie from something impactful from a cinematography perspective. With the right music, ambience and script you could absolutely do any genre of movie you wish to.

Re: Meta Movie Gen

#220

Post by declan_roberts »

newaccount74 wrote: post #53
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.

I thought the movements were off. The little girl on the beach moves like an adult, the painter looks like a puppet, and everything is in slow motion?

They look like some commercial promo video, which makes sense since that's probably what they were trained on.
Post reply on HN