Live data from Hacker News

Meta Movie Gen

ai.meta.com

951–960 of 1001 posts

Re: Meta Movie Gen

#951

Earlier quoted context omitted.

> "AI generated" I just instantly find it un-interesting artistically How familiar are you with what is possible and how much human effort goes towards achieving it? https://civitai.com/images Photography, digital painting, 3D rendering -- these all went through a phase of being panned as "not real art" before they were accepted, but they were all eventually accepted and they all turned out to have their own type of…

I would say the difference here is with these: > Photography, digital painting, 3D rendering You still make these. You sit down and form the art. When you use AI you don't make anything, you ask someone else to make it, i.e. you've commissioned it. It doesn't really matter if I sit down for a portrait and describe in excruciating detail what I want, I'm still not a painter. It doesn't even matter, in my eyes, how goo…

When I make 3D art I instruct a lot of things, how the renderer is configured, lighting details, various systems that need to be tweaked to get the final render to look good.

Using the AI tool chains, you'd start with some generation either via text or image input, then modify various settingas, model, render steps, sampler, loras, then a generative upscaling pass, control nets to extract and apply depth, pose, outlines all etc. A colourful mix of systems and config, not unlike working 3D tool chains.

Its also not unusual to mix and match, handcrafted geometry but projection mapped generated textures and then a final pass in Photoshop or what have you.

Typing "awesome art piece" into ChatGPT is like rendering a donut.

Re: Meta Movie Gen

#952
post #882

Why are there so many websites that are essentially static HTML that make my phone stutter? The video’s look cool, but I can’t really enjoy reading about them if my phone freezes every 2 seconds.

Must be because Facebook use php

Your comment uses php.

Re: Meta Movie Gen

#953
post #51

Off topic but some day you could live off grid with your own solar fusion mini reactor powering your own hardware that enables creating your own stories, movies and tales. No more need of streaming services. Internet would be to obtain news, goods and buy greatest and latest (or not) data to update your models. Decentralization could be for once not as painful as it is now; however, I still believe every single hardw…

To me, this feels like a very dystopian take. I watch movies, read books, and listen to music because they are a way to connect with fellow human beings. Taking the human out of the equation also removes any meaning for me. I get that this is kind of a fundamental line in the sand for most of the "AI art" going around, and it seems like most people fall on one side or the other. "I consume art for entertainment" vs "…

Surely if you’ve watched an amazing show you’re likely to share it with a friend, no? I see this bringing likeminded people together in tight, niche communities.

Re: Meta Movie Gen

#954

Earlier quoted context omitted.

> AI systems offer high fidelity with weak control You are spot on. I've been involved in creating technologies used by film and video creators for decades, so I have some understanding of what would be useful to them. The best video AIs I've seen only seem capable of replacing some stock video clip creation because, so far, I haven't seen any ability to maintain robust consistency from shot to shot and scene to scen…

> You are spot on. I've been involved in creating technologies used by film and video creators for decades, so I have some understanding of what would be useful to them. The best video AIs I've seen only seem capable of replacing some stock video clip creation because, so far, I haven't seen any ability to maintain robust consistency from shot to shot and scene to scene. There's also no granular control other than th…

> neural networks, generally, are already fantastically useful in tools

Yes, I agree. You've highlighted the distinction I should have included of "prompt-based".

There's a vast gulf between these AI-researcher-based concept demos on one side and the NN-based features slowly getting implemented in real production tools. Like you, I've found it challenging to have constructive conversations about AI tooling with anyone not versed in real production workflows. To anyone with real industry experience it's obvious that so far these demos don't represent a threat to real production workflows or the skilled career professionals making a good living. It's not that they're not threatening, they're just threatening to replace a different type of job entirely. If you're one of the poor souls in an off-shore locale doing remote low-end piece-work like manning a stock photo/video clip farm or doing >$100 per piece gigs on Fivver - then, yeah, you should feel "threatened".

A meta-point I try to make in these conversations is that, at least so far, every actual paying creative job I've seen AI threaten are, IMHO, work I wouldn't wish on my worst enemy. These are low-paid entry-level sweatshop gigs and everyone doing them aspires to do something else as soon as they can. The two analogies I use are: 1) How the "threat" of robotics to jobs is actually playing out. So far, in industrial applications robots are replacing Amazon warehouse and manufacturing assembly line workers, literally today's equivalent of 1920s sweatshop work. Much like the heart-wrenching videos of children in Calcutta earning pennies sifting through junk piles for metal scraps, it'll be a better world when robots replace those jobs and humans have jobs designing, installing, programming and servicing the robots. Likewise in consumer robotics applications, so far, the robots in our house only vacuum the floors, change the cat litter box, and wash the dishes/clothes. Growing up my family spent a couple years living in Asia in the 1970s and we actually had a "wash ama" who came twice a week and washed our clothes manually with a washboard and a tub. Sounds quaint but in reality it was grueling labor. She was a lovely lady but I'm glad Maytag replaced that job.

The second analogy I often use is observing that self-driving cars are mainly a threat to Uber and Lyft drivers who often barely earn minimum wage and have no job security to start with. Career professionals actually working in real video and film production workflows feel as "threatened" by prompt-based AIs as Formula 1 drivers feel about self-driving cars. Why does current F1 champion Max Verstappen never get asked how he feels about AI self-driving cars coming for his job? :-) As you observed, anyone who understands the thousands of creative choices which comprise any shot in a quality film doesn't even see these prompt-based AI demos as relevant. Once you've heard a skilled cinematographer, colorist or director of photography spend over an hour deconstructing and debating the creative choices made in single shot or scene from a film, it's hard to even imagine these demos as a threat to that level of creative skill. But being able to crudely copy the traits of a composite of a thousand exemplars of the craft without understanding any of the interactions between those thousands of creative choices does make for impressive demos. Even though the fidelity of the crude copy is amazing, the fact is such shots are a random puree of a thousand different creative choices pulled from a thousand different great shots. That's the root of what unskilled people call the "AI-clip sheen". It won't be easy to eliminate from prompt-based clip generators because the nature of the NN is it doesn't understand the interactions of all those subtle creative choices it's aping. Mashing together one cinematographer's lens choice from one shot with another cinematographer's filter choice from another shot with a third cinematographer's film stock choice from another film and a colorist's palette from a fourth unrelated work and then training the output filter only against broad criteria like "looks good" or "like a high-quality art film" is not a strategy that, IMHO, will ever produce a true threat to skilled top-level production workflows.

At the same time, as you observed, NN's are already delivering tremendous value eliminating labor-intensive, repetitive manual production work like frame-by-frame rotoscoping and animation tweening, work no one actually in the industry is sorry to see humans being relieved of. While I think NN-based features in production tools will continue to expand the use cases they can assist, I'm not sure AI tools will ever completely replace high-skill production professionals. I've already mentioned the technical challenges based on how NNs work but even if these challenges are someday overcome, there's a more fundamental limitation which is economic. Although feature film, network-level television and high-end commercials have massive cultural reach and are huge industries, the overall economic value of the entire technical production workflow and related tooling isn't as large as most people imagine. From Panavision cameras, Zeiss film lenses and Adobe Premiere to Chapman camera cranes, Sachtler tripods and Kinoflow lights, it's a relatively small industry with no unicorn-level startups. Even assuming one could license all the necessary content and manually tag it, it's hard to imagine a viable business plan which justifies investing the hundreds of millions required to recruit top-level AI researchers, thousands of H100 GPUs, etc to create and train a tool that could really replace the top 1000 career production pros working in Hollywood. There are so many other markets AI can target which are potentially far more lucrative than high-end film and video production workflows. Even the handful of blockbuster Summer tent pole movies made each year that cost $200M to make only spend somewhere around $10M or $20M on production labor and tooling below the department head level. That's not enough money to fund AI replacement anytime in the foreseeable future. The total addressable market of high-end film and video production just isn't big enough to be an attractive target for investors to fund going after it.

Re: Meta Movie Gen

#955

Earlier quoted context omitted.

A surprising amount of it is really popular too. I recently figured out that the Movie Recaps channel was all AI when the generated voice slipped and mispronounced a word in a really unnatural way. They post videos almost daily and they get millions of views. Must be making bank.

I was watching UFC recaps on Youtube and the algorithm got me onto AI generated MMA content, I watched for a while before realizing it. They were using old videos which were "enhanced" using AI and had an AI narrator. I only realized it when the fight footage got so old, and the AI had to do so much work to touch it up, that artifacts started appearing in the video. Once I realized it I rewatched the earlier clips in…

There's already rabbit holes of fake MMA fighting you can fall into online? Even if you're a "fan" and relatively aware of what to look for ... still difficult to spot? Horribly, had the same sensation while watching UFC at a bar. "Haven't I seen this match where they fall on the ground and hug for hours before?" Mostly empty background audience with limited reactions.

Somebody took AI video editing, and in a year or two, we're already at entire MMA rabbit holes of fake videos.

Commenting mostly as a personal evidence reference of how crazy the World Wide Web has gotten from anecdotal sources.

Re: Meta Movie Gen

#956

I've been saying for years that generated content is an impending tsunami that's going to drown out all real human voices online. The internet may become effectively unusable as a result for anything other than entertainment.

> The internet may become effectively unusable as a result for anything other than entertainment. That already happened, even without AI.

What was useful and usable about the internet before that isn't now?

Re: Meta Movie Gen

#957

Earlier quoted context omitted.

is it easy? i’m not a photographer but i enjoy taking pictures as a hobby. Your opinion baffles me haha. People always wonder why their iphone can’t shoot photos that look as good as the iphone camera reviews. https://www.austinmann.com/trek/iphone-16-pro-camera-review-... Understanding why your camera performs well in certain conditions and how to tweak the camera, is a mini-science all of its own. Also i think the…

> Knowing where to choose the right words, and at what moment, can make video gen turn out magical. The AI is processing millions of tokens a second, but a prompter often finds just ONE perfect prompt to capture some scenes. Some people appreciate the “art” in that. :) I do. It can take hours to make the vision in your head be replicated by the AI. Sure you can spit out generic scenes, but the game changes when the g…

there’s a reason i put “art” in quotes. I don’t mean the traditional definition, but rather the less commonly used definition from the dictionary:

“a skill at doing a specified thing, typically one acquired through practice.”

I agree that a photographer is not a true artist. It’s not hard to understand why people might appreciate their skill and creativity though?

Re: Meta Movie Gen

#958
post #861
post #228

Earlier quoted context omitted.

100% agree, the background replace that puts the guy into a stadium would be fully usable as a cut in a movie/tv show, and the background is believable enough that no one would bat an eye. If you use it properly, I expect a quality uplift on indie films/shorts. Your limit is your creativity

I personally expect a decrease in quality. Without limits people tend to get less creative. Sure, there is some balance here in that tools also enable new things to be done which are not possible without tools but working around limits has often inspired some of the most creative works.

> Without limits people tend to get less creative

But lowering those limits allows for more people to get creative

How many beautiful stories never left their author's head because their author couldn't afford it? Either the monetary cost or the opportunity cost

Considering how many movies come from one place in one country (Hollywood), we haven't even scratched the surface of human creativity

Re: Meta Movie Gen

#959
post #890

Earlier quoted context omitted.

Why should I care? Have you seen what most humans say? If an AI says more intelligent things I'm all for it.

There could be AI agents in this thread right now And you wouldn’t even know it

If you can't tell, does it matter?

Re: Meta Movie Gen

#960
post #55

Earlier quoted context omitted.

…I mean, it was advancing slowly for linguistic tasks until late 2022, that’s fair. That’s why we’re in such a crazy unexpected rollercoaster of an era - we accidentally cracked intuitive computing while trying to build the best text autocomplete. AI in general is from 1950, or more generally from whenever the abacus was invented. This very website runs on AI, and always has. I would implore us to speak more exactly…

AI so far has given us ability to mass produce shit content of no use to anybody and the next iteration of customer support phone menu trees that sound more convincingly yet remain just as useless. That and another round of IP theft and mass surveillance in the name of progress.

The core use case is as a small part of larger programs. It’s just computer vision but for words :)
Post reply on HN