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

Sora: Creating video from text

openai.com

Post reply on HN
Print view View original

661–670 of 1001 posts

Re: Sora: Creating video from text

#661

Post by Karuma »

snewman wrote: post #637
Animats wrote: post #588

The Hollywood Reporter says many in the industry are very scared.[1] “I’ve heard a lot of people say they’re leaving film,” he says. “I’ve been thinking of where I can pivot to if I can’t make a living out of this anymore.” - a concept artist responsible for the look of the Hunger Games and some other films. "A study surveying 300 leaders across Hollywood, issued in January, reported that three-fourths of respondents…

Honest question: of what possible use could Sora be for Hollywood? The results are amazing, but if the current crop of text-to-image tools is any guide, it will be easy to create things that look cool but essentially impossible to create something that meets detailed specific criteria. If you want your actor to look and behave consistently across multiple episodes of a series, if you want it to precisely follow a det…

It wouldn't be too hard to do any of the things you mention. See ControlNet for Stable Diffusion, and vid2vid (if this model does txt2vid, it can also do vid2vid very easily).

So you can just record some guiding stuff, similar to motion capture but with just any regular phone camera, and morph it into anything you want. You don't even need the camera, of course, a simple 3D animation without textures or lighting would suffice.

Also, consistent look has been solved very early on, once we had free models like Stable Diffusion.

Re: Sora: Creating video from text

#662

Post by hello_newman »

itissid wrote: post #487

How does one cope with this? - Disruptions like this happen to every industry every now and then. Just not on the level of "Communicating with people with words, and pictures". Anduril and SpaceX disrupted defense contractors and United Launch Alliance; Someone working for a defense contractor/ULA here affected by that might attest to the feeling? - There will be plenty of opportunity to innovate. Industries are bein…

Totally agree with you.

Most of the responses in this thread remind me of why I don't typically go into the comment section of these announcements. It's way too easy to fall into the trap set by the doomsday-predicting armchair experts, who make it sound like we're on the brink of some apocalypse. But anyone attempting to predict the future right now is wasting time at best, or intentionally fear mongering at worst.

Sure, for all we know, OpenAI might just drop the AGI bomb on us one day. But wasting time worrying about all the "what ifs" doesn't help anyone.

Like you said, there is so much work out there to be done, _even if_ AGI has been achieved. Not to get sidetracked from your original comment, but I've seen AGI repeatedly mentioned in this thread. It's really all just noise until proven otherwise.

Build, adapt, and learn. So much opportunity is out there.

Re: Sora: Creating video from text

#665

Post by ta8645 »

ericzawo wrote: post #291

Why can't AI take the non-fun jobs?

Why are you able to have a fun job, when another human has a non-fun job? Because you're more talented and have skills they lack. Same goes for AI versus you. You're just starting to feel what billions of other people have felt, for a long time.

Re: Sora: Creating video from text

#666

Post by ShamelessC »

slothtrop wrote: post #529
darkhorse13 wrote: post #460

Does anyone else feel a sense of doom from these advancements? I'm definitely not a Luddite, I've been working professionally as a programmer for quite some time now, but I just can't shake this feeling. And this is not in the "I might lose my job to this" kind of feeling, that's obviously there, but it's something deeper, more sinister. I don't think I can explain it properly. Anyway, videos look incredible. I genui…

It allows the technical possibility for a post-truth reality, where it's impossible to tell what's true and what isn't. Every piece of information fed through your machine and smartphone. That's the scariest part to me. We need to get ahead of that, because certain interests will be fabricating things with it. As jobs go, well, we're a long ways from full automation but this represents some serious growing pains that…

> It allows the technical possibility for a post-truth reality

Social media already did that. Donald Trump got elected POTUS which is effectively the sum of all fears w.r.t. a "post truth reality".

Re: Sora: Creating video from text

#667

Post by Trasmatta »

darkhorse13 wrote: post #460

Does anyone else feel a sense of doom from these advancements? I'm definitely not a Luddite, I've been working professionally as a programmer for quite some time now, but I just can't shake this feeling. And this is not in the "I might lose my job to this" kind of feeling, that's obviously there, but it's something deeper, more sinister. I don't think I can explain it properly. Anyway, videos look incredible. I genui…

I felt the same thing when I saw LLMs writing code for the first time

Re: Sora: Creating video from text

#668

Post by grbsh »

nopinsight wrote: post #257

Many might miss the key paragraph at the end: "Sora serves as a foundation for models that can understand and simulate the real world, a capability we believe will be an important milestone for achieving AGI." This also helps explain why the model is so good since it is trained to simulate the real world, as opposed to imitate the pixels. More importantly, its capabilities suggest AGI and general robotics could be cl…

I think you are reading too far into this. The title of the technical paper is “ Video generation models as world simulators”.

This is “just” a transformer that takes in a sequence of noisy image (video frame) tokens + prompt, and produces a sequence of less noisy video tokens. Repeat until noise gone.

The point they’re making, which is totally valid, is that in order for such a model to produce videos with realistic physics, the underlying model is forced to learn a model of physics (a “world simulation”).

Re: Sora: Creating video from text

#669

Post by PepGuardiola »

ugh123 wrote: post #149

Imagine a movie script, but with more detail of the scenes and actors, plugged into this. The killer app for this is being able to give a prompt of a detailed description of a scene, with actor movements and all detail of environment, structure, furniture, etc. Add to that camera views/angles/movement specified in the prompt along with text for actors.

In the future, you won't need to do any of that. Your own AI will generate a movie for you and ask you if you feel like watching a movie. You will love it. Because it will know your taste, your hobbies, your friends, ads, chat history, website you visited, ..everything.

Re: Sora: Creating video from text

#670

Post by Trasmatta »

javednissar wrote: post #636

I question how much anyone has really used these models if they actually think these systems can replace people. I’ve consistently failed to get professional results out of these things and the degree of work required to get professional results makes me think a new class of job will be created to get professional results out of these systems. That being said, there is value in these systems for casual use. For examp…

The more I use them, the more I get a sense of something fundamental that's missing, and the less I worry about losing my job. It's hard to describe, I need to think harder about what that feeling is.
Post reply on HN