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

381–390 of 1001 posts

Re: Sora: Creating video from text

#381

Post by gerash »

crazygringo wrote: post #190

This is insane. But I'm impressed most of all by the quality of motion . I've quite simply never seen convincing computer-generated motion before . Just look at the way the wooly mammoths connect with the ground, and their lumbering mass feels real. Motion-capture works fine because that's real motion, but every time people try to animate humans and animals, even in big-budget CGI movies, it's always ultimately obvio…

When others create text to video systems (eg. Lumiere from Google) they publish the research (eg. https://arxiv.org/pdf/2401.12945.pdf). Open AI is all about commercialization. I don't like their attitude

Re: Sora: Creating video from text

#382

Post by charlotte-fyi »

smusamashah wrote: post #122

Did anyone else feel motion sickness or nausea watching some of these videos? In some of the videos with some panning or rotating motion, i felt some nausea like sickness effect. I guess its because some details were changing while in motion and I was unable to keep track or focus anything in particular. Effect was stronger in some videos.

Yeah, these all made me feel incredibly nauseous. I was trying to figure out what aspect of the motion was triggering this (bad parallax?) but couldn't. The results are impressive but it's still amazing to me how little defects like this can trigger our sense of not just uncanniness but actual sickness.

Re: Sora: Creating video from text

#383

Post by omega3 »

crazygringo wrote: post #190

This is insane. But I'm impressed most of all by the quality of motion . I've quite simply never seen convincing computer-generated motion before . Just look at the way the wooly mammoths connect with the ground, and their lumbering mass feels real. Motion-capture works fine because that's real motion, but every time people try to animate humans and animals, even in big-budget CGI movies, it's always ultimately obvio…

Out of all the examples, the wooly mammoths one actually feels like CGI the most to me, the other ones are much more believable than this one.

Re: Sora: Creating video from text

#384

Post by janalsncm »

minimaxir wrote: post #186
thepasswordis wrote: post #100

OpenAI demonstrating the size of their moat. How many multi-million-dollar funded startups did this just absolutely obsolete? This is so, so, so much better than every other generative video AI we've seen. Most of those were basically a still image with a very slowly moving background. This is not that. Sam is probably going to get his $7T if he keeps this up, and when he does everybody else will be locked out foreve…

> OpenAI demonstrating the size of their moat. How many multi-million-dollar funded startups did this just absolutely obsolete? For posterity since the term has been misused lately, having a very good product isn't a moat in the business sense. There's nothing stopping a competitor from creating a similar product (even if it's difficult), and there's nothing currently stopping OpenAI's users from switching from using…

> There's nothing stopping a competitor from creating a similar product

This is like saying there’s nothing stopping a competitor from launching reusable rockets into space. Of course there isn’t, but it’s hard and won’t happen for the foreseeable future.

Similarly with a physical moat, it’s not impossible to cross, but it’s hard to do.

Re: Sora: Creating video from text

#385

Post by __loam »

thomastraum wrote: post #182

I am a CG artist and Director and this made me so sad. I am watching in horror and amazement. I am not anti AI at all, but being on the wrong side of efficiency, for the individual this is heartbreaking. its so much fun to make CG and create shots and the reason its hard (just like anything) makes it rewarding.

I think it's okay to be a bit anti ai lol.

Re: Sora: Creating video from text

#386

Post by mtlmtlmtlmtl »

This is all very impressive. I can't help to wonder though. How is text-to-video going to benefit humanity? That's what OpenAI is supposedly about, right?

We'll get some groundbreaking film content out of this in the hands of a few talented creatives, and a vast ocean of mediocre content from the hands of talentless people who know how to type. What's the benefit to humanity, concretely?

Re: Sora: Creating video from text

#387

Post by Kydlaw »

neutralx wrote: post #378

Has anyone else noticed the leg swap in Tokyo video at 0:14. I guess we are past uncanny, but I do wonder if these small artifacts will always be present in generated content. Also begs the question, if more and more children are introduced to media from young age and they are fed more and more with generated content, will they be able to feel "uncanniness" or become completely blunt to it. There's definitely interes…

Yep, I noticed it immediately too. Yet it is subtle in reality. I'm not that good to spot imperfections on picture but on the video I immediately felt something was not quite right.

Re: Sora: Creating video from text

#388

Post by MrNeon »

hooande wrote: post #303

This really seems like "DALL-E", but for videos. I can make cool/funny videos for my friends, but after a while the novelty wears off. All of the AI generated media has this quality where I can immediately tell that it's ai, and that becomes my dominant thought. I see these things on social media and think "oh, another ai pic" and keep scrolling. I've yet to be confused about whether something is ai generated or real…

> I've yet to be confused about whether something is ai generated or real for more than several seconds.

How did you rule out survivorship bias?

Re: Sora: Creating video from text

#389

Post by bottlepalm »

partiallypro wrote: post #243

These are insanely good, but there are still some things that just give them away (which is good, imo.) Like the Tokyo video is amazing, the reflections, etc are all great, but the gaits of people in the background and how fast they are moving is clearly off. It sticks out once you notice it. These things will obviously improve as time marches on. The fear I have has less to do with these taking jobs, but in that eve…

Why aren't you more afraid of ASI? We're clearly just dancing around it at this point.

Re: Sora: Creating video from text

#390

Post by andai »

mtlmtlmtlmtl wrote: post #386

This is all very impressive. I can't help to wonder though. How is text-to-video going to benefit humanity? That's what OpenAI is supposedly about, right? We'll get some groundbreaking film content out of this in the hands of a few talented creatives, and a vast ocean of mediocre content from the hands of talentless people who know how to type. What's the benefit to humanity, concretely?

That's exactly what we have now with YouTube.
Post reply on HN