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

391–400 of 1001 posts

Re: Sora: Creating video from text

#391

Post by dinobones »

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?

If a model can generate it, it can understand it.

They can probably reverse engineer this to build a multi-modal GPT that is fed video and understands what is going on. That's how you get "smart" robots. Active scene understanding via the video modality + conversational capabilities via the text/audio modality.

Re: Sora: Creating video from text

#392

Post by JKCalhoun »

treesciencebot wrote: post #14

This is leaps and bounds beyond anything out there, including both public models like SVD 1.1 and Pika Labs' / Runway's models. Incredible.

I know it's Runway (and has all manner of those dream-like AI artifacts) but I like what this person is doing with just a bunch 4 second clips and an awesome soundtrack:

https://youtu.be/JClloSKh_dk

https://youtu.be/upCyXbTWKvQ

Re: Sora: Creating video from text

#393

Post by throwaway4233 »

drdaeman wrote: post #86
treesciencebot wrote: post #14

This is leaps and bounds beyond anything out there, including both public models like SVD 1.1 and Pika Labs' / Runway's models. Incredible.

Let's hold our breath. Those are specifically crafted hand-picked good videos, where there wasn't any requirement but "write a generic prompt and pick something that looks good", with no particular requirements. Which is very different from the actual process where you have a very specific idea and want the machine to make it happen. DALL-E presentation also looked cool and everyone was stoked about it. Now that we k…

While Sora might be able to generate short 60-90 second videos, how well it would scale with a larger prompt or a longer video remains yet to be seen. And the general logic of having the model do 90% of the work for you and then you edit what is required might be harder with videos.

Re: Sora: Creating video from text

#394

Post by umeshunni »

Alifatisk wrote: post #187
break_the_bank wrote: post #160

In less than a few hours Gemini 1.5 is old news. Sam is doing live demos on Twitter while Google just released a blog. Didn't think Google would be the first of the Facebook, Apple, Google and Microsoft to get disrupted.

I disagree, Gemini 1.5 is still impressive (if true) with the 10 million context size!

It'll be impressive when I can use it.

Re: Sora: Creating video from text

#395

Post by y_gy »

gerash wrote: post #381
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

Ironic, isn't it! OpenAI started out "open," publishing research, and now "ClosedAI" would be a much better name.

Re: Sora: Creating video from text

#396

Post by seydor »

kweingar wrote: post #206

Obviously incredibly cool, but it seems that people are incredibly overstating the applications of this. Realistically, how do you fit this into a movie, a TV show, or a game? You write a text prompt, get a scene, and then everything is gone—the characters, props, rooms, buildings, environments, etc. won’t carry over to the next prompt.

tiktok

Re: Sora: Creating video from text

#397

Post by resolutebat »

chasing wrote: post #24

Yeah, you just can't let all media, all the cost and hard work of millions of photographers, animators, filmmakers, etc be completely consumed and devalued by one company just because it's a very cool technical trick. The more powerful these services become the more obvious that will be. What OpenAI does is amazing, but they obviously cannot be allowed to capture the value of every piece of media ever created — it'll…

It's worth remembering that "intellectual property" is an entirely artificial and fairly recent construct. Humanity did fine for thousands of years without it, and I'm not going to shed too many years if OpenAI blows it up.

https://www.gnu.org/philosophy/not-ipr.en.html

https://www.gnu.org/philosophy/not-ipr.en.html

Re: Sora: Creating video from text

#398

Post by Sxubas »

I wonder what this tech would do using a descriptive fragment from a book. I don't read many books at all but I would spend some time feeding in fantasy fragments and see how much they differ from what I imagined.

Re: Sora: Creating video from text

#399

Post by Janicc »

fassssst wrote: post #220
kweingar wrote: post #206

Obviously incredibly cool, but it seems that people are incredibly overstating the applications of this. Realistically, how do you fit this into a movie, a TV show, or a game? You write a text prompt, get a scene, and then everything is gone—the characters, props, rooms, buildings, environments, etc. won’t carry over to the next prompt.

It generates up to 1 minute videos which is like what all the kids are watching on TikTok and YouTube Shorts, right? And most ads are shorter than 1 minute.

A few months ago ai generated videos of people getting arrested for wearing big boots went viral on TikTok. I think this sort of silly "interdimensional cable" stuff will be really big on these short form video type sites once this level of quality becomes available to everyone.

Re: Sora: Creating video from text

#400

Post by ladberg »

vilius wrote: post #289

The Lagos video ( https://openai.com/sora?video=lagos ) is very much how my dreams unfold. One moment, I'm with my friends in a bustling marketplace, then suddenly we are no longer at the marketplace, but rather overlooking a sunset and a highway. I wonder if there are some conceptual similarities how dreams and AI video models work.

Yeah that one has more surreal elements every time you watch it: the people at the table are giants compared to everyone else, someone is headless, the kid's hand warps around like crazy.
Post reply on HN