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

Sora is here

openai.com

Post reply on HN
Print view View original

241–250 of 1001 posts

Re: Sora is here

#241

Post by throwup238 »

bongodongobob wrote: post #168
throwup238 wrote: post #129

Earlier quoted context omitted.

“A frame is worth a billion rays” The last production I worked on averaged 16 hours per frame for the final rendering. The amount of information encoded in lighting, models, texture, maps, etc is insane.

What were you working on? It took a month to render 2 seconds of video?

VFX heavy feature for a Disney subsidiary. Each frame is rendered independently of each other - it’s not like video encoding where each frame depends on the previous one, they all have their own scene assembly that can be sent to a server to parallelize rendering. With enough compute, the entire film can be rendered in a few days. (It’s a little more complicated than that but works to a first order approximation)

I don’t remember how long the final rendering took but it was nearly two months and the final compute budget was 7 or 8 figures. I think we had close to 100k cores running at peak from three different render farms during crunch time, but don’t take my word for it I wasn’t producing the picture.

Re: Sora is here

#242

Post by highwaylights »

lacoolj wrote: post #235

A little worried how young children watching these videos may develop inaccurate impressions of physics in nature. For instance, that ladybug looks pretty natural, but there's a little glitch in there that an unwitting observer, who's never seen a ladybug move before, may mistake as being normal. And maybe it is! And maybe it isn't? The sailing ship - are those water movements correct? The sinking of the elephant int…

I’d be more worried about the inevitable “we’re under nuclear attack, head for shelter” CNN deepfakes.

Re: Sora is here

#243

Post by icepat »

lacoolj wrote: post #235

A little worried how young children watching these videos may develop inaccurate impressions of physics in nature. For instance, that ladybug looks pretty natural, but there's a little glitch in there that an unwitting observer, who's never seen a ladybug move before, may mistake as being normal. And maybe it is! And maybe it isn't? The sailing ship - are those water movements correct? The sinking of the elephant int…

> The sinking of the elephant into snow - how deep is too deep? Should there be snow on the elephant or would it have melted from body heat? Should some of the snow fall off during movement or is it maybe packed down too tightly already?

Should there be an elephant in the snow? The layers of possible confusion, and subtle incorrect understandings go much deeper.

Re: Sora is here

#244

Post by tetris11 »

lacoolj wrote: post #235

A little worried how young children watching these videos may develop inaccurate impressions of physics in nature. For instance, that ladybug looks pretty natural, but there's a little glitch in there that an unwitting observer, who's never seen a ladybug move before, may mistake as being normal. And maybe it is! And maybe it isn't? The sailing ship - are those water movements correct? The sinking of the elephant int…

Also, I guess its just normal for a car lane to just merge seamlessly into a pedestrian zone

Re: Sora is here

#245

Post by imiric »

quenix wrote: post #199
sjm wrote: post #162

Anyone else find this stuff extremely distasteful? "Disrupting" creativity and art feels like it goes against our humanity.

The past few years' innovation in AI has roughly been split into two camps for me. LLMs -- Awesome and useful. Disruptive, and somewhat dangerous, but probably more good than harm if we do it right. 'Generative art' (i.e. music generation, image generation, video generation) -- Why? Just why? The 'art' is always good enough to trick most humans at a glance but clearly fake, plastic, and soulless when you look a bit c…

I don't understand why you see a distinction between models that generate text, and those that generate images, video or audio. They're all digital formats, and the technology itself is fairly agnostic about what it's actually generating.

Can't text also be considered art? There's as much art in poetry, lyrics, novels, scripts, etc. as in other forms of media.

The thing is that the generative tech is out of the bag, and there's no going back. So we'll have to endure the negative effects along with the positive.

Re: Sora is here

#246

Post by treesciencebot »

minimaxir wrote: post #33
Geee wrote: post #18

Earlier quoted context omitted.

What's the best open source video model right now?

Hunyan ( https://replicate.com/tencent/hunyuan-video , $0.70/video) is the best but somewhat expensive. LTX ( https://replicate.com/fofr/ltx-video , $0.10) is cheaper/faster but less capable. Both are permissively licensed.

Hunyuan at other providers like fal.ai is cheaper than SORA for the same resolution (720p 5 seconds gets you ~15 videos for $20 vs almost 50 videos at fal). It is slower than SORA (~3 minutes for a 720p video) but faster than replicate's hunyuan (by 6-7x for the same settings).

https://fal.ai/models/fal-ai/hunyuan-video

Re: Sora is here

#247

Post by RyeCombinator »

lacoolj wrote: post #235

A little worried how young children watching these videos may develop inaccurate impressions of physics in nature. For instance, that ladybug looks pretty natural, but there's a little glitch in there that an unwitting observer, who's never seen a ladybug move before, may mistake as being normal. And maybe it is! And maybe it isn't? The sailing ship - are those water movements correct? The sinking of the elephant int…

I share your concern as well and at times worry about what I'm seeing too.

I suppose the reminder here is that seeing does not warrant believing.

Re: Sora is here

#248

Post by lacoolj »

MyFirstSass wrote: post #61

Wow this is bad. And by bad i mean worse than leading open source and existing alternatives. Is it me or does it seem like OpenAI revolutionized with both chatGPT and Sora, but they've completely hit the ceiling? Honestly a bit surprised it happened so fast!

If you're going to say something like this, you need to back it up with specific alternatives that provide a better result.

Besides just citing your sources, I'm genuinely curious what the best ones are for this so I can see the competition :)

Re: Sora is here

#249

Post by darepublic »

lacoolj wrote: post #235

A little worried how young children watching these videos may develop inaccurate impressions of physics in nature. For instance, that ladybug looks pretty natural, but there's a little glitch in there that an unwitting observer, who's never seen a ladybug move before, may mistake as being normal. And maybe it is! And maybe it isn't? The sailing ship - are those water movements correct? The sinking of the elephant int…

Sure this is problematic for society although I'm not concerned about what you are mentioning. I remember as a kid noticing how in looney tunes wile e coyote could run off the cliff a few steps and thinking maybe there's a way to do that. Or kids arguing about whether it was possible to perform a sonic boom like in street fighter. Or jumping off the playground with an umbrella etc

Re: Sora is here

#250

Post by Stevvo »

petercooper wrote: post #51

I wonder what it is about EU and UK law, in particular, that restricts its availability there. Their FAQs don't mention this. If it's about training models on potentially personal information, the GDPR (EU and UK variants) kicks in, but then that hasn't restricted OpenAI's ability to deploy (Chat)GPT there. The same applies to broader copyright regulations around platforms needing to proactively prevent copyright vio…

It's a capacity related constraint, not a legal one.
Post reply on HN