Live data from Hacker News

Sora is here

openai.com

131–140 of 1001 posts

Re: Sora is here

#131
Genuinely curious who is doing this for adult content?

Complaints about Sora's quality and prompt complexity likely not as important to auteur's in that category, especially with ability to load a custom character etc

Re: Sora is here

#133

Earlier quoted context omitted.

Real artists struggle matching vague descriptions of what is in your head too. This is at least quicker?

Real artists take comic book scripts and turn them into actual comic books every month. They may not match exactly what the writer had in mind, but they are fit for purpose.

> They may not match exactly what the writer had in mind, but they are fit for purpose.

That's what GenAI is doing, too. After all, the audience only sees the final product; they never get know what the writer had in mind.

Re: Sora is here

#135
I feel like there is a sweet spot for AI generation of images and videos that I would describe as "charmingly bad", like the stuff we got from the old CLIP+VQGAN models. I feel like Sora has jumped past that into the valley of "unappealingly bad".

Re: Sora is here

#137

I hope somebody pays 100.000 pro subscriptions and uses AI to request Sora to generate videos 24/7. Maybe Elon? Even if they use queues, I'm sure they are running at a loss and the GPU time is going to cost 100x more than what they charge. Creating false demand for AI can easily bankrupt their business, as they will believe people actually want to use that crap for that purpose.

Deliberately wasting electricity isn't exactly a moral win.

Re: Sora is here

#138

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!

What are the leading alternatives? (Open source or otherwise)

MidJourney (commercial), Standard Diffusion XL

Re: Sora is here

#139

Earlier quoted context omitted.

The adage "a picture is worth a thousand words" has the nice corollary "A thousand words isn't enough to be precise about an image". Now expand that to movies and games and you can get why this whole generative-AI bubble is going to pop.

> Now expand that to movies and games and you can get why this whole generative-AI bubble is going to pop. What will save it is that, no matter how picky you are as a creator, your audience will never know what exactly was that you dreamed up, so any half-decent approximation will work. In other words, a corollary to your corollary is, "Fortunately, you don't need them to be, because no one cares about low-order bits…

> What will save it is that, no matter how picky you are as a creator, your audience will never know what exactly was that you dreamed up, so any half-decent approximation will work.

Part of the problem is the "half decent approximations" tend towards a clichéd average, the audience won't know that the cool cyberpunk cityscape you generated isn't exactly what you had in mind, but they will know that it looks like every other AI generated cyberpunk cityscape and mentally file your creation in the slop folder.

I think the pursuit of fidelity has made the models less creative over time, they make fewer glaring mistakes like giving people six fingers but their output is ever more homogenized and interchangable.

Re: Sora is here

#140
post #52

MKBHD's review of the new Sora release: https://www.youtube.com/watch?v=OY2x0TyKzIQ

Interesting to see how bad the physics/object permanence is. I wonder if combining this with a Genie 2 type model (Google's new "world model") would be the next step in refining it's capabilities.

This feels like computer graphics and the 'screen space' techniques that got introduced in the Xbox 360 generation - reflection, shadows etc. all suffered from the inability to work with off screen information and gave wildly bad answers once off screen info was required.

The solution was simple - just maintain the information in world space, and sample for that. But simple does not mean cheap, and it led to a ton of redundant (as in invisible in the final image) having to be kept track of.

Post reply on HN