Hacker News new | ask | show | jobs
by it_citizen 566 days ago
Looking at the examples here: https://x.com/kimmonismus/status/1861450051085545880

It seems pretty underwhelming compared to what was shown in early 2024 no?

7 comments

There's a bunch of commercial options live right now that have comparable results. Not sure what all the hype is about, here are a few:

https://runwayml.com/

https://klingai.com/

https://hailuoai.video/

https://lumalabs.ai/

https://pika.art/

https://viggle.ai/

I don't think it's worse, just that the standards moved up, the expectations are now much higher. Sam forgot YC's advice to launch fast.
Apparently they only had access to the light/turbo model, not the full one.
Source for this claim? I've never heard it before.
> It seems pretty underwhelming compared to what was shown in early 2024 no?

People seem to have five fingers so I would say that as a win.

Yeah, for all the talk of Sora building an internal “world model” that could be a building block for AGI… this seems to suffer from all the same glitches as the Will Smith spaghetti video, just with much, much more polish.

I don’t think it’s that much worse than what OpenAI showed off earlier in the year when you consider that those examples were very cherry-picked, though. These new videos don’t make it seem like a bad model, they’re just a bit more realistically mediocre.

Anyone who works closely with diffusion models knows the "world model" thing was hype. Diffusion models are really good at faking, starting with nonsensical large-scale structure and forcing it towards plausibility with lots of nice details.
Yeah, I'm struggling to understand what the use case of this is. These videos aren't tricking anybody who's used a cameraphone. Just shooting video with phone costs nearly nothing. People don't particularly seem to want to generate films of places they aren't.
Wow yeah. The pixelation makes it hard but chopstick pens, pages moving, cars crossing over eachother.

Demo's gonna demo.