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

Veo 2: Our video generation model

deepmind.google

Post reply on HN
Print view View original

21–30 of 342 posts

Re: Veo 2: Our video generation model

#22

Post by ilaksh »

zb3 wrote: post #3

We should collectively ignore these announcements of unavailable models. There are models you can use today, even in the EU.

Actually there is a pretty significant new model announced today and available now: "MiniMax (Hailuo)Video-01-Live" https://blog.fal.ai/introducing-minimax-hailuo-video-01-live...

Although I tried that and it has the same issue all of them seem to have for me: if you are familiar with the face but they are not really famous then the features in the video are never close enough to be able to recognize the same person.

Re: Veo 2: Our video generation model

#24

Post by PittleyDunkin »

turnsout wrote: post #14
larodi wrote: post #4

Earlier quoted context omitted.

And then suddenly this is not something that fascinates people anymore… in 10 years as non-synthetic becomes the new bio or artisan or whatever you like. Humanity has its ways of objecting accelerationism.

Put another way, over time people devalue things which can be produced with minimal human effort. I suspect it's less about humanity's values, and more about the way money closely tracks "time" (specifically the duration of human effort).

https://en.wikipedia.org/wiki/Labor_theory_of_value

Re: Veo 2: Our video generation model

#26

Post by gom_jabbar »

larodi wrote: post #4
jsheard wrote: post #2

Judging by how they've been trying to ram AI into YouTube creators workflows I suppose it's only a matter of time before they try to automate the entire pipeline from idea, to execution, to "engaging" with viewers. It won't be good at doing any of that but when did that ever stop them. https://www.youtube.com/watch?v=26QHXElgrl8 https://x.com/surri01/status/1867433782992879617

And then suddenly this is not something that fascinates people anymore… in 10 years as non-synthetic becomes the new bio or artisan or whatever you like. Humanity has its ways of objecting accelerationism.

Sure, humanity has its ways of objecting Accelerationism, but the process fundamentally challenges human identity:

"The Human Security System is structured by delusion. What's being protected there is not some real thing that is mankind, it's the structure of illusory identity. Just as at the more micro level it's not that humans as an organism are being threatened by robots, it's rather that your self-comprehension as an organism becomes something that can't be maintained beyond a certain threshold of ambient networked intelligence." [0]

See also my research project on the core thesis of Accelerationism that capitalism is AI. [1]

[0] https://syntheticzero.net/2017/06/19/the-only-thing-i-would-...

[1] https://retrochronic.com/

Re: Veo 2: Our video generation model

#27

Post by echelon »

xnx wrote: post #6

This looks great, but I'm confused by this part: > Veo sample duration is 8s, VideoGen’s sample duration is 10s, and other models' durations are 5s. We show the full video duration to raters. Could the positive result for Veo 2 mean the raters like longer videos? Why not trim Veo 2's output to 5s for a better controlled test? I'm not surprised this isn't open to the public by Google yet, there's a huge amount of volu…

> I'm not surprised this isn't open to the public by Google yet,

Closed models aren't going to matter in the long run. Hunyuan and LTX both run on consumer hardware and produce videos similar in quality to Sora Turbo, yet you can train them and prompt them on anything. They fit into the open source ecosystem which makes building plugins and controls super easy.

Video is going to play out in a way that resembles images. Stable Diffusion and Flux like players will win. There might be room for one or two Midjourney-type players, but by and large the most activity happens in the open ecosystem.

Post reply on HN