Live data from Hacker News

Veo 2: Our video generation model

deepmind.google

1–10 of 342 posts

Re: Veo 2: Our video generation model

#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

Re: Veo 2: Our video generation model

#4
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.

Re: Veo 2: Our video generation model

#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 volunteer red-teaming to be done by the public on other services like hailuoai.video yet.

P.S. The skate tricks in the final video are delightfully insane.

Re: Veo 2: Our video generation model

#7
Winning 2:1 in user preference versus sora turbo is impressive. It seems to have very similar limitations to sora. For example- the leg swapping in the ice skating video and the bee keeper picking up the jar is at a very unnatural acceleration (like it pops up). Though by my eye maybe slightly better emulating natural movement and physics in comparison to sora. The blog post has slightly more info:

>at resolutions up to 4K, and extended to minutes in length.

https://blog.google/technology/google-labs/video-image-gener...

Re: Veo 2: Our video generation model

#9
My theory as to why all the bigtech companies are investing so much money in video generation models is simple: they are trying to eliminate the threat of influencers/content creators to their ad revenue.

Think about it, almost everyone I know rarely clicks on ads or buys from ads anymore. On the other hand, a lot of people including myself look into buying something advertised implicitly or explicitly by content creators we follow. Say a router recommended by LinusTechTips. A lot of brands started moving their as spending to influencers too.

Google doesn't have a lot of control on these influencers. But if they can get good video generations models, they can control this ad space too without having human in the loop.

Re: Veo 2: Our video generation model

#10
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

> Judging by how they've been trying to ram AI into YouTube creators workflows […]

Thanks for sharing that video and post!

One way to think about this stuff is to imagine that you are 14 and starting to create videos, art, music, etc in order to build a platform online. Maybe you dream of having 7 channels at the same time for your sundry hobbies and building audiences.

For that 14 year old, these tools are available everywhere by default and are a step function above what the prior generation had. If you imagine these tools improving even faster in usability and capability than prior generations' tools did …

If you are of a certain age you'll remember how we were harangued endlessly about "remix culture" and how mp3s were enabling us to steal creativity without making an effort at being creative ourselves, about how photobashing in Photoshop (pirated cracked version anyway) was not real art, etc.

And yet, halfway through the linked video, the speaker, who has misgivings, was laughing out loud at the inventiveness of the generated replies and I was reminded that someone once said that one true IQ test is the ability to make other humans laugh.

Post reply on HN