Live data from Hacker News

Imagen Video: high definition video generation with diffusion models

imagen.research.google

21–30 of 500 posts

Re: Imagen Video: high definition video generation with diffusion models

#21

"We have decided not to release the Imagen Video model or its source code until these concerns are mitigated" Okay then why even post it in the first place? What exactly is Google going to do with this model?

Indeed, it's almost just a flex? "Oh yeah, we can do better! No, no one can use it, ever."

Re: Imagen Video: high definition video generation with diffusion models

#22

"We have decided not to release the Imagen Video model or its source code until these concerns are mitigated" Okay then why even post it in the first place? What exactly is Google going to do with this model?

Ask the "AI Ethicists". They have to justify their salaries in some way or another. Or maybe Google is using "Responsible AI" as an excuse to minimize competitors when they release their own Imagen Video as a Service API in Google Cloud. It's quite strange when the "ethical" thing to do is to not publicly release your research, put it behind a highly restrictive API and charge a high price for it ($0.02 per 1k tokens…

This, 100%

The word "ethics" has become very flexible...

Re: Imagen Video: high definition video generation with diffusion models

#23

"We have decided not to release the Imagen Video model or its source code until these concerns are mitigated" Okay then why even post it in the first place? What exactly is Google going to do with this model?

Even just giving out high quality research papers helps a lot, so it's still great thing that they published it.

Re: Imagen Video: high definition video generation with diffusion models

#25
post #18

Someone can explains the tech limitation of the size ( 512*512 ) for those AI generated arts?

byte alignment has always been a consideration for high performance computing.

this alludes to a fascinating, yet elementary, fact about computer science to me: there’s a physical atomic constraint in every algorithm.

Re: Imagen Video: high definition video generation with diffusion models

#26

"We have decided not to release the Imagen Video model or its source code until these concerns are mitigated" Okay then why even post it in the first place? What exactly is Google going to do with this model?

Why post? to show methods and their capabilities. Also flex.

What will they do with model? figure out how to prevent abuse and incorporate into future Google Assistant, Photos and AR offerings.

Re: Imagen Video: high definition video generation with diffusion models

#29

I’m going to post an Ask HN about what am I supposed to do when I’m “disrupted”. I work in film / video / CG where the bread and butter is short form advertising for Youtube, Instagram and TV. It’s painfully obvious that in 1 year the job might be exceedingly more difficult than it is now.

When you animate a horse, does it have 5 legs with weird backwards joints? If not, your job is probably safe for now.
Post reply on HN