News for hackers. Stuff that matters.
Re:Imagen Video: high definition video generation with diffu... by jeffbee on Wednesday October 05, 2022 @02:13PM (#33099161)
When you animate a horse, does it have 5 legs with weird backwards joints? If not, your job is probably safe for now.
Re:Imagen Video: high definition video generation with diffu... by kranke155 on Wednesday October 05, 2022 @02:18PM (#33099218)
How long do you think until the horse looks perfect? 12 months? 5 years? I’m still 30 and I don’t see how my industry won’t be entirely disrupted by this within the next decade.

And that’s my optimistic projection. It could be we have amazing output in 24 months.

Re:Imagen Video: high definition video generation with diffu... by visarga on Wednesday October 05, 2022 @03:36PM (#33100305)
IT has been disrupting itself for six decades and there are more developers than ever, with high pay.
Re:Imagen Video: high definition video generation with diffu... by Vetch on Wednesday October 05, 2022 @06:16PM (#33101909)
Have to temper expectations with fact that a generated video of a thing is also a recording of a simulation of the thing. For long video, you'd want everything from temporal consistency and emotional affect maintenance to conservation of energy, angular momentum and respecting this or that dynamics.

A bunch of fields would be simultaneously impacted. From computational physics to 3D animation (if you have a 3D renderer and video generator, you can compose both). While it's not completely unfounded to extrapolate that progress will be as fast as with everything prior, consequences would be a lot more profound while complexities are much compounded. I down weight accordingly even though I'd actually prefer to be wrong.

Re:Imagen Video: high definition video generation with diffu... by bitL on Wednesday October 05, 2022 @02:58PM (#33099816)
It's not about random short clips - imagine introducing a character like Mickey Mouse and reusing him everywhere with the same character - my guess is it's going to take a while until "transfer" like that will work reliably.
Re:Imagen Video: high definition video generation with diffu... by fragmede on Wednesday October 05, 2022 @03:13PM (#33100013)
Dreambooth and Texual inversion is already here, and it's been just over a month since Stable Diffusion was released, so I'd bet on sooner rather than later.

https://github.com/XavierXiao/Dreambooth-Stable-Diffusion

https://textual-inversion.github.io/

Re:Imagen Video: high definition video generation with diffu... by spoonjim on Wednesday October 05, 2022 @02:31PM (#33099433)
Think about where this stuff was 2 years ago and then think about where it will be 2 years from now.
Re:Imagen Video: high definition video generation with diffu... by rcpt on Wednesday October 05, 2022 @02:44PM (#33099621)
Relationships between objects has been a problem with computer vision for a long time.

10 years ago: https://karpathy.github.io/2012/10/22/state-of-computer-visi...

Now: https://arxiv.org/pdf/2204.13807

Given that this is what makes photos and videos interesting I think it's still a while before artists are automated.

Re:Imagen Video: high definition video generation with diffu... by visarga on Wednesday October 05, 2022 @02:47PM (#33099676)
Take a look at Flamingo "solving" the joke: https://pbs.twimg.com/media/FSFwYL7WUAEgxqQ?format=jpg&name=...