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

Stable Video Diffusion

stability.ai

Post reply on HN
Print view View original

41–50 of 316 posts

Re: Stable Video Diffusion

#41

Post by yorwba »

ericpauley wrote: post #8

I'm still puzzled as to how these "non-commercial" model licenses are supposed to be enforceable. Software licenses govern the redistribution of the software , not products produced with it. An image isn't GPL'd because it was produced with GIMP.

The license is a contract that allows you to use the software provided you fulfill some conditions. If you do not fulfill the conditions, you have no right to a copy of the software and can be sued. This enforcement mechanism is the same whether the conditions are that you include source code with copies you redistribute, or that you may only use it for evil, or that you must pay a monthly fee. Of course this enforcement mechanism may turn out to be ineffective if it's hard to discover that you're violating the conditions.

Re: Stable Video Diffusion

#42

Post by valine »

Der_Einzige wrote: post #37
valine wrote: post #7

The rate of progress in ML this past year has been breath taking. I can’t wait to see what people do with this once controlnet is properly adapted to video. Generating videos from scratch is cool, but the real utility of this will be the temporal consistency. Getting stable video out of stable diffusion typically involves lots of manual post processing to remove flicker.

Controlnet is adapted to video today, the issues are that it's very slow. Haven't you seen the insane quality of videos on civitai?

I have seen them, the workflows to create those videos are extremely labor intensive. Control net lets you maintain poses between frames, it doesn’t solve the temporal consistency of small details.

Re: Stable Video Diffusion

#43

Post by nottheengineer »

FrozenTuna wrote: post #28
kshacker wrote: post #24

Earlier quoted context omitted.

Assuming we can post links, you mean this video: https://youtu.be/G7mihAy691g?si=o2KCmR2Uh_97UQ0N Also, maybe you can't edit post facto, but when you give prompts, would you not be able to say : two blue jays but no CN tower

Yes, its called a negative prompt. Idk if txt2video has it, but both llms and stable-diffusion have it so I'd assume its good to go.

Haven't implemented negative prompts yet, but from what I can tell it's as simple as substracting from the prompt in embedding space.

Re: Stable Video Diffusion

#44

Post by littlethoughts »

cubefox wrote: post #13
ericpauley wrote: post #8

I'm still puzzled as to how these "non-commercial" model licenses are supposed to be enforceable. Software licenses govern the redistribution of the software , not products produced with it. An image isn't GPL'd because it was produced with GIMP.

Nobody claimed otherwise?

Fantasy.ai was subject to controversy for attempting to license models.

Re: Stable Video Diffusion

#46

Post by accrual »

dinvlad wrote: post #15

Seems relatively unimpressive tbh - it's not really a video, and we've seen this kind of thing for a few months now

It seems like the breakthrough is that the video generating method is now baked into the model and generator. I've seen several fairly impressive AI animations as well, but until now, I assumed they were tediously cobbled together by hacking on the still-image SD models.

Re: Stable Video Diffusion

#47

Post by dist-epoch »

ericpauley wrote: post #8

I'm still puzzled as to how these "non-commercial" model licenses are supposed to be enforceable. Software licenses govern the redistribution of the software , not products produced with it. An image isn't GPL'd because it was produced with GIMP.

Visual Studio Community (and many other products) only allows "non-commercial" usage. Sounds like it limits what you can do with what you produce with it.

At the end of the day, a license is a legal contract. If you agree that an image which you produce with some software will be GPL'ed, it's enforceable.

As an example, see the Creative Commons license, ShareAlike clause:

> If you remix, transform, or build upon the material, you must distribute your contributions under the same license as the original.

Re: Stable Video Diffusion

#48

Post by 2-718-281-828 »

spaceman_2020 wrote: post #29

A seemingly off topic question, but with enough compute and optimization, could you eventually simulate “reality”? Like, at this point, what are the technical counters to the assertion that our world is a simulation?

> Like, at this point, what are the technical counters to the assertion that our world is a simulation?

How about this theory is neither verifiable nor falsifiable.

Post reply on HN