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

31–40 of 316 posts

Re: Stable Video Diffusion

#31

Post by not2b »

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?

There are sites that make Stable Diffusion-derived models available, along with GPU resources, and they sell the service of generating images from the models. The company isn't permitting that use, and it seems that they could find violators and shut them down.

Re: Stable Video Diffusion

#32

Post by accrual »

christkv wrote: post #10

Looks like I'm still good for my bet with some friends that before 2028 a team of 5-10 people will create a blockbuster style movie that today costs 100+ million USD on a shoestring budget and we won't be able to tell.

The first full-length AI generated movie will be an important milestone for sure, and will probably become a "required watch" for future AI history classes. I wonder what the Rotten Tomatoes page will look like.

Re: Stable Video Diffusion

#33

Post by xianshou »

btbuildem wrote: post #11

In the video towards the bottom of the page, there are two birds (blue jays), but in the background there are two identical buildings (which look a lot like the CN Tower). CN Tower is the main landmark of Toronto, whose baseball team happens to be the Blue Jays. It's located near the main sportsball stadium downtown. I vaguely understand how text-to-image works, and so it makes sense that the vector space for "blue j…

Emu edit should be exactly what you're looking for: https://ai.meta.com/blog/emu-text-to-video-generation-image-...

Re: Stable Video Diffusion

#34

Post by epiccoleman »

This is really, really cool. A few months ago I was playing with some of the "video" generation models on Replicate, and I got some really neat results[1], but it was very clear that the resulting videos were made from prompting each "frame" with the previous one. This looks like it can actually figure out how to make something that has a higher level context to it.

It's crazy to see this level of progress in just a bit over half a year.

[1]: https://epiccoleman.com/posts/2023-03-05-deforum-stable-diff...

Re: Stable Video Diffusion

#35

Post by gorbypark »

torginus wrote: post #22

I admit I'm ignorant about these model's inner workings, but I don't understand why text is the chosen input format for these models. It was the same for image generation, where one needed to produce text prompts to create the image, and stuff like img2img and Controlnet that allowed things like controlling poses and inpainting, or having multiple prompts with masks controlling which part of the image is influenced b…

According to the GitHub repo this is an "image-to-video model". They tease of an upcoming "text to video" interface on the linked landing page, though. My guess is that interface will use a text-to-image model and then feed that into the image-to-video model.

Re: Stable Video Diffusion

#36

Post by Der_Einzige »

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.

They're not enforceable.

Re: Stable Video Diffusion

#37

Post by Der_Einzige »

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?

Re: Stable Video Diffusion

#39

Post by accrual »

youssefabdelm wrote: post #18

Can't wait for these things to not suck

It's definitely pretty impressive already. If there could be some kind of "final pass" to remove the slightly glitchy generative artifacts, these look completely passible for simple .gif/.webm header images. Especially if they could be made to loop smoothly ala Snapchat's bounce filter.

Re: Stable Video Diffusion

#40

Post by refulgentis »

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?

A little too freshman's first bit off a bong for me. There is, of course, substantial differences between video and reality.

Let's steel-man — you mean 3D VR. Let's stipulate there's a headset today that renders 3D visually indistinguishable from reality. We're still short the other 4 senses

Much like faith, there's always a way to sort of escape the traps here and say "can you PROVE this is base reality"

The general technical argument against "brain in a vat being stimulated" would be the computation expense of doing such, but you can also write that off with the equivalent of foveated rendering but for all senses / entities

Post reply on HN