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

151–160 of 316 posts

Re: Stable Video Diffusion

#151

Post by kaashif »

freedomben wrote: post #93
KineticLensman wrote: post #68

Earlier quoted context omitted.

(disclaimer: worked in the sim industry for 25 years, still active in terms of physics-based rendering). First off, there are zero technical proofs that we are in a sim, just a number of philosophical arguments. In practical terms, we cannot yet simulate a single human cell at the molecular level, given the massive number of interactions that occur every microsecond. Simulating our entire universe is not technically…

I don't think you would need to simulate the entire universe, just enough of it that the consciousness receiving sense data can't encounter any missing info or "glitches" in the metaphorical matrix. Still hard of course, but substantially less compute intensive than every molecule in the universe.

And you don't have to simulate it in real time, maybe 1 second here takes years or centuries to simulate outside the simulation. It's not like we'd have any way to tell.

Re: Stable Video Diffusion

#152

Post by nwienert »

evrenesat wrote: post #94
Chabsff wrote: post #50

Earlier quoted context omitted.

It's really not. Don't get me wrong, this is insanely cool, but it's still a long way from good enough to be truly disruptive.

In a few years' time, teenagers will be consuming shows and films made by their peers, not by streaming providers. They'll forgive and perhaps even appreciate the technical imperfections for the sake of uncensored, original content that fits perfectly with their cultural identity. Actually, when processing power catches up, I'm expecting a movie engine with well-defined characters, scenes, entities, etc., so people w…

They do that now (forget the name there's a popular one my niece uses to make animated comics, others do similar things in Minecraft etc), and have been doing that since forever - nearly 30 years ago my friends and I were scribbling comic panels into our notebooks and sharing them around class.

Re: Stable Video Diffusion

#153

Post by ronsor »

comex wrote: post #72
yorwba wrote: post #41

Earlier quoted context omitted.

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 enforce…

It also somewhat depends on open legal questions like whether models are copyrightable and, if so, whether model outputs are derivative works of the model. Suppose that models are not copyrightable, due to their not being the product of human creativity (this is debatable). Then the creator can still require people to agree to contractual terms before downloading the model from them, presumably including the usage li…

> Then the creator can still require people to agree to contractual terms before downloading the model from them, presumably including the usage limitations as well as an agreement not to redistribute the model to anyone else who does not also agree.

I don't think it's possible to invent copyright-like rights.

Re: Stable Video Diffusion

#154

Post by underscoring »

woeirua wrote: post #87
echelon wrote: post #63

Earlier quoted context omitted.

One year. All of Hollywood falls.

Every time something like this is released someone comments how it’s going to blow up legacy studios. The only way you can possibly think that is that: 1-the studios themselves will somehow be prevented from using this tech themselves, and 2-that somehow customers will suddenly become amenable to low grade garbage movies. Hollywood already produces thousands of low grade B or C movies every year that cost fractions o…

> 2-that somehow customers will suddenly become amenable to low grade garbage movies

People have been amenable to low grade garbage movies for a long, long time. See Adam Sandler's back catalog.

Re: Stable Video Diffusion

#155

Post by jowday »

epr wrote: post #104
TacticalCoder wrote: post #52

Earlier quoted context omitted.

> Has anyone come across a solution where model can iterate (eg, with prompts like "move the bicycle to the left side of the photo")? It feels like we're close. I feel like we're close too, but for another reason. For although I love SD and these video examples are great... It's a flawed method: they never get lighting correctly and there are many incoherent things just about everywhere. Any 3D artist or photographer…

> you'll describe something and you'll get a full 3D scene, with 3D models, source of lights set up, etc. I'm always confused why I don't hear more about projects going in this direction. Controlnets are great, but there's still quite a lot of hallucination and other tiny mistakes that a skilled human would never make.

There's a lot of issues with it, but perhaps the biggest is that there aren't just troves of easily scrapable and digestible 3D models lying around on the internet to train on top of like we have with text, images, and video.

Almost all of the generative 3D models you see are actually generative image models that essentially (very crude simplification) perform something like photogrammetry to generate a 3D model - 'does this 3D object, rendered from 25 different views, match the text prompt as evaluated by this model trained on text-image pairs'?

This is a shitty way to generate 3D models, and it's why they almost all look kind of malformed.

Re: Stable Video Diffusion

#157

Post by SXX »

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.

It doesn't have to be enforceable. This licensing model works exactly the same as Microsoft Windows licensing or WinRAR licensing. Lots and lots of people have pirated Windows or just buy some cheap keys off Ebay, but no one of them in their sane mind would use anything like that at their company.

The same way you can easily violate any "non-commercial" clauses of models like this one as private person or as some tiny startup, but company that decide to use them for their business will more likely just go and pay.

So it's possible to ignore license, but legal and financial risks are not worth it for businesses.

Re: Stable Video Diffusion

#158

Post by hackerlight »

kaashif wrote: post #151
freedomben wrote: post #93

Earlier quoted context omitted.

I don't think you would need to simulate the entire universe, just enough of it that the consciousness receiving sense data can't encounter any missing info or "glitches" in the metaphorical matrix. Still hard of course, but substantially less compute intensive than every molecule in the universe.

And you don't have to simulate it in real time, maybe 1 second here takes years or centuries to simulate outside the simulation. It's not like we'd have any way to tell.

These are all open questions in philosophy of mind. Nobody knows what causes consciousness/qualia so nobody knows if it's substrate dependent or not and therefore nobody knows if it can be simulated in a computer, or if it can nobody knows what type of computer is required for consciousness to be a property of the resulting simulation.

Re: Stable Video Diffusion

#159

Post by nwoli »

speedgoose wrote: post #86

Has anyone managed to run the thing? I got the streamlit demo to start after fighting with pytorch, mamba, and pip for half an hour, but the demo runs out of GPU memory after a little while. I have 24GB on GPU on the machine I used, does it need more?

Is the checkpoint default fp16 or fp32?

Re: Stable Video Diffusion

#160

Post by guyomes »

boppo1 wrote: post #111
epr wrote: post #104

Earlier quoted context omitted.

> you'll describe something and you'll get a full 3D scene, with 3D models, source of lights set up, etc. I'm always confused why I don't hear more about projects going in this direction. Controlnets are great, but there's still quite a lot of hallucination and other tiny mistakes that a skilled human would never make.

Blender files are dramatically more complex than any image format, which are basically all just 2D arrays of 3-value vectors. The blender filetype uses a weird DNA/RNA struct system that would probably require its own training run. More on the Blender file format: https://fossies.org/linux/blender/doc/blender_file_format/my...

Voxel files could be a simpler step for 3D images.
Post reply on HN