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

Video to video with Stable Diffusion

stable-diffusion-art.com

Post reply on HN
Print view View original

51–60 of 110 posts

Re: Video to video with Stable Diffusion

#51

Post by washadjeffmad »

Kuinox wrote: post #27
andybak wrote: post #14

Earlier quoted context omitted.

automatic1111 isn't what immediately springs to mind when I hear the phrase "UI simplicity"

ComfyUI allow you to design your own workflow. It also mean understanding how things works, it's far harder to use than automatic1111 UI.

Comfy is harder if you've only used gradio, just like Blender's modal interface was "too complicated" if you'd only used Autodesk products.

Each has its strengths, but I do wonder whether I'd feel automatic1111 was too random and restrictive if Comfy had been released first.

Re: Video to video with Stable Diffusion

#52

Post by nialv7 »

DrSiemer wrote: post #7

Not going to bother with this until the temporal cohesion issue is solved. The results are cool, but the variety in frames makes it look like a very specific and distracting art style instead of true animation.

NVIDIA has already published something that solves the coherence problem, and IIUC it's even based on stable diffusion. Hopefully the community will reproduce it soon.

https://research.nvidia.com/labs/toronto-ai/VideoLDM/

Re: Video to video with Stable Diffusion

#53

Post by j_not_j »

dist-epoch wrote: post #44
hospitalJail wrote: post #43

Earlier quoted context omitted.

You'd expect manufacturing costs to go down.

Most of the cost is in CPU/GPU/RAM.

Ahh, most of the cost is RAM. Then GPU then CPU.

Look at a Dell or HP server configurator website to see why.

If you "only" need GPU, a craigslist search should find a less expensive 2 or 3yo server to plug your latest GPU into.

Re: Video to video with Stable Diffusion

#55

Post by swayvil »

That first video is fabulous. It reminds me of a standard trope in generative art : You generate a whole bunch of prospective images and then pick the nicest ones.

Except in this case we get to see all the prospects (The variations in chestplate, wings etc). And in such a cool style.

Re: Video to video with Stable Diffusion

#56

Post by llm_nerd »

colordrops wrote: post #8
DrSiemer wrote: post #7

Not going to bother with this until the temporal cohesion issue is solved. The results are cool, but the variety in frames makes it look like a very specific and distracting art style instead of true animation.

Did you scroll down and see the different methods used, specifically method 5? Not perfect, but getting pretty close.

The last one is largely the original video with a cartoon filter and basically anime facetune. It is educational and interesting, but it looks the best because it's actually doing the least, though even then you get the temporal artifacts on the hair and so on.

It is improving super rapidly and it will be a pretty seamless soon enough in all likelihood. We are in the intermediate stage right now, and the results are going to be incredible.

Re: Video to video with Stable Diffusion

#57

Post by civilitty »

rvcdbn wrote: post #47
hospitalJail wrote: post #36

I was going to get a 4090 this year, but I just don't think 24gb VRAM is going to bee enough in the short term future(for AI related stuff). Ended up getting a 3060 for 1/4 of the cost, and I'm planning on using/paying for Colab until some 6090 comes out with 128gb vram. Something that kind of bothers me that I don't understand. Why is there such an obsession about having small computers/servers? I don't care if I ha…

Why wouldn’t you use colab for nsfw? Do you really not trust Google Cloud that much? Or do they have some kind of policy I’m not aware of (can’t imagine how they would enforce this)?

Google Cloud really freaks out when you ask it to do weird stuff with porcupines.

My wife and I just want to do weird stuff with porcupines, damnit!

Re: Video to video with Stable Diffusion

#58

Post by hospitalJail »

rvcdbn wrote: post #47
hospitalJail wrote: post #36

I was going to get a 4090 this year, but I just don't think 24gb VRAM is going to bee enough in the short term future(for AI related stuff). Ended up getting a 3060 for 1/4 of the cost, and I'm planning on using/paying for Colab until some 6090 comes out with 128gb vram. Something that kind of bothers me that I don't understand. Why is there such an obsession about having small computers/servers? I don't care if I ha…

Why wouldn’t you use colab for nsfw? Do you really not trust Google Cloud that much? Or do they have some kind of policy I’m not aware of (can’t imagine how they would enforce this)?

Yes, I don't trust any offsite stuff. (Remember PRISM?)

Me and my wife aren't even that obsessed with nudity and stuff, but given how nsfw stuff comes up in media and politics, I'll keep it offline until nudist colonies are the norm.

Re: Video to video with Stable Diffusion

#59

Post by dmingod666 »

rvcdbn wrote: post #47
hospitalJail wrote: post #36

I was going to get a 4090 this year, but I just don't think 24gb VRAM is going to bee enough in the short term future(for AI related stuff). Ended up getting a 3060 for 1/4 of the cost, and I'm planning on using/paying for Colab until some 6090 comes out with 128gb vram. Something that kind of bothers me that I don't understand. Why is there such an obsession about having small computers/servers? I don't care if I ha…

Why wouldn’t you use colab for nsfw? Do you really not trust Google Cloud that much? Or do they have some kind of policy I’m not aware of (can’t imagine how they would enforce this)?

You apparently can't use anything to do with automatic-111 webui from colab, don't remember the exact restriction but I hear even if you do a simple, print with the word it freaks out..

Re: Video to video with Stable Diffusion

#60

Post by dmingod666 »

andybak wrote: post #12
DrSiemer wrote: post #7

Not going to bother with this until the temporal cohesion issue is solved. The results are cool, but the variety in frames makes it look like a very specific and distracting art style instead of true animation.

Mark my words. In a few years people will be writing filters and trying to figure out how to recreate the look of early AI animation.

Or they could just use the models we are using right now and get the same effect, not like the models are going away anywhere
Post reply on HN