Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

> very capable models

Well that's the problem though, those models don't come any close to being useful at all. At least not yet. And they also run much slower.

As compute increases in general, there will be larger and more capable state of the art models and it'll make more sense to just use those instead of trying to run some local one that won't give you any useful answers. Data centers will always have a few orders of magnitude more horsepower than your average laptop, even with some kind of inference accelerator card.



Stable diffusion isn't useful at all?


Do people use it for anything practical? Making stock photos maybe? I haven't really had a proper use case for it and all the random things I tried to make with it weren't good enough to use with anything. Could be useful for making concepts for real artists, but last I heard they were all too busy boycotting it.

Also, not an LLM.


> I haven't really had a proper use case for it and all the random things I tried to make with it weren't good enough to use with anything.

Sounds a lot like most of my early programming experiments…

Though I’ve heard on good authority that the early programmers looked past being able to calculate ballistic charts and have done some interesting things with these “computer” things.


There are some models that can generate tileable textures, for example.


Ah interesting yeah, found this one: https://replicate.com/tommoore515/material_stable_diffusion

Trying out some prompts, maybe last I used SD my mistake was going with a lower resolution to speed up generation. I literally cannot get this one to make anything that isn't a weird blob at 256px and lower, but at 512px it works fine? Weird that it's so resolution dependant. I guess some proper stuff can be made at 1024px and above.


SD basically doesnt function at 256px, it was trained on 512px


Not sure why they'd give the option to run at those resolutions then?


SD 1.1 was trained on 256x256 so, I guess it was left in there for backwards compatibility reasons.


How is running a LLM related to stable diffusion?

Your contention is that models will run on devices; but latent diffusion models have lower memory footprints (see: latent).

The hardware you need to run a good LLM is what, 10x more than a latent diffusion one?

They are not comparable.




Consider applying for YC's Fall 2026 batch! Applications are open till July 27.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: