News for hackers. Stuff that matters.
Re:Stable Diffusion based image compression by Gigachad on Tuesday September 20, 2022 @03:22AM (#32908707)
Do you also include the library to render a jpeg? And maybe the whole OS required to display it on your screen?

There are very many uses where any fixed overhead is meaningless. Imagine archiving billions of images for long term storage. The 4GB model quickly becomes meaningless.

Re:Stable Diffusion based image compression by 112233 on Tuesday September 20, 2022 @06:54AM (#32910073)
Fixed overheads are never meaningless. O(n^2) algorithm that processes your data in 5s is faster on your data than O(log n) that takes 20 hours.

Long term storage of billions of images is meaningless, if it takes billions of years to archive these images.

Re:Stable Diffusion based image compression by Gigachad on Tuesday September 20, 2022 @07:44AM (#32910400)
It’s a one time cost rather than per image. You need the 4GB model only once and then you can uncompress unlimited images.
Re:Stable Diffusion based image compression by 112233 on Tuesday September 20, 2022 @08:01AM (#32910527)
Yes, but each image needs access to this 4GB (actually, I have no idea how much RAM it takes up), plus whatever the working set size is. It is a non-trivial overhead that really limits throughput of your system, so you can process less images in parallel, so compressing billion of images in reasonable time suddenly may cost much more than the amount of storage it would save, compared to other methods.
Re:Stable Diffusion based image compression by stavros on Tuesday September 20, 2022 @04:48AM (#32909243)
> Do you also include the library to render a jpeg? And maybe the whole OS required to display it on your screen?

No, what does that have to do with reconstructing the original data?

If the fixed overhead works for you, that's fine, but including it is not meaningless.