zlacker

[parent] [thread] 0 comments
1. angust+(OP)[view] [source] 2023-01-15 07:58:02
Stable diffusion (or any likelihood-based generative model) is a learned compression algorithm. It is not the "container of compressed bytes". You can use a trained generative model to compress images, by combining it with some kind of entropy coding / arithmetic coding.

In this sense, stable diffusion is more analogous to the JPEG algorithm than it is to a specific collection of JPEG files. As it stands, the originals trainng data is not stored, even in a compressed way.

[go to top]