Given the approach, they'll probably come back with better reconstruction/decomp... | Hacker News

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

		bane on Sept 20, 2022 \| parent \| context \| favorite \| on: Stable Diffusion based image compression Given the approach, they'll probably come back with better reconstruction/decompression too.

pishpash on Sept 20, 2022 [–]

Not clear. Fully encoding the training images could not be a feasible aspect of a good auto-encoder.

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