They are bad because they explicitly filtered out faces from the training data. | Hacker News

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

		dannyw on Aug 31, 2022 \| parent \| context \| favorite \| on: Stable Diffusion is a big deal They are bad because they explicitly filtered out faces from the training data.

andybak on Aug 31, 2022 [–]

Not true of SD

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