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

One was more parameters, sure.

More training on fingers specifically.

Image VAEs (variation auto encoders) are functions that compress the latent (working) image down. The earlier VAEs would mess up fine details. At a most basic level, just picture compression issues.

Training against bad previous work with six fingers.

Models working in 1024 instead of 512.



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

Search: