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

Their implementation appears to lose a lot of detail in many examples. This is especially true on human faces or pictures that include human faces. Can you reproduce an improvement there?


I didn't see any examples of human faces, can you link me to one? Happy to try it out and see the results.




Consider applying for YC's Summer 2026 batch! Applications are open till May 4

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

Search: