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

Took a lot of failed experiments, the model would keep converging to greyscale / sepia images. Think one of the ways I fixed was by adding an greyscale encoder to the arch. Used its output embedding as additional conditioning. Can't remember if I only added it to the Unet input or injected it during various stages of the unet down pass.


Think the final training run was only a couple hours on a Colab V100




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: