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

Did you do any inpainting experiments? I can imagine a pixel-space diffusion model to be better at it than one with a latent auto-encoder.


Not yet, we focused on the architecture for this paper. I totally agree with you though - pixel space is generally less limiting than a latent space for diffusion, so we would expect good performance inpainting behavior and other editing tasks.




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

Search: