Surely you don't need to? Just over-expand the mask and let stable diffusion dec... | Hacker News

Hacker News new | past | comments | ask | show | jobs | submit

login

phire on Sept 19, 2022 | parent | context | favorite | on: Stable Diffusion Text-Prompt-Based Inpainting – Re...

Surely you don't need to?

Just over-expand the mask and let stable diffusion decide what it's going to keep and what it's going to replace.

XorNot on Sept 20, 2022 [–]

You'd effectively be trying to do a pixel-by-pixel diffusion strength parameter, which I'm not sure has a coherent interpretation to the algorithm (because it's currently a scalar applied to the run settings).

Consider applying for YC's Summer 2025 batch! Applications are open till May 13
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact