Why does the mask need to be binary?
Surely it's possible to have a full alpha mask, such that 50% alpha means "push the diffusion process towards this value, but don't force it to generate this value".
Surely it's possible to have a full alpha mask, such that 50% alpha means "push the diffusion process towards this value, but don't force it to generate this value".
Just over-expand the mask and let stable diffusion decide what it's going to keep and what it's going to replace.