Scribble-guided editing
wileewang opened this issue · 2 comments
Hi! I wonder if a loss such as MSE or LPIPS is used between the user-provided scribbles and the scribbled regions of
Hi,
Thank you for your interest in our work.
No - there is no need for MSE/LPIPS loss, the only signal for the scribbles comes from the partial nosing of the image (i.e. to noise the image to a certain noise level).
The shapes and the colors stay somewhat consistent because of the why the diffusion model operates - the initial stages generate a rough sketch of the image and the finer details are added later, so we can noise the image up to the point that preserves the colors/shapes. For more details please see Figure 32 in the paper.
I see. Thanks for your reminding.