fill masked area is actually smaller than the input mask

[whmc76]

Especially when I use the fill method, which will keep the pixels on the edge of the original image, it is difficult for me to change the color of a piece of clothing through this method. White clothes will always be filled with white pixels.

falloff should at least support negative input to offset the result of shrinking the mask range inward. If I want to fill the background color to change the image, this would be more reasonable.
In most cases, neutral will produce a relatively obvious boundary with the background edge.

i make a mask like this

but i got this

and this

i have to grow the mask to get expect result

[Acly]

You always get the fill where the mask is perfectly white. Outside of the area there is optional blending according to the falloff parameter.

So there is no shrinking, and negative falloff doesn't make sense. What you're seeing is that your mask has some smoothing and mask areas that aren't 100% white are not filled. This is intentional, to avoid any grey areas getting less than 100% denoise strength (it results in color skew and visible borders).

Using mask grow is a solution, or make sure your mask fully covers the area (without blur!) in the first place.

[whmc76]

Ok, thanks for your reply. This is reasonable. I'll take a look and optimize the pre-steps.