Multiple masks cause confused output

[darshats]

Hi, Thanks for providing this amazing capability for SD!

I had a question for multiple objects placed in the image. Sometimes I'm finding if two masks are provided for the image inpainting (via canny or segments) it causes confused output. For example, a canny outline for an apple and a canny outline for a succulent plant is given. Once inpainting is done it will at times try to squeeze the green plant into the apple. At times it may not draw the second object at all.

Was training done with multiple objects provided? And is there a way to better achieve this? Thanks!