a53769 opened this issue 2 years ago · 1 comments
I see, some codes had already written at stable_diffusion.py, but if use input_mask param directly It cause a error in runtime.
The input_mask param is the path to your mask file and should be used together with input_image. The mask is a single-channel uint8 array with two dimensions.
Could you try this colab example and see if that works？