Hi, I noticed that the image
and mask
are resized in the PowerPaintController
class:
input_image["image"] = input_image["image"].resize((H, W))
input_image["mask"] = input_image["mask"].resize((H, W))
I'm wondering: if I comment out or remove this resizing step, will it negatively affect the quality of the inpainting results?
Would it be possible for the model to still work effectively with the original image and mask resolutions?
Thanks in advance for your clarification!