Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.
Hello！Dear @Sanster
The mask image generated by the app works better than the mask image generated by my code：mask = cv2.circle(mask, (int(x), int(y)), int(radius), (255, 255, 255), -1)
Did you use anything else？
original image：app mask：app effect：custom mask：code：mask = cv2.circle(mask, (int(x), int(y)), int(radius), (255, 255, 255), -1) generate custom mask：You can download this mask image with original image to reproducecustom effect：
At first glance, it feels like there is no big difference between these two masks, but the result is too different
Hello！Dear @Sanster The mask image generated by the app works better than the mask image generated by my code：mask = cv2.circle(mask, (int(x), int(y)), int(radius), (255, 255, 255), -1) Did you use anything else？ original image：
app mask：
app effect：
custom mask：
code：mask = cv2.circle(mask, (int(x), int(y)), int(radius), (255, 255, 255), -1) generate custom mask：
You can download this mask image with original image to reproduce
custom effect：
At first glance, it feels like there is no big difference between these two masks, but the result is too different
我感觉本质上是由于app和自己写的代码产生的mask不一样引起的，自己产生mask的圆会叠加，但不清楚为什么叠加了就会出问题，叠加后不还是白色的吗？。。。