Closed pingren closed 1 year ago
The JINA executor use PIL to load input image which the color space is RGB. While official GFPGAN use cv2 to load image with default BGR color space.
This will cause upscaled image color looks sightly different from original and usually the face becomes pale. For example:
Using cv2.cvtColor will convert the color space to match the official implementation.
cv2.cvtColor
Thanks for the contribution @pingren
The JINA executor use PIL to load input image which the color space is RGB. While official GFPGAN use cv2 to load image with default BGR color space.
This will cause upscaled image color looks sightly different from original and usually the face becomes pale. For example:
Using
cv2.cvtColor
will convert the color space to match the official implementation.