Faceswap Forum

Hello,

Just a stupid question:
Being a fan of classic movies... most of which in Black and White... would it be reasonable to create a simpler neural network (trainer) working on a single luminance channel, instead of full RGB ?

Would it be ...let's say feasible in this way to trade the infos usually needed for the other two colors in a higher resolution/greater speed ?

Just a question... I am still a newbye, but ...curious.

Yes it's possible in theory, in reality black and white has less information to go off of and tends to require more model space to get a good result, so it's usually just as good to use RGB.