Ive been Starting to Train With deepfacelab and recently i just wanted to swap the Same Face to different pictures. Data_src has around 1500 faces but data_dst only one because its a picture. Do i really have to Train for several Hours to get a good Quality picture? After 18k its still pretty blurry so just photoshopping the Face would be so much faster. I dont Want to take 6hours of Training for one picture, isnt there a way to get Less Blurry faces? Because as mentioned photoshop would be so much faster and Not Blurry but i cant do That.
Discussions about research, Faceswapping and things that don't fit in the other categories here.
Firstly, this is the forum for Faceswap, not DFL, so you will get no support for DFL here.
Secondly, yes, it takes a long time. For quick single image face swaps, then photoshop is undoubtedly the better solution,
My word is final