ak9250

@HsiaoYingLu were you able to solve this issue, also got the same problem

@HsinYingLee have you tried few shot vid2vid?

@netolcc06 were you able to get the inference demo working? @xiaodongyang is the preprocess module correct?

@xiaodongyang see https://github.com/NVlabs/Dancing2Music/issues/1#issuecomment-626378974

@john-rocky ok, yes I am, what about this model https://github.com/Onr/Council-GAN the selfie2anime weights

@zhulei1228 have you tried https://github.com/shaoanlu/fewshot-face-translation-GAN it face swaps only needing a single image and facial expression is preserved

I cant even get it to run on a mac lol

@iperov good results, is your model few shot or does it have to be trained for each face pair?

@shaoanlu ok, can you please add mtcnn, i think it also reducing flickering/jittering as shown in your other face-swap gan repo. I will try it again by disabling draw_iris() thanks

tried it again  I changed the return aligned_face, colored_parsing_map, aligned_im, (x0, y0, x1, y1), landmarks to return the colored_parsing_map instead of the...