YangyangXu comments

Results 8 comments of


                                            YangyangXu

Confusion about training results

I meet the same error, I believe this implementation contains many bugs and it will leads us to a wrong way.

Add more pretrain model

> We have tried the style of Anime, but the results are not satisfactory. For those styles that are far from the real faces, the correspondence beween the inputs and...

Add more pretrain model

> My checkpoint is trained with color transfer. You need not specify `--fix_color` during training and testing Thanks for your reply, I train the model without `--fix_color`, but the log...

Add more pretrain model

Thanks for your suggestion, I have trained the anime model on DualStylegan following your suggestion. By the way, I also train Vtoonify based on toonify generator, without mixing shadow and...

pytorch version

Pytorch=1.8.0, thanks for your interest.

关于pSp Encoder生成W+ latent space embedding

Thanks for your interest, we use the StyleGAN inversion checkpoint (https://drive.google.com/file/d/1bMTNWkh5LArlaWSc_wa8VKyq2V42T2z0/view). Note that you need to align the faces before inversion.

关于pSp Encoder生成W+ latent space embedding

> > Thanks for your interest, we use the StyleGAN inversion checkpoint (https://drive.google.com/file/d/1bMTNWkh5LArlaWSc_wa8VKyq2V42T2z0/view). Note that you need to align the faces before inversion. > > Hi, tanks for your reply!...

Hello, what does smooth-mask in test.py file stand for? I didn't find the answer in the paper or the code.

Thanks for your careful comment, you can ignore the smooth-mask, it's useless in test.py.