Tao Zhong

@xinntao Thank you for sharing code Did GFPGAN1.3 also only use FFHQ datasets? I found that the generated teeth are very neat. 

I used the version of this repo's detection, all resource were depended on this repo.

And it seems that the latest mmdetection doesn't include the config file of cascade_rcnn_fpn_20e_sge_resnet101.py

Since I want use MobileStyleGAN to blend anime and real face models, like stylegan in toonify. But I found this feature become weakened, especially when I reduce the channels of...

Still have a question about Rt, since I use opencv Camera Cooradinate([right, down, forward]) as source pose, then for meeting the requirements of [ down, right, backwards ] which some...

Thank for your quick reply. I have another question. If I want to continue to improve the detail of face. For example, tattoos on the face, can you share some...

the same question, can anyone have explantion?

I have get a good result.   I use the code bellow, x is 68d face keypoint x = x / np.max(x) * 255 x -= np.mean(x)

Thank you for detailed and patient reply～ Yes, I add serveral custom picture, so I total use 189 pictures. Have you published the paper on arXiv about the single GPU...

> "the D_fake and D_real still drop to very small values after several steps", I get this training results too. But I thick that should mean the discriminator D is...