Hello and sorry, in advance, for the ignorance included in this message. I do a lot of work in the restoration and colourisation of photographic portraits of historical figures. After discovering artist Nathan Shipley's work using your code to 'reverse-toonify' historical portraits, I am quite despe...

Can you provide the model parameters trained on the dataset FFHQ with a resolution of 256?

pSp is a really great job for image to image translation. But there is a question that do you ever retrain the stylegan network for your applications (inversion, impainting, super-resolution)? I find that the stylegan model file you provide in your project is different from the NVIDIA official imple...

Hi, I'm working with the LSUN Horses dataset and I noticed that in the ReStyle repo there are pre-trained weights for the e4e encoder. Is there a straightforward way to use the e4e encoder from ReStyle repository to perform sketch-to-image translation in this repository? Thank you.

Thanks for your awesome works, I have a question about GAN inversion. I used the psp to do GAN inversion in anime domain(512x512 300k images), and used pre-trained anime StyleGAN2(512x512 ). After training 100,000 iteration with batch_size=4, I observed two problems. detaied structure of anime fa...

Hello, thank you very much for your research, when I trained the 16,000 images dataset with 2 GPUs with 24G memory, the training parameters were as follows. After a week of training the test images are as follows, I am wondering if any parameter is set wrong.

Hi, thank you for this excellent repo. I have unfortunately encountered an error when training a p2p StyleGAN inversion encoder using a custom StyleGAN model using the ResNetBackBoneEncoder as my default encoder type. This is my error as shown below: Traceback (most recent call last): File "script...

Hi, thank for sharing great work~ I have some question about psp final resize, which is show as below: pixel2style2pixel/models/psp.py Line 32 in 334f45e self.face_pool = torch.nn.AdaptiveAvgPool2d((256, 25...

Hi, thanks for your code I want to train PSP on my own paired dataset, and the dataset is independent of the face. After I read README and some related questions, I made the following changes: then, I successfully run the training code: My model is still in training. I have some questions: Alt...