pixel2style2pixel
pixel2style2pixel copied to clipboard
eladrich
Official Implementation for "Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation" (CVPR 2021) presenting the pixel2style2pixel (pSp) framework
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...
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...
This is not an issue. I just wanted to remark that I have never seen a better-structured Colab notebook. The code is easily understandable, but also skippable using dropdown boxes...
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)?...
Hi Mr Yuval, I am trying to retrain the model that you developed by training it on my own images. I created an image mask by using another model, and...
The following are my training parameters, which are basically based on the parameters you gave me. The data set used is FFHQ training. Why is there such a big jump...
Hello, Thanks for sharing your code! I am honored to have the opportunity to ask you. I currently have around 6,000 one-to-one images, consisting of the original images and the...
How can I use the style mixing to just change the hair color, using the pixel2style2pixel model. Any help on this would be highly appreciated Thank you
When loading a new bath from dataloader item, i don't understand the meaning of y. Dataset (FFHQ) is a label free dataset or am i wrong? y is then used...
