So can we get a new w+ vector based on style_space, latent and G three parameters?

[123456klk1]

Hello, your work is excellent! I have a question I'd like to ask you. You know, we can get the new image after editing the updated style vector guided by three parameters of S (stylegan2 space vector), the original image obtained by e4e latent space vector latent (w+) and stylegan2 generator. So can we get a new w+ vector based on these three parameters?

[StelaBou]

Hi, just to make sure I understand your question correctly. Do you want to predict a new w+ latent code based on the edited style code? Could you please clarify what you mean by 'get a new w+ vector based on these three parameters'?

[123456klk1]

yes, I want to predict a new w+ latent code based on the edited style code?

[StelaBou]

The w+ latent code remains the same when you edit the style code.

[123456klk1]

The input is the style_space and latent. Generally, the image can be generated according to the code of the above image, and then the image can be input into the e4e network to generate a new latent code. So can we get a new w+ vector based on style_space, latent, and G three parameters?