Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

How to change weights for getting better results of style transformation ? #68

Closed
kasarampavan opened this issue Mar 1, 2023 · 2 comments

Comments

@kasarampavan
Copy link

some styles are coming fully different face, some times style only replacing with original image, how to change weights to get style transform similar to original image face

origninal
StyleTransformImage
resultImage

@williamyang1991
Copy link
Owner

Here are the supported options:

  • Specify the style style with --style and --style_id
  • Specify the weight to adjust the degree of style with --weight (adjust this to keep the shape)
  • Specify --preserve_color or set the last 11 elements of --weight to all zeros to preserve the color style of the content image
  • Specify --wplus to use the original pSp encoder to extract the W+ intrinsic style code, which may better preserve the face features of the content image.

Our trained pSp encoder on Z+/W+ space cannot perfectly encode the content image. If the style transfer result more consistent with the content image is desired, one may use latent optimization to better fit the content image or using other StyleGAN encoders (as discussed in #11 and #29).

@kasarampavan
Copy link
Author

Thank you for fast reply...

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants