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

Number of images generated #5

Closed
chenxwh opened this issue Sep 24, 2021 · 1 comment
Closed

Number of images generated #5

chenxwh opened this issue Sep 24, 2021 · 1 comment
Assignees

Comments

@chenxwh
Copy link
Contributor

chenxwh commented Sep 24, 2021

Hi I have tried the model, really cool!
Just wondering whether it always generate 64 images? is there a way to output the 'best one'/ 'best ones'?
Or do the 64 output from the style palette have style names if I just want to have one of a few output?

Thank you

@wonjongg
Copy link
Owner

Hi,
You can generate countless examples by sampling style code from Gaussian distribution. Maybe you can use torch.randn() for random sampling.

Since everyone has different personal preferences, it is really difficult to define which output or style is 'best'. Our current work does not suggest methods to find the best caricature output. I think it will be a good future work.

If you want to have one of a few output, you should put the style code (.pt) in the same directory with your image file and name the style code as (filename)_style.pt. For more details, please see our test code on sample images.

Thank you for your interest in our work! 😄

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