A problem about how to get diverse images?

eladrich / pixel2style2pixel

Official Implementation for "Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation" (CVPR 2021) presenting the pixel2style2pixel (pSp) framework

https://eladrich.github.io/pixel2style2pixel/

MIT License

3.19k stars 570 forks source link

A problem about how to get diverse images? #311

Closed Sakura-ldx closed 1 year ago

Sakura-ldx commented 1 year ago

I tried to project face segmentations to real face images. To finish the task, I used CelebAMask-HQ dataset and load the model with psp_celebs_seg_to_face.pt. But I could't get diverse results althougn I set the randomize_noise is True. I want to know how to get the results like this.

Sakura-ldx commented 1 year ago

I have solved this problem, thanks.