search

a312863063 / seeprettyface-face_editor

这是一个基于StyleGAN的人脸属性编辑器
540 stars 170 forks source link

Generating latent spaces for our own images. #4

Open GunaSekhar-T opened 4 years ago

GunaSekhar-T commented 4 years ago

Hi @a312863063 ,

Thank you for this great repository and we are using this for our GANs research.

I need a clarification for creating the latent space vector from our own image to feed into this model. I can able to create new image and using that image can able to adjust the different attributes using latest directions like smile, age, etc.

I tried StyleGAN-encoder package to create latent space with FFHQ model and its size is (18,512) with .npy format. But this repository needs in the format of .txt and its length is around (512). If possible can you please help me on how can I generate the latent space for the original(our own) images which is compatible with this model(i.e. latent spaces in .txt format without any loss in the quality of image).

Also, while we create latent space form real image using StyleGan encoder, we are facing some loss in the quality, is it because of the model or do I need to adjust any parameter in general?

Thanks in advance, looking forward you response.

Cherry2410 commented 4 years ago

@GunaSekhar-T,do you know how to generate the latent spaces in *.txt format?

foamliu commented 4 years ago

@GunaSekhar-T finetune the model.