search

KelestZ / Latent2im

ICLR'21 paper ``Enjoy Your Editing: Controllable GANs for Image Editing via Latent Space Navigation"
46 stars 3 forks source link

An optimization-based GAN inversion method #7

Open fradino opened 3 years ago

fradino commented 3 years ago

hello. i think it's an impressive work, and it can also work on real images. Could you provide the code ( real image to z ), thank you very much!

KelestZ commented 3 years ago

Sure, added the real image backpropagation code in https://github.com/KelestZ/Latent2im/blob/main/BP.py.

fradino commented 3 years ago

Sure, added the real image backpropagation code in https://github.com/KelestZ/Latent2im/blob/main/BP.py.

图片 hello, could you privide this module. thank you very much

KelestZ commented 3 years ago

Sure, added the real image backpropagation code in https://github.com/KelestZ/Latent2im/blob/main/BP.py.

图片 hello, could you privide this module. thank you very much

It is a naive VGG16. Put the model here: https://github.com/KelestZ/Latent2im/tree/main/perceptual_vgg.