interfacegan icon indicating copy to clipboard operation
interfacegan copied to clipboard

[CVPR 2020] Interpreting the Latent Space of GANs for Semantic Face Editing

Results 41 interfacegan issues
Sort by recently updated
recently updated
newest added

Hi I am wondering for this step, why you can put R = r to be R = 1? ![image](https://user-images.githubusercontent.com/86935669/146906559-f5af933e-9d43-470f-ac70-5fb22c5d7c0f.png) This is taken from the appendix, the proof for property...

trying to inference based on my own jpg/png. how can i encode the img into latent code?

after trying all 3 pretrained models, all return the error stating that I am using a pytorch version without cuda enabled. using macos without GPU

Would you please tell me about how to train the boundaries to manipulate multiple semantics? is it putting two trained boundaries together or computing the covariance of diferent semantics' scores?

First, thank you for any suggestions. Based on the guide, first we need to download the pre-trained pggan model. I found one that is in the [here](https://mycuhk-my.sharepoint.com/personal/1155082926_link_cuhk_edu_hk/_layouts/15/onedrive.aspx?id=%2Fpersonal%2F1155082926%5Flink%5Fcuhk%5Fedu%5Fhk%2FDocuments%2FGenForce%2Ftf%5Fmodels%2Fpggan%5Fofficial%2Fkarras2018iclr%2Dcelebahq%2D1024x1024%2Epkl&parent=%2Fpersonal%2F1155082926%5Flink%5Fcuhk%5Fedu%5Fhk%2FDocuments%2FGenForce%2Ftf%5Fmodels%2Fpggan%5Fofficial) and rename it...

Hi, I really thanks for your great research. I want to try training boundaries so i need attribute score classifier to get the score. In some issues (ex, **Latent code-...

Hi, first thanks for sharing your work. I'm running using: `python3.6 edit.py -m stylegan_celebahq -b boundaries/stylegan_celebahq_eyeglasses_boundary.npy --n 4 --o results/sg_eg_celebhq` But I'm getting a change in gender, and not gallasses...

Would you be interested in a Replicate demo for InterfaceGAN? I'm one of the founders of the [Replicate project](https://replicate.ai/), where we're trying to make it easier to reproduce great ML...

do you guys have any plan to support stylegan2?