baopmessi

Looking forward to the results from you soon ! . By the way, results in your paper without addition of the average latent code ?

I was still confuse about this part (what g_i). It mean :  So why " We can find that large amount of gradient information are reused for updating weights...

How to solved this problem？

Same problem. How to solving it. Thanks.

Thanks for answer quickly! I load vector from interfaceGan and inference but it's not working. The face has no change as expected.  

I have a few questions: - the ckpt in styleganex_edit_age.pt is a model trained as fine-tuned from **Video face editing**. [https://github.com/williamyang1991/StyleGANEX#video-editing-1](url) - The results of editing the face (young face)...

Thanks you for your help! I have succeeded in inversion + editing vector (from the ckpt in your pretrained_models/styleganex_edit_age.pt).  However, I couldn't find where the editing vector comes from....

Oh! I see. - `self.editing_dicts = torch.load(hf_hub_download('PKUWilliamYang/StyleGANEX', 'direction_dics.pt')) editing_w = self.editing_dicts['smile'].to(self.device)` The smile direction in this code snippet is same to that in the LowRankGAN repo [link](https://github.com/zhujiapeng/LowRankGAN/blob/master/directions/ffhq1024/expression.npy), not in InterfaceGAN....

I have tried all the age vectors in [1](https://github.com/genforce/interfacegan/tree/master/boundaries), but none of them work as well as yours. Because I want to retrain with some new expressions, I need to...