wty-ustc / HairCLIP

[CVPR 2022] HairCLIP: Design Your Hair by Text and Reference Image
GNU Lesser General Public License v2.1
508 stars 66 forks source link

Inference on image data without converting to e4e #44

Open ArsalanAli915 opened 8 months ago

ArsalanAli915 commented 8 months ago

Thanks for making such a good model. Actually, I wanted to inference the model on my image data without converting it e4e. Could u please help with this? Thanks.

wty-ustc commented 8 months ago

The easiest way to do this is to first get the latent code of the image with e4e and then use our method to edit the hair. I've been busy with some issues lately and I'll integrate that part into our repository in a while.