How can I drag a real image?

[BankNatchapol]

Anyway, thanks for the cool project!

[PDillis]

As per the README:

This GUI supports editing GAN-generated images. To edit a real image, you need to first perform GAN inversion using tools like PTI. Then load the new latent code and model weights to the GUI.

So you need a trained model (e.g., FFHQ for faces), a real image, and project said image into the latent space of the model. Then you can use that latent vector in the GUI to do the manipulation. Hope this helps!

[Pawandeep-prog]

@BankNatchapol @PDillis I have created step by step tutorial video, hope this helps

https://youtu.be/viWiOC1Mikw

[sipie800]

It's very weird that one can only drag a lion or a dog as a program. There is supposed to be a PTI training pipeline right insides this.