Sergei Belousov

@AK391 We research possibilities to use some features from StyleGAN3 in our pipeline. Some updates will be available soon.

@rotem154154 which versions of pytorch and corml-tools do you use?

@rotem154154 sorry for the late response. I checked model conversion to coreml and it works good for me with coremltools==5.2.0. Please, try to update coremltools in your python env.

@zydjohnHotmail hi, thanks for interesting to our project. So, our framework is only for compression of the pretrained StyleGAN2 models, not for training from scratch. To use our framework for...

@zydjohnHotmail no, we support ONNX/CoreML export only for MobileStyleGAN

@zydjohnHotmail https://github.com/bes-dev/MobileStyleGAN.pytorch#pretrained-models

nope, you have some problems with your git settings

@zhongtao93 so, gt["rgb"] contain partial sums of the gt["img"], as we don't use aggregation of intermediate predictions like in StyleGAN2, it isn't correct to use gt["rgb"] here

@zhongtao93 I didn't try toonify pipeline on top of MobileStyleGAN. But if you have some experimental results it will be great if you share it.

@yaseryacoob hey, thanks for you feedback! Yes, we observed problems with glasses generation—detailed exploration of this problem we have postponed for further work. The main hypothesis about this problem is...