Bad test examples

[hallwaypzh]

I have tried the inference code on the examples in the paper (Figure 5.), however this one goes horribly wrong , this is the picture generated by stylegan

I'm using ftm method btw

[zyainfal]

We trained two models, one for ff++ and one for celeba-hq (you can see more details in the experiment section). The released model is the latter one.

The difference is the training dataset, i.e. the model trained for ff++ used more images from celeba, which gives better generalization on 256px images.

[hallwaypzh]

Thank u for the reply, will the other one be released?

[zyainfal]

Nope