FFHQ results are not matching as shown in the paper

[VirajBagal]

I trained on 1000 FFHQ 1024x1024 images for a little more than 10 hours with all default settings. Following are some of the samples after training of the network:

These images look much worse than those shown in the paper. Anyone knows the reason? Help much appreciated.

I think the default model in the code is same in size as described in the paper

[yangyu615]

I trained on 1000 FFHQ 1024x1024 images for a little more than 10 hours with all default settings. Following are some of the samples after training of the network:

These images look much worse than those shown in the paper. Anyone knows the reason? Help much appreciated.

I think the default model in the code is same in size as described in the paper Can you share FFHQ datasets?Thank you very much!

[yangyu615]

Can you share FFHQ datasets?Thank you very much!