zlacker

[parent] [thread] 1 comments
1. mywitt+(OP)[view] [source] 2020-06-24 15:02:17
I wonder if this is trained on the same, or similar, datasets.
replies(1): >>jcims+0x1
2. jcims+0x1[view] [source] 2020-06-24 22:18:01
>>mywitt+(OP)
One of the underlying models, PULSE, was trained on CelebAHQ, which is likely what the results are mostly white-looking. StyleGAN, which was trained on the much more diverse (but sparse) FFHQ dataset does come up with a much more diverse set of faces[1]...but PULSE couldn't get them to converge very closely on the pixelated subjects...so they went with CelebA [2].

[1] https://github.com/NVlabs/stylegan [2] https://arxiv.org/pdf/2003.03808.pdf (ctrl+f ffhq)

[go to top]