The coarse knob of #StyleGAN really is mesmerizing. Esp. how it adds/replaces some features to match the artistic style (collars, hats..etc)

7:54 PM · Feb 10, 2019

9
69
9
259
12,170
On random interpolation, the truncated latent space also looks surprisingly continuous & morphologically coherent.
1
11
2
47
3,269
(Last one) with the fine knobs (range 6-16). Looks much more like a traditional style transfer which keeps the face features & pose relatively intact.
2
4
0
15
2,009
Back to work now... Here is the Colab to generate all 3 samples gist.github.com/kikko/d48c18…
4
3
0
22
Replying to @cyrildiagne
holy stromboli 😮
0
0
0
2
Replying to @cyrildiagne
Wow
0
0
0
1
Replying to @cyrildiagne
The co-author of styleGAN from @NvidiaAI just gave a talk now in @KAUST_News about their latest GAN . The introduced latent at different layers aims to force the discriminator to learn more variation . And that what made different from progressiveGAN
1
1
0
7
They even removed the traditional input and replaced if with a constant tensor. Another thing I find amazing is that it looks like a good chunk of the FID gain from ProGAN comes from hyperparameter tuning (8.04 > 5.25 on FFHQ)
0
0
0
1
Replying to @cyrildiagne
Looks great! Did you train this image set yourself - and is it public available?
1
0
0
1
Thanks! It's a custom dataset yes but not public at the moment
1
0
0
0
This Tweet was deleted by the Tweet author.
It's a custom dataset with multiple sources
0
0
0
2