I used StyleGAN2-ADA to generate the original portrait, and then applied some special effects in Unreal.
The previous AI exercises I used StyleGAN or StyleGAN2, which required a lot of data sets and training time.
This batch changed to StyleGAN2-ADA, which was later released by Nvidia.
It supports small data sets, that is really a gospel for amateur players.
In addition, in terms of framework, Google’s Tensorflow was used before, but Facebook’s Pytorch was replaced this time.
There is no special reason. Seeing that Pytorch is being used more and more, just try it.
There are many articles, patches, source code and some advanced Patron-only content there.
- Or you can get a source code/patch directly in gumroad. https://gumroad.com/avantcontra
MORE articles in my site:
[Experimental Programming], meaning is derived from experimental art, experimental electronics, or experimental music. And that’s how I create things through programming.