Played around with @gwern's TWDNEv2 model to generate images of Hayasaka Ai! This is after ~9 hours of training (n = 300+). Stopped working on it after a bit, so a bunch of potential improvements. More thoughts here: github.com/ZKTKZ/thdne/blob/โ€ฆ

11:56 PM ยท Oct 11, 2020

1
0
0
3
GIF
Some quick thoughts: * i hate colab * pixiv doesn't tag images properly. ended up writing a short script to filter hayasaka out by hair color. * pretty sure there's a LOT of room for improvement; this was trained for very little time on a Colab Notebook
2
0
0
1
I may end up writing a proper blog post at some point, but for now, I'd like to thank Gwern for his super in-depth guide at gwern.net/Faces. Also helped out by the author of this article on CSDN: tinyurl.com/csdn-twdne
0
0
0
0