I have trained StyleGAN2 from scratch with a dataset of female portraits(github.com)
github.com
I have trained StyleGAN2 from scratch with a dataset of female portraits
https://github.com/l4rz/practical-aspects-of-stylegan2-training
20 comments
For AI, a female can only be white?
why are they all naked?
According to the readme, to avoid common defects related to clothing.
Click on the picture with the faces -when having a closer look it can be seen that every picture goes from "slightly distorted" to "disturbingly disfigured".
Seems that was just v1. There's a link to the 2nd iteration of the project, and the images, to my eyes, are very much improved with respect to realism.
https://github.com/l4rz/scaling-up-stylegan2
https://github.com/l4rz/scaling-up-stylegan2
This one clearly has a tendency to create asymmetric eyes slightly beyond what my brain perceives as average asymmetry.
Seems the less accurate images occur at smaller training set sizes (at least that's how I read those image captions about kimg).
> I was curious how it would work on the human anatomy
Mmm-hmmmmmmmm.
Mmm-hmmmmmmmm.
I guess it is aimed at people already conversant with the tech lingo, but to the uninitiated it looks like a deep-fake related generator of attractive white women.
I think deep fake means using face of some existing person, while the faces generated using this method does not exist.
I mean, it kind of is, and that's okay.
It seems the training data was almost certainly built from adult actress portraits of which you can easily scrape endless amounts from, like any porn site.
Impressive. When I saw the guy is from Luxembourg, and the sultry visages of the images, I felt sure this had something to do with some of the porn behemoths there. Which I Googled and found were MindGeek or LiveJasmin.
When StyleGAN2 came out I played with the original NVidia training set for about a week - and when I say a week I mean I did nothing else, day and night, for a week - just exploring "seed space" to see what variety of faces would come out, trying to select for certain faces, etc... I had a grand old time with it, but what you discover in the end is that the models can not nearly generate every imaginable human face. For lack of better words I would say there was a certain "averageness" to the results. By the way beautiful faces tended towards Isabella Rossellini so apparently she has the "most average beautiful face" :) So for sure this generator has blown away everything that came before, but there is still plenty of room for improvement IMO. In the end what impressed me most was the hair. It does hair better than any other software that I know of.
One day style gan will be used to recreate pornography and with all its weird anomalies the outcome will be truly horrifying.
Goodness knows there’s plenty of porno training images out there.
Goodness knows there’s plenty of porno training images out there.
“Female portraits” is some chefs kiss whitewashing. More like “women under the male gaze”.
It dovetails with the current news of Apple's client-side content scanning using perceptual hashes. I'm strongly against that, but with regards to opening Pandora's box with the situation above...It'd be interesting to hear peoples thoughts on what might be able to be done about these sorts of tech induced dilemmas. (Ban the tech? License it? Accept more and deeper blanket surveillance? Allow it all!?)