26 comments

[ 1.7 ms ] story [ 66.7 ms ] thread
Neat twist on the other website.
Some of these generated images look oddly male, or at least gender-unspecific, with their longer faces, eye-nose distances and wider chins. Mixing lots of female drawings inside a gann apparently doesn't result in females in every case.
A lot of anime waifus have androgynous features (often intentionally, e.g. Felix from Re:Zero). I wouldn't be surprised if the training set included many such examples.
I didn't filter out male faces (no convenient way, anyway), so there are males in it. Not a ton, certainly, but at least a few thousand.
It has some hiccups beyond gender. For example: https://imgur.com/a/d3SfrnQ
It looks like a bug alright, but then again... it's not something I wouldn't expect to see in actual anime :).
The size of the generated images seems to vary. Any idea what might be the cause of this?
I am about halfway through upscaling them from 512px to 1024px with waifu2x.
I imagine that tools such as this will be invaluable for game developers of the future.
I'm new to this how "This X Does Not Exist" thing ("This Person Does Not Exist" in seems especially impressive). It seems like this images are generated through some Machine Learning Magic(TM), but could anyone here give a rundown of how it all actually works? These all seem freaky good for something generated by a computer.
They are generated by Generative Adversarial Networks.

Have you heard about convolutional networks? They are neural networks that are especially well-suited for problems that have spatial structure (such as 2D images) and translational invariance (a face is a face, no matter of its coordinates in the picture).

Generative Adversarial Networks, or GANs for short is an architecture that arranges an image-generating network and fake-detecting network in a competitive situation. That makes them co-evolve towards generating pictures that are harder and harder to distinguish from the real ones.

Wow, that's really interesting! I've heard a bit about convolutional networks, but I've never heard of pitting two systems against each other like that. Thanks for taking the time to write that out.
How much porn was in the dataset? The generated faces seem to have a tendency to have white goo arond the mouth...
~9%. (I didn't think it would be much of a problem since they'd be cropped down and anyway, all my previous GANs sucked too much to care about fine details.)
Was this pun intended?)
It is an occupational hazard.
(comment deleted)
When Asia or the Japanese , manage to create an ROBOT with AI that can :-

* Cook

* Clean the house

* Wash the dish's

* Wash the clothes

* Simple gardening

* Service its master

Natural Born females can be replaced over night

I'm waiting to order my Asia Cat girl Waifu robot

================================================

How to fix Marriage in the west+EU+JP

* Fault divorce, not no fault

* One LAW for everyone with the SAME punishment for ALL.

* REMOVE Duluth Model from LAW+Courts+Police

* REMOVE PUSSY PASS

* False rape and False Sexual Assault to be convicted

* Ban Abortion

* Remove Child support

* Remove Vagmony (Alimony)

* Remove forced 50% of other person's assets

* False rape/assault claim register database

* Kid goes to the BEST person , Not automatically to the mother

* DNA test at all birth of kids

I doubt it will never happen

since women will actually be EQUAL & ACCOUNTABLE