Hacker News Reader

It's very interesting and kinda creepy. The controls behave randomly, if you decrease "age" it might start changing skin color, etc.

View on HN

Actually, you can click on the name of the attribute to "lock" it. That way you can change one without changing the other!

Excellent

Oh yeah! I wrote a similar algorithm and constantly suffered similar problems. Constraining the latent space can be a major pain. Its hard to visualize but I think a lot of latent features may exist in non-continuous latent "pockets", meaning that the desired direction of the latent vector is dependent on your position in space.

I´m having a blast changing all the parameters. Really uncanney valley feelings. Some women come up very attractive, looking like Jessica Alba. How can I react to a face of a person that don't even exist?

On a second thought, I don´t mean that the controls behave randomly. I understand they affect related parts of the system. If you increase "baldness" on a woman's face, it will obviously increase the "male" factor and the "gray hair" factor. I understand that this faces are being generated from a continuous space. Fascinating.

Looking like Jessica Alba is not a coincidence. This model was trained on CelebA, a dataset of Hollywood celebrity face photos. Jessica Alba is almost certainly in the training set.

Reply on news.ycombinator.com