Show HN: Ganvatar - Hacking StyleGAN to adjust age, gender, and emotion of faces
ganvatar.com
ganvatar.com
Excited to share this demo with the HN.
All of the portraits in this demo are computer-generated by a machine learning model called “StyleGAN”. While most of the recent excitement around StyleGAN centers around its amazing ability to generate infinite variation (e.g. thispersondoesnotexist.com <3), the emergent semantics encoded in the latent space are impressive as well.
For instance, faces in this space allow for some semantic vector math, reminiscent of word2vec’s “king - man + woman = queen” (https://p.migdal.pl/2017/01/06/king-man-woman-queen-why.html).
We can find the latent representations of, say, smiling people. We can then average them and create a new semantic vector that, when added to pictures of non-smiling faces, makes them all smile.
Play with the sliders to see what I mean.
Some possible applications: Generation of assets for games, Customizing ad photography by region/demographics, Lifelike, custom avatars, Compression, Modeling longitudinal medical imagery, Zero-shot inpainting, super-resolution, etc.
Happy to answer any questions!
The clearest immediate opportunity for GANs is generating content where artifacts might add value or are easily ignored (eg. art). The problem here is there's very little tech moat for these businesses given how easy it is to train a GAN. It'd come down to having a valuable, private dataset.
Lots of other potential commercial applications - we list some more on the demo.