With latent interpolations, I'm always fascinated by the points in between discrete regions eg how it jumps from 'g' to 'G' shapes.
Generative model of fonts by @fulhack: https://erikbern.com/2016/01/21/analyzing-50k-fonts-using-deep-neural-networks.html … Interpolations like this suggest it knows way more than me about fonts:pic.twitter.com/b3Y3UuaS24
-
-
-
I remember Hofstadter in Metamagical Themas talking about difficulty of casing because the shapes of the 'same' letter can totally differ.
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.