Follow

The final version of my asemic novel _Ahe Thd Yearidy Ti Isa_ (made for NaNoGenMo 2019) is now available, either as a 100MB PDF static.decontextualize.com/ahe or as an online image gallery static.decontextualize.com/ahe

it was generated from a suite of GANs trained on bitmaps of random words, which I then sampled from and arranged to look sorta novel-esque. training code: github.com/aparrish/word-dcgan novel generation/layout code: github.com/aparrish/word-gan-b

using the same models and code I also made a book of latent space interpolations. this isn't 50k words long but I like it and wanted to share. PDF version static.decontextualize.com/int image gallery: static.decontextualize.com/int

this has been on my "open projects and ideas" board for like a year and i am very happy right now to be able to take it down and rip it in half and throw it away

@aparrish have you yet tried tricking a linguist into researching and translating it?

@314 in my experience linguists are very difficult to trick!

@aparrish that's too bad! i really wanted to read your novel

@aparrish Do you have any way of doing a latent space interpolation between "laurel" and "yanny"?

@aparrish Ah, I was afraid of that.

Having read up on GANs a tiny bit... if you wanted to find the latent space coordinates that best matched a target, could you use a different discriminator that just knows that target, and have the generator work its way towards that?

(Not asking you to, just curious about the limitations.)

@varx yep it's definitely possible and worth exploring, just not built into the gan code i hacked to make this thing work!

@aparrish

This is amazing. It's such a good approximation of language that if you didn't know where it came from, it'd be a real mystery.

I could believe it was a poor copy of a manuscript in a language I can't read.

@aparrish this is pretty much what the visual symptoms of a migraine look like for me

@aparrish I haven't followed the entire development thread so maybe you touched on this but it's really interesting that the "noise" around the letters is very clearly (to me) a really good approximation of font antialiasing. It looks super crisp zoomed out

@darius the GAN is trained on words drawn with antialiased letters so I think it's learning the antialiasing along with the rest of the shapes. I am pleased with how it looks!

@aparrish I love how the smashing together of words creates these ligatures and letter formations that feel familiar yet are totally unknown... I almost want to trace some and make a conlang out of them!

Sign in to participate in the conversation
Friend Camp

Hometown is adapted from Mastodon, a decentralized social network with no ads, no corporate surveillance, and ethical design.