NaN operates as a lab where creativity and technology intertwine. Discover the self-initiated projects fuelling our typographic practice.
Trial fonts
Machine Learning Font
Could a machine learning model be trained to generate realistic (or at least interesting) letterforms? As it turns out, yes, albeit with mixed results. Starting with a styleGAN model, we trained the programme in RunwayML on a dataset of 2674 Google fonts, organised as individual image-per-glyph in Drawbot. Runway-generated images were then piped via Python into GlyphsApp to process the final font. The full project, including downloadable fonts, was released under the SIL Open Font Licence.
Generative Fonts
GenerativeFonts.xyz is a collection of procedurally generated, free-to-use, free-to-modify display fonts and the codebase that was used to design them. Many of these ideas began on paper and were reverse-engineered into a bespoke system (with a heavy handful of randomness chucked into the mix), approached with the philosophy that both the terms ‘design’ and ‘algorithm’ are one and the same.
Confusify
A confusable is a glyph that is so similar to another that it may be confused for it. Confusify.py generates fonts that, when typed, automatically swap confusables for the original. All confusables generated are existing characters in the source font. In that sense, consider it a remix.
Select pre-processed fonts released under the SIL Open Font License:
This Font Does Not Exist
In collaboration with Production Type, we trained a machine learning model on around 30,000 font bios to generate descriptions of speculative fonts.
Follow us on Instagram
More on Instagram
