Home

Could a machine learning model be trained to generate realistic (or just interesting) letterforms? As it turns out, yes, albeit with mixed results. A styleGAN model was trained 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 in to GlyphsApp to process the final font. Some characters took longer/more steps to create recognisable forms but generally speaking each glyph was processed on 3k model training steps.