Here’s another idea for generating type data… what if we give it vector coordinates using with GPT2?
Rough idea of pipeline
Get Data via MyFonts API (PNGs of Glyphs)
Batch Image Trace .PNG to .AI via Adobe Bridge Script
Convert .AI to SVG via Illustrator Script
Process SVG data via Python to get rid of White backgrounds (#FFFFFF)
… Long story short, all the files were good to go, and the model ran on Runway.
I’m not quite sure why it didn’t work out the way I thought it would.
Most of the images looked like the above — not quite comprehensible beyond the black and white.