Hi HN, I’ve been tinkering with this for a while and finally have it in a decent state. It’s a plotter robot that draws caricatures from photos.
I trained a diffusion model (Flux Kontext LoRA) on caricature images, 3D-printed a Sharpie mount for my Ender 3, and hacked together a pipeline that goes photo → caricature → G-code. After a lot of trial and error it’s working pretty well, and I put up a little site where you can try it out.
Happy to answer questions or hear any feedback. Thanks!
Sorry to ask the obvious: why not just print the caricatures using a regular printer instead?
Yeah fair question – the appeal is mostly in letting the physical drawing process shape the final design a bit. The little quirks in how it draws make it unique, instead of simulating imperfections in AI and printing them.
Plus it was fun to build, and it’s fun to watch :)