🎨Mathematicians Reimagined

Mathematicians Reimagined

A private side project, winter 2023
Marcel Padilla
TU Berlin

Abstract

I was fooling around with Ai image generators and came across stable diffusion models and extensions which allowed me to generate modern images of famous mathematicians using old existing public domain images as input. I present here a few of my results.

I will continue to update this page every once and a while when I feel like it. The people here sorted by birth year.

Euclid (Sometime in ~350-200BC) reimagined.

René Descartes (1596-1650) reimagined.

Issac Newton (1642-1727) reimagined.

Gottfried Wilhelm Leibniz (1646-1716) reimagined.

Leonhard Euler (1707-1783) reimagined.

Pierre-Simon Laplace (1749-1827) reimagined.

Carl Friedrich Gauss (1777-1855) reimagined in a modern look.

Carl Gustav Jacob Jacobi (1804-1851) reimagined. Fun fact: Jacobi is not living in my neighbourhood.

Bernhard Riemann (1826-1866) reimagined.

Georg Cantor (1845-1918) reimagined.

Henri Poincaré (1854-1912) reimagined. He became a bit of a hipster.

David Hilberto (1862-1943) reimagined.

Emmy Noether (1882-1935) reimagined.

Workflow

I cant really be more specific without going into endless explainations when to use which ControlNet model with what settings. None two examples here were made with the same pipeline. Things kept not working here and there and I had to test my way around to get images that I am ok with. I had many visions that I could simply not fullfil. Especially regarding hair and beard features.

👉 Email me if you have a specific request for a mathematician.

Bonus Content

Using a few more Ai tools, I manged to recreate more creative stuff.

More Euler images. The left image focuses on maintinging the painting stlye. Yes, the hat-wear is weird. The right image is Leon-Hard Euler.

About Copyright

I personally make no copy right claims on this output, and advice you to be careful regarding copyrights of these images as they are output of ai models that were trained on unknown data sets. You can however still cite this webpage using the bibtext below.

Bibtex

@article{padilla_mathematicians_reimagined,
  author = {Marcel Padilla,
  title = {Mathematicians Reimagined},
  year = {2023},
  url = {https://marcelpadilla.com/Projects/Mathematicians_Reimagined/},
}