chigozienri / visual-anagrams

Generates multi-view optical illusions

  • Public
  • 981 runs
  • GitHub
  • Paper
  • License



Run time and cost

This model runs on Nvidia A40 (Large) GPU hardware. Predictions typically complete within 23 seconds. The predict time for this model varies significantly based on the inputs.


This repo contains code to generate visual anagrams and other multi-view optical illusions. These are images that change appearance or identity when transformed, such as by a rotation, a color inversion, or a jigsaw rearrangement.