Fake-Inversion:

Learning to Detect Images from Unseen
Models by Inverting Stable Diffusion

CVPR 2024

George Cazenavette, Avneesh Sud, Thomas Leung, Ben Usman

Massachusetts Institute of Technology, Google Research

arXiv Code

We are currently still working to release the new datasets publically.

In the meantime, if you're interested in our new datasets, please reach out to gcaz@mit.edu, and I would be happy to help :)