meta / ic_gan

Instance-Conditioned GAN

  • Public
  • 26.7K runs
  • GitHub
  • Paper
  • License

😵 Uh oh! This model can't be run on Replicate because it was built with a version of Cog or Python that is no longer supported. Consider opening an issue on the model's GitHub repository to see if it can be updated to use a recent version of Cog. If you need any help, please Contact us about it.

Run time and cost

This model costs approximately $0.00075 to run on Replicate, or 1333 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia T4 GPU hardware. Predictions typically complete within 4 seconds.

Readme

IC-GAN: Instance-Conditioned GAN

Web demo of Instance-Conditioned GAN by Arantxa Casanova, Marlène Careil, Jakob Verbeek, Michał Drożdżal, Adriana Romero-Soriano. Check out IC-GAN’s Github repository for the original source code.

Generate images with IC-GAN

Generate images with IC-GAN and its class-conditional counter part.

The figure below depicts two instances, unseen during training and downloaded from Creative Commons search, and the generated images with IC-GAN and class-conditional IC-GAN when conditioning on the class “castle”:

Cite the paper

If this repository, the paper or any of its content is useful for your research, please cite:

@inproceedings{casanova2021instanceconditioned,
      title={Instance-Conditioned GAN}, 
      author={Arantxa Casanova and Marlène Careil and Jakob Verbeek and Michal Drozdzal and Adriana Romero-Soriano},
      booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
      year={2021}
}