Composable Diffusion

Compositional Visual Generation with Composable Diffusion Models (ECCV 2022)

Webpage | GitHub

Overview

We propose to use conjunction and negation (negative prompts) operators for compositional generation with conditional diffusion models in test time without any training.

For more details, please refer to our paper:

Compositional Visual Generation with Composable Diffusion Models.
Nan Liu, Shuang Li, Yilun Du*, Antonio Torralba, Joshua B. Tenenbaum, ECCV 2022

Citation

If you find our paper useful in your research, please cite the following paper:

@article{liu2022compositional,
  title={Compositional Visual Generation with Composable Diffusion Models},
  author={Liu, Nan and Li, Shuang and Du, Yilun and Torralba, Antonio and Tenenbaum, Joshua B},
  journal={arXiv preprint arXiv:2206.01714},
  year={2022}
}