cjwbw/compositional-vsual-generation-with-composable-diffusion-models-pytorch

Public
Composable Diffusion

Run time and cost

Predictions run on Nvidia T4 GPU hardware. Predictions typically complete within 17 seconds. The predict time for this model varies significantly based on the inputs.

This is a cog implementation of https://github.com/energy-based-model/Compositional-Visual-Generation-with-Composable-Diffusion-Models-PyTorch

Composable Diffusion

Project Page

This is the official codebase for Compositional Visual Generation with Composable Diffusion Models.

Compositional Visual Generation with Composable Diffusion Models


Nan Liu
Shuang Li
Yilun Du
Antonio Torralba
Joshua B. Tenenbaum


  • The codebase is built upon GLIDE.

Citing our Paper

If you find our code useful for your research, please consider citing

@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}
}