Shuang59/Composable-Diffusion

1---2title: Composable-Diffusion3sdk: gradio4sdk_version: 3.12.05app_file: app.py6pinned: true7---8 9# Composable Diffusion10**Compositional Visual Generation with Composable Diffusion Models (ECCV 2022)**11 12**[Webpage](https://energy-based-model.github.io/Compositional-Visual-Generation-with-Composable-Diffusion-Models/) | [GitHub](https://github.com/energy-based-model/Compositional-Visual-Generation-with-Composable-Diffusion-Models-PyTorch)**13 14## Overview15We propose to use **conjunction and negation** (negative prompts) operators for **compositional generation with conditional diffusion models in test time without any training**. 16 17For more details, please refer to our paper: 18 19[Compositional Visual Generation with Composable Diffusion Models](https://arxiv.org/abs/2206.01714).<br>20[Nan Liu](https://nanliu.io)*\, [Shuang Li](https://people.csail.mit.edu/lishuang)*\, [Yilun Du](https://yilundu.github.io)*\, [Antonio Torralba](https://groups.csail.mit.edu/vision/torralbalab/), [Joshua B. Tenenbaum](https://mitibmwatsonailab.mit.edu/people/joshua-tenenbaum/), **ECCV 2022**21 22## Citation23 24If you find our paper useful in your research, please cite the following paper:25 26``` latex27@article{liu2022compositional,28  title={Compositional Visual Generation with Composable Diffusion Models},29  author={Liu, Nan and Li, Shuang and Du, Yilun and Torralba, Antonio and Tenenbaum, Joshua B},30  journal={arXiv preprint arXiv:2206.01714},31  year={2022}32}33```34