---
license: mit
---

### (NeurIPS 2023) Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models 
### Official Model Repo

#### Model Include:
- Stage1-CAVP Pretrained Model.
- Stage2-LDM Pretrained Model.
- Double Guidance Classifier.

<p align="center">
    <img src="teaser.png">
</p>

## BibTeX

```bibtex
@misc{luo2023difffoley, 
title={Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models}, 
author={Simian Luo and Chuanhao Yan and Chenxu Hu and Hang Zhao}, 
year={2023}, 
eprint={2306.17203}, 
archivePrefix={arXiv}, 
primaryClass={cs.SD} 
}
```