Wan-S2V: Audio-Driven Cinematic Video Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914005779480576 |
|---|---|
| author | Gao, Xin Hu, Li Hu, Siqi Huang, Mingyang Ji, Chaonan Meng, Dechao Qi, Jinwei Qiao, Penchong Shen, Zhen Song, Yafei Sun, Ke Tian, Linrui Wang, Guangyuan Wang, Qi Wang, Zhongjian Xiao, Jiayu Xu, Sheng Zhang, Bang Zhang, Peng Zhang, Xindi Zhang, Zhe Zhou, Jingren Zhuo, Lian |
| author_facet | Gao, Xin Hu, Li Hu, Siqi Huang, Mingyang Ji, Chaonan Meng, Dechao Qi, Jinwei Qiao, Penchong Shen, Zhen Song, Yafei Sun, Ke Tian, Linrui Wang, Guangyuan Wang, Qi Wang, Zhongjian Xiao, Jiayu Xu, Sheng Zhang, Bang Zhang, Peng Zhang, Xindi Zhang, Zhe Zhou, Jingren Zhuo, Lian |
| contents | Current state-of-the-art (SOTA) methods for audio-driven character animation demonstrate promising performance for scenarios primarily involving speech and singing. However, they often fall short in more complex film and television productions, which demand sophisticated elements such as nuanced character interactions, realistic body movements, and dynamic camera work. To address this long-standing challenge of achieving film-level character animation, we propose an audio-driven model, which we refere to as Wan-S2V, built upon Wan. Our model achieves significantly enhanced expressiveness and fidelity in cinematic contexts compared to existing approaches. We conducted extensive experiments, benchmarking our method against cutting-edge models such as Hunyuan-Avatar and Omnihuman. The experimental results consistently demonstrate that our approach significantly outperforms these existing solutions. Additionally, we explore the versatility of our method through its applications in long-form video generation and precise video lip-sync editing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_18621 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Wan-S2V: Audio-Driven Cinematic Video Generation Gao, Xin Hu, Li Hu, Siqi Huang, Mingyang Ji, Chaonan Meng, Dechao Qi, Jinwei Qiao, Penchong Shen, Zhen Song, Yafei Sun, Ke Tian, Linrui Wang, Guangyuan Wang, Qi Wang, Zhongjian Xiao, Jiayu Xu, Sheng Zhang, Bang Zhang, Peng Zhang, Xindi Zhang, Zhe Zhou, Jingren Zhuo, Lian Computer Vision and Pattern Recognition Current state-of-the-art (SOTA) methods for audio-driven character animation demonstrate promising performance for scenarios primarily involving speech and singing. However, they often fall short in more complex film and television productions, which demand sophisticated elements such as nuanced character interactions, realistic body movements, and dynamic camera work. To address this long-standing challenge of achieving film-level character animation, we propose an audio-driven model, which we refere to as Wan-S2V, built upon Wan. Our model achieves significantly enhanced expressiveness and fidelity in cinematic contexts compared to existing approaches. We conducted extensive experiments, benchmarking our method against cutting-edge models such as Hunyuan-Avatar and Omnihuman. The experimental results consistently demonstrate that our approach significantly outperforms these existing solutions. Additionally, we explore the versatility of our method through its applications in long-form video generation and precise video lip-sync editing. |
| title | Wan-S2V: Audio-Driven Cinematic Video Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.18621 |