Wan-Animate: Unified Character Animation and Replacement with Holistic Replication
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916954833420288 |
|---|---|
| author | Cheng, Gang Gao, Xin Hu, Li Hu, Siqi Huang, Mingyang Ji, Chaonan Li, Ju Meng, Dechao Qi, Jinwei Qiao, Penchong Shen, Zhen Song, Yafei Sun, Ke Tian, Linrui Wang, Feng Wang, Guangyuan Wang, Qi Wang, Zhongjian Xiao, Jiayu Xu, Sheng Zhang, Bang Zhang, Peng Zhang, Xindi Zhang, Zhe Zhou, Jingren Zhuo, Lian |
| author_facet | Cheng, Gang Gao, Xin Hu, Li Hu, Siqi Huang, Mingyang Ji, Chaonan Li, Ju Meng, Dechao Qi, Jinwei Qiao, Penchong Shen, Zhen Song, Yafei Sun, Ke Tian, Linrui Wang, Feng Wang, Guangyuan Wang, Qi Wang, Zhongjian Xiao, Jiayu Xu, Sheng Zhang, Bang Zhang, Peng Zhang, Xindi Zhang, Zhe Zhou, Jingren Zhuo, Lian |
| contents | We introduce Wan-Animate, a unified framework for character animation and replacement. Given a character image and a reference video, Wan-Animate can animate the character by precisely replicating the expressions and movements of the character in the video to generate high-fidelity character videos. Alternatively, it can integrate the animated character into the reference video to replace the original character, replicating the scene's lighting and color tone to achieve seamless environmental integration. Wan-Animate is built upon the Wan model. To adapt it for character animation tasks, we employ a modified input paradigm to differentiate between reference conditions and regions for generation. This design unifies multiple tasks into a common symbolic representation. We use spatially-aligned skeleton signals to replicate body motion and implicit facial features extracted from source images to reenact expressions, enabling the generation of character videos with high controllability and expressiveness. Furthermore, to enhance environmental integration during character replacement, we develop an auxiliary Relighting LoRA. This module preserves the character's appearance consistency while applying the appropriate environmental lighting and color tone. Experimental results demonstrate that Wan-Animate achieves state-of-the-art performance. We are committed to open-sourcing the model weights and its source code. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_14055 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Wan-Animate: Unified Character Animation and Replacement with Holistic Replication Cheng, Gang Gao, Xin Hu, Li Hu, Siqi Huang, Mingyang Ji, Chaonan Li, Ju Meng, Dechao Qi, Jinwei Qiao, Penchong Shen, Zhen Song, Yafei Sun, Ke Tian, Linrui Wang, Feng 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 We introduce Wan-Animate, a unified framework for character animation and replacement. Given a character image and a reference video, Wan-Animate can animate the character by precisely replicating the expressions and movements of the character in the video to generate high-fidelity character videos. Alternatively, it can integrate the animated character into the reference video to replace the original character, replicating the scene's lighting and color tone to achieve seamless environmental integration. Wan-Animate is built upon the Wan model. To adapt it for character animation tasks, we employ a modified input paradigm to differentiate between reference conditions and regions for generation. This design unifies multiple tasks into a common symbolic representation. We use spatially-aligned skeleton signals to replicate body motion and implicit facial features extracted from source images to reenact expressions, enabling the generation of character videos with high controllability and expressiveness. Furthermore, to enhance environmental integration during character replacement, we develop an auxiliary Relighting LoRA. This module preserves the character's appearance consistency while applying the appropriate environmental lighting and color tone. Experimental results demonstrate that Wan-Animate achieves state-of-the-art performance. We are committed to open-sourcing the model weights and its source code. |
| title | Wan-Animate: Unified Character Animation and Replacement with Holistic Replication |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.14055 |