Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2503.20314 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909585513644032 |
|---|---|
| author | Wan, Team Wang, Ang Ai, Baole Wen, Bin Mao, Chaojie Xie, Chen-Wei Chen, Di Yu, Feiwu Zhao, Haiming Yang, Jianxiao Zeng, Jianyuan Wang, Jiayu Zhang, Jingfeng Zhou, Jingren Wang, Jinkai Chen, Jixuan Zhu, Kai Zhao, Kang Yan, Keyu Huang, Lianghua Feng, Mengyang Zhang, Ningyi Li, Pandeng Wu, Pingyu Chu, Ruihang Feng, Ruili Zhang, Shiwei Sun, Siyang Fang, Tao Wang, Tianxing Gui, Tianyi Weng, Tingyu Shen, Tong Lin, Wei Wang, Wei Wang, Wei Zhou, Wenmeng Wang, Wente Shen, Wenting Yu, Wenyuan Shi, Xianzhong Huang, Xiaoming Xu, Xin Kou, Yan Lv, Yangyu Li, Yifei Liu, Yijing Wang, Yiming Zhang, Yingya Huang, Yitong Li, Yong Wu, You Liu, Yu Pan, Yulin Zheng, Yun Hong, Yuntao Shi, Yupeng Feng, Yutong Jiang, Zeyinzi Han, Zhen Wu, Zhi-Fan Liu, Ziyu |
| author_facet | Wan, Team Wang, Ang Ai, Baole Wen, Bin Mao, Chaojie Xie, Chen-Wei Chen, Di Yu, Feiwu Zhao, Haiming Yang, Jianxiao Zeng, Jianyuan Wang, Jiayu Zhang, Jingfeng Zhou, Jingren Wang, Jinkai Chen, Jixuan Zhu, Kai Zhao, Kang Yan, Keyu Huang, Lianghua Feng, Mengyang Zhang, Ningyi Li, Pandeng Wu, Pingyu Chu, Ruihang Feng, Ruili Zhang, Shiwei Sun, Siyang Fang, Tao Wang, Tianxing Gui, Tianyi Weng, Tingyu Shen, Tong Lin, Wei Wang, Wei Wang, Wei Zhou, Wenmeng Wang, Wente Shen, Wenting Yu, Wenyuan Shi, Xianzhong Huang, Xiaoming Xu, Xin Kou, Yan Lv, Yangyu Li, Yifei Liu, Yijing Wang, Yiming Zhang, Yingya Huang, Yitong Li, Yong Wu, You Liu, Yu Pan, Yulin Zheng, Yun Hong, Yuntao Shi, Yupeng Feng, Yutong Jiang, Zeyinzi Han, Zhen Wu, Zhi-Fan Liu, Ziyu |
| contents | This report presents Wan, a comprehensive and open suite of video foundation models designed to push the boundaries of video generation. Built upon the mainstream diffusion transformer paradigm, Wan achieves significant advancements in generative capabilities through a series of innovations, including our novel VAE, scalable pre-training strategies, large-scale data curation, and automated evaluation metrics. These contributions collectively enhance the model's performance and versatility. Specifically, Wan is characterized by four key features: Leading Performance: The 14B model of Wan, trained on a vast dataset comprising billions of images and videos, demonstrates the scaling laws of video generation with respect to both data and model size. It consistently outperforms the existing open-source models as well as state-of-the-art commercial solutions across multiple internal and external benchmarks, demonstrating a clear and significant performance superiority. Comprehensiveness: Wan offers two capable models, i.e., 1.3B and 14B parameters, for efficiency and effectiveness respectively. It also covers multiple downstream applications, including image-to-video, instruction-guided video editing, and personal video generation, encompassing up to eight tasks. Consumer-Grade Efficiency: The 1.3B model demonstrates exceptional resource efficiency, requiring only 8.19 GB VRAM, making it compatible with a wide range of consumer-grade GPUs. Openness: We open-source the entire series of Wan, including source code and all models, with the goal of fostering the growth of the video generation community. This openness seeks to significantly expand the creative possibilities of video production in the industry and provide academia with high-quality video foundation models. All the code and models are available at https://github.com/Wan-Video/Wan2.1. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_20314 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Wan: Open and Advanced Large-Scale Video Generative Models Wan, Team Wang, Ang Ai, Baole Wen, Bin Mao, Chaojie Xie, Chen-Wei Chen, Di Yu, Feiwu Zhao, Haiming Yang, Jianxiao Zeng, Jianyuan Wang, Jiayu Zhang, Jingfeng Zhou, Jingren Wang, Jinkai Chen, Jixuan Zhu, Kai Zhao, Kang Yan, Keyu Huang, Lianghua Feng, Mengyang Zhang, Ningyi Li, Pandeng Wu, Pingyu Chu, Ruihang Feng, Ruili Zhang, Shiwei Sun, Siyang Fang, Tao Wang, Tianxing Gui, Tianyi Weng, Tingyu Shen, Tong Lin, Wei Wang, Wei Wang, Wei Zhou, Wenmeng Wang, Wente Shen, Wenting Yu, Wenyuan Shi, Xianzhong Huang, Xiaoming Xu, Xin Kou, Yan Lv, Yangyu Li, Yifei Liu, Yijing Wang, Yiming Zhang, Yingya Huang, Yitong Li, Yong Wu, You Liu, Yu Pan, Yulin Zheng, Yun Hong, Yuntao Shi, Yupeng Feng, Yutong Jiang, Zeyinzi Han, Zhen Wu, Zhi-Fan Liu, Ziyu Computer Vision and Pattern Recognition This report presents Wan, a comprehensive and open suite of video foundation models designed to push the boundaries of video generation. Built upon the mainstream diffusion transformer paradigm, Wan achieves significant advancements in generative capabilities through a series of innovations, including our novel VAE, scalable pre-training strategies, large-scale data curation, and automated evaluation metrics. These contributions collectively enhance the model's performance and versatility. Specifically, Wan is characterized by four key features: Leading Performance: The 14B model of Wan, trained on a vast dataset comprising billions of images and videos, demonstrates the scaling laws of video generation with respect to both data and model size. It consistently outperforms the existing open-source models as well as state-of-the-art commercial solutions across multiple internal and external benchmarks, demonstrating a clear and significant performance superiority. Comprehensiveness: Wan offers two capable models, i.e., 1.3B and 14B parameters, for efficiency and effectiveness respectively. It also covers multiple downstream applications, including image-to-video, instruction-guided video editing, and personal video generation, encompassing up to eight tasks. Consumer-Grade Efficiency: The 1.3B model demonstrates exceptional resource efficiency, requiring only 8.19 GB VRAM, making it compatible with a wide range of consumer-grade GPUs. Openness: We open-source the entire series of Wan, including source code and all models, with the goal of fostering the growth of the video generation community. This openness seeks to significantly expand the creative possibilities of video production in the industry and provide academia with high-quality video foundation models. All the code and models are available at https://github.com/Wan-Video/Wan2.1. |
| title | Wan: Open and Advanced Large-Scale Video Generative Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.20314 |