Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2505.14135 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913863203553280 |
|---|---|
| author | Li, Ruihuang Zhou, Caijin Zheng, Shoujian Lu, Jianxiang Huang, Jiabin Chen, Comi Tang, Junshu Xu, Guangzheng Tao, Jiale Wang, Hongmei Li, Donghao Yu, Wenqing Wang, Senbo Li, Zhimin Shi, Yetshuan Yang, Haoyu Wang, Yukun Dai, Wenxun Li, Jiaqi Wang, Linqing Wang, Qixun Xu, Zhiyong Zhang, Yingfang Xiong, Jiangfeng Kong, Weijie Zhang, Chao Zhang, Hongxin Zheng, Qiaoling Guo, Weiting Deng, Xinchi Li, Yixuan Wei, Renjia Jian, Yulin Huang, Duojun Ren, Xuhua Yuan, Junkun Zhou, Zhengguang Cheng, Jiaxiang Ma, Bing Huang, Shirui Bai, Jiawang Li, Chao Lin, Sihuan Sun, Yifu Zhou, Yuan Wang, Joey Lin, Qin Zheng, Tianxiang Yu, Jingmiao Zhang, Jihong Zhong, Caesar Wang, Di Liu, Yuhong Linus Jiang, Jie Wu, Longhuang Shao, Shuai Lu, Qinglin |
| author_facet | Li, Ruihuang Zhou, Caijin Zheng, Shoujian Lu, Jianxiang Huang, Jiabin Chen, Comi Tang, Junshu Xu, Guangzheng Tao, Jiale Wang, Hongmei Li, Donghao Yu, Wenqing Wang, Senbo Li, Zhimin Shi, Yetshuan Yang, Haoyu Wang, Yukun Dai, Wenxun Li, Jiaqi Wang, Linqing Wang, Qixun Xu, Zhiyong Zhang, Yingfang Xiong, Jiangfeng Kong, Weijie Zhang, Chao Zhang, Hongxin Zheng, Qiaoling Guo, Weiting Deng, Xinchi Li, Yixuan Wei, Renjia Jian, Yulin Huang, Duojun Ren, Xuhua Yuan, Junkun Zhou, Zhengguang Cheng, Jiaxiang Ma, Bing Huang, Shirui Bai, Jiawang Li, Chao Lin, Sihuan Sun, Yifu Zhou, Yuan Wang, Joey Lin, Qin Zheng, Tianxiang Yu, Jingmiao Zhang, Jihong Zhong, Caesar Wang, Di Liu, Yuhong Linus Jiang, Jie Wu, Longhuang Shao, Shuai Lu, Qinglin |
| contents | Intelligent game creation represents a transformative advancement in game development, utilizing generative artificial intelligence to dynamically generate and enhance game content. Despite notable progress in generative models, the comprehensive synthesis of high-quality game assets, including both images and videos, remains a challenging frontier. To create high-fidelity game content that simultaneously aligns with player preferences and significantly boosts designer efficiency, we present Hunyuan-Game, an innovative project designed to revolutionize intelligent game production. Hunyuan-Game encompasses two primary branches: image generation and video generation. The image generation component is built upon a vast dataset comprising billions of game images, leading to the development of a group of customized image generation models tailored for game scenarios: (1) General Text-to-Image Generation. (2) Game Visual Effects Generation, involving text-to-effect and reference image-based game visual effect generation. (3) Transparent Image Generation for characters, scenes, and game visual effects. (4) Game Character Generation based on sketches, black-and-white images, and white models. The video generation component is built upon a comprehensive dataset of millions of game and anime videos, leading to the development of five core algorithmic models, each targeting critical pain points in game development and having robust adaptation to diverse game video scenarios: (1) Image-to-Video Generation. (2) 360 A/T Pose Avatar Video Synthesis. (3) Dynamic Illustration Generation. (4) Generative Video Super-Resolution. (5) Interactive Game Video Generation. These image and video generation models not only exhibit high-level aesthetic expression but also deeply integrate domain-specific knowledge, establishing a systematic understanding of diverse game and anime art styles. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_14135 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hunyuan-Game: Industrial-grade Intelligent Game Creation Model Li, Ruihuang Zhou, Caijin Zheng, Shoujian Lu, Jianxiang Huang, Jiabin Chen, Comi Tang, Junshu Xu, Guangzheng Tao, Jiale Wang, Hongmei Li, Donghao Yu, Wenqing Wang, Senbo Li, Zhimin Shi, Yetshuan Yang, Haoyu Wang, Yukun Dai, Wenxun Li, Jiaqi Wang, Linqing Wang, Qixun Xu, Zhiyong Zhang, Yingfang Xiong, Jiangfeng Kong, Weijie Zhang, Chao Zhang, Hongxin Zheng, Qiaoling Guo, Weiting Deng, Xinchi Li, Yixuan Wei, Renjia Jian, Yulin Huang, Duojun Ren, Xuhua Yuan, Junkun Zhou, Zhengguang Cheng, Jiaxiang Ma, Bing Huang, Shirui Bai, Jiawang Li, Chao Lin, Sihuan Sun, Yifu Zhou, Yuan Wang, Joey Lin, Qin Zheng, Tianxiang Yu, Jingmiao Zhang, Jihong Zhong, Caesar Wang, Di Liu, Yuhong Linus Jiang, Jie Wu, Longhuang Shao, Shuai Lu, Qinglin Computer Vision and Pattern Recognition Intelligent game creation represents a transformative advancement in game development, utilizing generative artificial intelligence to dynamically generate and enhance game content. Despite notable progress in generative models, the comprehensive synthesis of high-quality game assets, including both images and videos, remains a challenging frontier. To create high-fidelity game content that simultaneously aligns with player preferences and significantly boosts designer efficiency, we present Hunyuan-Game, an innovative project designed to revolutionize intelligent game production. Hunyuan-Game encompasses two primary branches: image generation and video generation. The image generation component is built upon a vast dataset comprising billions of game images, leading to the development of a group of customized image generation models tailored for game scenarios: (1) General Text-to-Image Generation. (2) Game Visual Effects Generation, involving text-to-effect and reference image-based game visual effect generation. (3) Transparent Image Generation for characters, scenes, and game visual effects. (4) Game Character Generation based on sketches, black-and-white images, and white models. The video generation component is built upon a comprehensive dataset of millions of game and anime videos, leading to the development of five core algorithmic models, each targeting critical pain points in game development and having robust adaptation to diverse game video scenarios: (1) Image-to-Video Generation. (2) 360 A/T Pose Avatar Video Synthesis. (3) Dynamic Illustration Generation. (4) Generative Video Super-Resolution. (5) Interactive Game Video Generation. These image and video generation models not only exhibit high-level aesthetic expression but also deeply integrate domain-specific knowledge, establishing a systematic understanding of diverse game and anime art styles. |
| title | Hunyuan-Game: Industrial-grade Intelligent Game Creation Model |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.14135 |