Hunyuan-Game: Industrial-grade Intelligent Game Creation Model

• URL: http://arxiv.org/abs/2505.14135v2
• Date: Wed, 28 May 2025 13:11:02 GMT
• Title: Hunyuan-Game: Industrial-grade Intelligent Game Creation Model
• Authors: Ruihuang Li, Caijin Zhou, Shoujian Zheng, Jianxiang Lu, Jiabin Huang, Comi Chen, Junshu Tang, Guangzheng Xu, Jiale Tao, Hongmei Wang, Donghao Li, Wenqing Yu, Senbo Wang, Zhimin Li, Yetshuan Shi, Haoyu Yang, Yukun Wang, Wenxun Dai, Jiaqi Li, Linqing Wang, Qixun Wang, Zhiyong Xu, Yingfang Zhang, Jiangfeng Xiong, Weijie Kong, Chao Zhang, Hongxin Zhang, Qiaoling Zheng, Weiting Guo, Xinchi Deng, Yixuan Li, Renjia Wei, Yulin Jian, Duojun Huang, Xuhua Ren, Junkun Yuan, Zhengguang Zhou, Jiaxiang Cheng, Bing Ma, Shirui Huang, Jiawang Bai, Chao Li, Sihuan Lin, Yifu Sun, Yuan Zhou, Joey Wang, Qin Lin, Tianxiang Zheng, Jingmiao Yu, Jihong Zhang, Caesar Zhong, Di Wang, Yuhong Liu, Linus, Jie Jiang, Longhuang Wu, Shuai Shao, Qinglin Lu,
• Abstract summary: Hunyuan-Game is an innovative project designed to revolutionize intelligent game production.<n>The project encompasses two primary branches: image generation and video generation.<n>The image generation component is built upon a vast dataset comprising billions of game images.<n>The video generation component is built upon a dataset of millions of game and anime videos.
• Score: 42.685908112453106
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition [18.789597877579986]
  Hunyuan-GameCraft is a novel framework for high-dynamic interactive video generation in game environments.<n>To achieve fine-grained action control, we unify standard keyboard and mouse inputs into a shared camera representation space.<n>We propose a hybrid history-conditioned training strategy that extends video sequences autoregressively while preserving game scene information.
  arXiv  Detail & Related papers  (2025-06-20T17:50:37Z)
• Generative AI for Film Creation: A Survey of Recent Advances [9.778792224015275]
  Generative AI (GenAI) is transforming filmmaking, equipping artists with tools like text-to-image and image-to-video diffusion, neural radiance fields, avatar generation, and 3D synthesis.<n>This paper examines the adoption of these technologies in filmmaking, analyzing from recent AI-driven films.<n>We highlight emerging trends such as the growing use of 3D generation and the integration of real footage with AI-generated elements.
  arXiv  Detail & Related papers  (2025-04-11T06:54:29Z)
• AnimeGamer: Infinite Anime Life Simulation with Next Game State Prediction [58.240114139186275]
  Recently, a pioneering approach for infinite anime life simulation employs large language models (LLMs) to translate multi-turn text dialogues into language instructions for image generation.<n>We propose AnimeGamer, which is built upon Multimodal Large Language Models (MLLMs) to generate each game state.<n>We introduce novel action-aware multimodal representations to represent animation shots, which can be decoded into high-quality video clips.
  arXiv  Detail & Related papers  (2025-04-01T17:57:18Z)
• Position: Interactive Generative Video as Next-Generation Game Engine [32.7449148483466]
  We propose Interactive Generative Video (IGV) as the foundation for Generative Game Engines (GGE)<n>IGV's unique strengths include unlimited high-quality content synthesis, physics-aware world modeling, user-controlled interactivity, long-term memory capabilities, and causal reasoning.<n>Our work charts a new course for game development in the AI era, envisioning a future where AI-powered generative systems fundamentally reshape how games are created and experienced.
  arXiv  Detail & Related papers  (2025-03-21T17:59:22Z)
• Make-A-Character 2: Animatable 3D Character Generation From a Single Image [27.270195676966637]
  Make-A-Character 2 is an advanced system for generating high-quality 3D characters from single portrait photographs.<n>The entire image-to-3D-character generation process takes less than 2 minutes.<n>These technologies have been integrated into our conversational AI avatar products.
  arXiv  Detail & Related papers  (2025-01-14T06:21:31Z)
• UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics [74.10447111842504]
  UniReal is a unified framework designed to address various image generation and editing tasks.<n>Inspired by recent video generation models, we propose a unifying approach that treats image-level tasks as discontinuous video generation.<n>Although designed for image-level tasks, we leverage videos as a scalable source for universal supervision.
  arXiv  Detail & Related papers  (2024-12-10T18:59:55Z)
• GameGen-X: Interactive Open-world Game Video Generation [10.001128258269675]
  We introduce GameGen-X, the first diffusion transformer model specifically designed for both generating and interactively controlling open-world game videos.<n>It simulates an array of game engine features, such as innovative characters, dynamic environments, complex actions, and diverse events.<n>It provides interactive controllability, predicting and future altering content based on the current clip, thus allowing for gameplay simulation.
  arXiv  Detail & Related papers  (2024-11-01T17:59:17Z)
• Unbounded: A Generative Infinite Game of Character Life Simulation [68.37260000219479]
  We introduce the concept of a generative infinite game, a video game that transcends the traditional boundaries of finite, hard-coded systems by using generative models. We leverage recent advances in generative AI to create Unbounded: a game of character life simulation that is fully encapsulated in generative models.
  arXiv  Detail & Related papers  (2024-10-24T17:59:31Z)
• StoryImager: A Unified and Efficient Framework for Coherent Story Visualization and Completion [78.1014542102578]
  Story visualization aims to generate realistic and coherent images based on a storyline. Current models adopt a frame-by-frame architecture by transforming the pre-trained text-to-image model into an auto-regressive manner. We propose a bidirectional, unified, and efficient framework, namely StoryImager.
  arXiv  Detail & Related papers  (2024-04-09T03:22:36Z)
• DreamVideo: Composing Your Dream Videos with Customized Subject and Motion [52.7394517692186]
  We present DreamVideo, a novel approach to generating personalized videos from a few static images of the desired subject. DreamVideo decouples this task into two stages, subject learning and motion learning, by leveraging a pre-trained video diffusion model. In motion learning, we architect a motion adapter and fine-tune it on the given videos to effectively model the target motion pattern.
  arXiv  Detail & Related papers  (2023-12-07T16:57:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.