arXiv:2505.14135cs.CV2025-05被引 4

Hunyuan-Game用AI生成高质量游戏图像与视频,提升创作效率。

Hunyuan-Game: Industrial-grade Intelligent Game Creation Model

  • 基于数十亿游戏图像和数百万游戏/动漫视频训练,定制化生成模型。
  • 支持文本/参考图生成特效、角色、360度动态形象及超分辨率视频。
  • 适合游戏开发者快速产出符合风格的视觉内容,工业级应用落地。

智能游戏创作代表游戏开发的变革性进展,利用生成式人工智能动态生成和增强游戏内容。尽管生成模型取得显著进展,但高质量游戏资产(包括图像和视频)的综合生成仍是重大挑战。为创建高保真且契合玩家偏好、显著提升设计效率的游戏内容,我们提出Hunyuan-Game,一项旨在革新智能游戏制作的创新项目。该项目包含两大核心分支:图像生成与视频生成。图像生成部分基于涵盖数十亿游戏图像的海量数据集,开发出专为游戏场景定制的四类模型:(1) 通用文本到图像生成;(2) 游戏视觉效果生成,支持文本到效果及参考图生成;(3) 角色、场景与视觉效果的透明图像生成;(4) 基于草图、黑白图与白模的角色生成。视频生成部分基于涵盖数百万游戏与动漫视频的综合数据集,开发出五种核心算法模型,分别解决游戏开发中的关键痛点,并具备对多种游戏视频场景的强大适应性:(1) 图像到视频生成;(2) 360度姿态/动作角色视频合成;(3) 动态插画生成;(4) 生成式视频超分辨率;(5) 交互式游戏视频生成。这些图像与视频生成模型不仅具有高水平的美学表达能力,还深度融合领域知识,建立了对多样游戏与动漫艺术风格的系统性理解。

原文摘要 · Abstract (English)

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.

游戏生成图像生成视频生成AI创作

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。