首个支持实时双人对战的生成式游戏引擎，可从键盘输入生成完整对战画面。
WanToFight: Real-Time Generative Game Engine for Multi-Player Combat Interaction
- 基于视频扩散模型构建流式生成架构，支持低延迟实时推理。
- 在单张RTX 5090上实现30帧/秒、512x384分辨率的全程稳定运行。
- 首次融合多人控制、实时交互与对抗性玩法，适合游戏生成研究者。
我们提出WanToFight，一个基于Wan-1.3B视频扩散变换器的生成式游戏引擎，能够从键盘输入实时模拟《拳皇97》双人对战场景。现有生成式游戏引擎多局限于单人第一人称或非实时协作场景，尚未同时解决多人控制、实时推理、复杂物理交互和对抗性对战等挑战。WanToFight通过三个组件实现突破：采用块因果注意力与滚动键值缓存的流式自回归生成器；视觉引导的玩家关联模块，将键盘信号绑定至角色身份；以及基于单人到完整对战课程训练的门控局部因果键盘注入模块。一个四步DMD蒸馏的学生模型搭配剪枝的VAE解码器，在单张NVIDIA RTX 5090显卡上实现了持续30FPS、512x384分辨率下的完整对局运行。据我们所知，WanToFight是首个整合多人控制、实时推理、复杂物理交互与对抗性对战的生成式游戏引擎。
原文摘要 · Abstract (English)
We present WanToFight, a generative game engine that simulates real-time, two-player The King of Fighters '97 (KOF~'97) gameplay from keyboard input. Prior generative game engines target either single-player first-person settings or non-real-time cooperative scenarios; multi-player control, real-time inference, complex physical interaction, and adversarial gameplay have not been jointly addressed. WanToFight closes this gap with three components built on the Wan-1.3B video diffusion transformer: a streaming autoregressive generator with block-causal attention and a rolling KV cache; a visually grounded Player Association module that binds each player's keyboard signal to a character identity; and a gated, locally causal keyboard injection module trained with a single-player-to-full-gameplay curriculum. A four-step DMD-distilled student paired with a pruned VAE decoder sustains 30FPS at 512x384 on a single NVIDIA RTX 5090 over the duration of a complete match. To our knowledge, WanToFight is the first generative game engine to combine multi-player control, real-time inference, complex physical interaction, and adversarial gameplay in one system.
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。