视频生成终于能记住消失的物体了
现在的AI视频生成，物体一旦移出画面再回来，往往就变样了——颜色、形状、甚至身份都乱掉。WorldDirector把「物体怎么动」和「画面怎么渲染」拆成两件事：先用大语言模型规划物体在3D空间里的完整轨迹（包括它出画后去哪、怎么回来），再把轨迹当指令传给视频生成器。这样物体即使消失很久再出现，长相和身份也能保持一致。你还能自由切换视角，像在游戏里调镜头一样。它不是你明天就能用的工具，但解决了视频生成里一个核心痛点——让AI真的「记住」东西。
📄 原文摘要(英文)
We present WorldDirector, a highly controllable video world model framework designed for persistent dynamic object memory and unrestricted viewpoint exploration. Unlike existing world models that entangle physical dynamics with pixel rendering and rely on continuous visual observation to sustain motion, our framework explicitly decouples semantic motion orchestration from visual generation. By leveraging an LLM to coordinate 3D trajectories with camera movements and subsequently employing these orchestrated trajectories as control signals for video generation, our approach ensures strict physical logic and appearance stability, successfully preserving the exact visual identities of dynamic entities even when they re-enter the scene after prolonged periods out of view. Experimental results demonstrate that our method supports the synthesis of complex and extended events with unprecedented controllability and persistent dynamic object memory. Project Page: https://worlddirector.github.io/