在消费级显卡上实现低延迟实时可控世界模拟
DreamForge-World 0.1 Preview: A Low-Compute Real-Time Controllable World Model
- 基于视频模型改进，加入动作残差路径提升控制性
- 单张RTX 4090运行达14-15帧/秒，内存占用低
- 适合游戏开发、交互式仿真等需要轻量化实时模型的场景
我们提出DreamForge-World 0.1 Preview，一个面向实时交互式世界模拟的轻量级基础世界模型。系统基于LongLive 1自回归视频架构，源自Wan2.1-T2V-1.3B，引入受Matrix-Game系列启发的残差动作路径。该模型聚焦于前沿级世界模拟器的补充方向：低算力适配、消费级GPU运行与广泛交互能力覆盖。支持键盘鼠标实时控制、多模态初始化、中途改写提示、双视角操作及原生480p分辨率下分钟级交互推演，单张RTX 4090可实现最高14至15帧/秒，内存开销极小。通过使用开源视频骨干网络并进行针对性微调，以高成本效益构建预览系统。当前版本非内存完备或前沿质量世界模拟器，但展示了在消费级显卡上实现实时可控世界模型预览的可行性路径。
原文摘要 · Abstract (English)
We present DreamForge-World 0.1 Preview, a preview foundational world model for real-time interactive world simulation. The system adapts the LongLive 1 autoregressive video stack, itself derived from Wan2.1-T2V-1.3B, with a residual action pathway inspired by the Matrix-Game family. DreamForge-World 0.1 Preview focuses on a complementary axis to frontier-scale world simulators: low-compute adaptation, consumer-GPU runtime, and broad interactive capability coverage. It supports live keyboard and mouse control, multimodal initialization, mid-stream reprompting, dual-view operation, and minute-scale interactive rollouts at native 480p resolution, reaching up to 14 to 15 FPS FPS on a single RTX 4090 with a low memory footprint. By leveraging open video backbones and applying targeted adaptation runs, we build the preview system with high cost-efficiency. DF-World 0.1 Preview is not yet a memory-complete or frontier-quality world simulator, but demonstrates a practical low-compute route toward real-time controllable world-model previews on consumer GPUs.
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。