DreamForge-World 0.1 Preview:低算力实时可控世界模型预览版
阅读原文· arxiv.orgDreamForge-World 0.1 Preview 是一款低算力实时交互世界模型预览版,基于 LongLive 1 自回归视频栈(源自 Wan2.1-T2V-1.3B)和 Matrix-Game 系列的残差动作路径。支持实时键盘鼠标控制、多模态初始化、中流重提示及双视角操作。在单张 RTX 4090 上以原生 480p 分辨率达到 14-15 FPS,内存占用低,展示了在消费级 GPU 上实现实时可控世界模型预览的低算力路线。
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.