DreamForge-World 0.1 預覽版：低計算量即時可控世界模型

摘要

我們推出 DreamForge-World 0.1 Preview，這是一個用於即時互動世界模擬的預覽基礎世界模型。該系統採用 LongLive 1 自迴歸影片堆疊（其本身源自 Wan2.1-T2V-1.3B），並配備受 Matrix-Game 系列啟發的殘差動作路徑。DreamForge-World 0.1 Preview 專注於與前沿規模世界模擬器互補的軸向：低計算量適配、消費級 GPU 運行時，以及廣泛的互動能力覆蓋。它支援即時鍵盤與滑鼠控制、多模態初始化、中段重新提示、雙視角操作，以及原生 480p 解析度下達分鐘級的互動式展開，在單張 RTX 4090 上可達到 14 至 15 FPS，且記憶體佔用量低。透過利用開放式影片骨幹網路並執行針對性的適配運行，我們以高成本效益建構了此預覽系統。DF-World 0.1 Preview 尚非記憶體完整或前沿品質的世界模擬器，但展示了一條在消費級 GPU 上實現即時可控世界模型預覽的實用低計算途徑。

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.