SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer

Haoyi Zhu ,

Haozhe Liu ,

Yuyang Zhao ,

Tian Ye ,

Junsong Chen ,

Jincheng Yu ,

Tong He ,

Song Han ,

Enze Xie

AK's Picks Embodied AI and Robotics World Models GenAI Diffusion TDIG

264

2026年05月14日

我们提出了SANA-WM——一种高效、参数量为26亿的开源世界模型，原生支持长达一分钟的视频生成，可合成高保真、720p分辨率、时长以分钟计的视频，并实现精准的相机运动控制。SANA-WM在视觉质量上可媲美LingBot-World和HY-WorldPlay等大规模工业级基线模型，同时显著提升了整体运行效率。本架构由四大核心设计驱动：（1）混合线性注意力机制（Hybrid Linear Attention），将帧级门控Delta网络（GDN）与Softmax注意力相结合，从而在保障长时序建模能力的同时大幅降低显存开销；（2）双分支相机控制模块（Dual-Branch Camera Control），确保模型严格遵循用户指定的六自由度（6-DoF）相机运动轨迹；（3）两阶段生成流程（Two-Stage Generation Pipeline），在第一阶段生成结果基础上，引入专用于长视频的精细化重构器（long-video refiner），显著提升生成视频的整体质量与帧间一致性；（4）鲁棒的标注流水线（Robust Annotation Pipeline），从公开视频中自动提取具备真实尺度信息的六自由度相机位姿，进而生成高质量、时空一致的动作标签。依托上述设计，SANA-WM在数据使用、训练算力及推理硬件三方面均展现出卓越的效率优势：仅需约21.3万段带真实尺度位姿监督的公开视频片段即可完成训练；在64块H100 GPU上仅需15天即可完成全部训练；单卡GPU即可生成一段60秒的完整视频；其蒸馏轻量化版本经NVFP4量化后，可在单块RTX 5090显卡上于34秒内完成一段60秒、720p分辨率视频的去噪生成。在我们构建的一分钟世界模型评测基准上，SANA-WM的动作跟随准确率明显优于此前所有开源基线模型，且在视觉质量相当的前提下，吞吐量达到现有方案的36倍，为可扩展的世界建模提供了切实可行的高效路径。

We introduce SANA-WM, an efficient 2.6B-parameter open-source world model natively trained for one-minute generation, synthesizing high-fidelity, 720p, minute-scale videos with precise camera control. SANA-WM achieves visual quality comparable to large-scale industrial baselines such as LingBot-World and HY-WorldPlay, while significantly improving efficiency. Four core designs drive our architecture: (1) Hybrid Linear Attention combines frame-wise Gated DeltaNet (GDN) with softmax attention for memory-efficient long-context modeling. (2) Dual-Branch Camera Control ensures precise 6-DoF trajectory adherence. (3) Two-Stage Generation Pipeline applies a long-video refiner to stage-1 outputs, improving quality and consistency across sequences. (4) Robust Annotation Pipeline extracts accurate metric-scale 6-DoF camera poses from public videos to yield high-quality, spatiotemporally consistent action labels. Driven by these designs, SANA-WMdemonstrates remarkable efficiency across data, training compute, and inference hardware: it uses only $\sim$213K public video clips with metric-scale pose supervision, completes training in 15 days on 64 H100s, and generates each 60s clip on a single GPU; its distilled variant can be deployed on a single RTX 5090 with NVFP4 quantization to denoise a 60s 720p clip in 34s. On our one-minute world-model benchmark, SANA-WM demonstrates stronger action-following accuracy than prior open-source baselines and achieves comparable visual quality at $36\times$ higher throughput for scalable world modeling.

许愿