Lumos-Nexus: 面向视频统一模型的同质潜在空间高效频率桥接方法

摘要

基于连接器的视频统一模型在指令驱动的视频合成中展现出强大能力，但将高保真生成器集成到统一训练流程中会带来高昂的计算成本，从而限制可实现的视觉质量。为此，我们提出Lumos-Nexus——一种训练高效的统一视频生成框架，在显著提升视觉保真度的同时，促进强大的推理驱动生成能力的发展。Lumos-Nexus采用两阶段设计：1）训练阶段，仅将轻量级生成器与理解模块对齐，以学习接收推理驱动的语义控制；2）推理阶段，我们引入统一渐进式频域桥接（UPFB）机制，在共享潜在空间中逐步将生成任务交接给高容量预训练生成器，从而实现由粗到细的精化过程，在保证推理质量的同时生成高保真视频。针对推理驱动视频生成基准的缺失，我们推出VR-Bench，该基准评估模型将推断意图转化为连贯且语义对齐的视频内容的能力。大量实验表明，Lumos-Nexus在VBench上显著提升了视觉真实度与时序连贯性，同时在VR-Bench上展现出强大的基于推理的生成性能。代码与模型已开源至 https://jiazheng-xing.github.io/nexus-lumos-home/。

English

Connector-based video unified models have demonstrated strong capability in instruction-grounded video synthesis, but integrating a large high-fidelity generator into the unified training loop is computationally prohibitive, limiting achievable visual quality. We therefore propose Lumos-Nexus, a training-efficient unified video generation framework that facilitates the development of strong reasoning-driven generation capabilities while significantly enhancing visual fidelity. Lumos-Nexus adopts a two-stage design: 1) During training, only a lightweight generator is aligned with the understanding block to learn to take in reasoning-driven semantic control. 2) During inference, we introduce Unified Progressive Frequency Bridging (UPFB) to progressively hand off generation to a high-capacity pretrained generator in the shared latent space, enabling coarse-to-fine refinement and producing high-fidelity videos without compromising reasoning quality. To fill the gap in reasoning-driven video generation benchmarks, we introduce VR-Bench, which assesses a model's capability to translate inferred intent into coherent and semantically aligned video content. Extensive experiments demonstrate that Lumos-Nexus achieves substantial gains in visual realism and temporal coherence on VBench, while exhibiting strong reasoning-based generative performance on VR-Bench. Code and models are available at https://jiazheng-xing.github.io/nexus-lumos-home/.