虚拟形象V：扩展视频参考的虚拟形象视频生成

摘要

生成不仅在外观上、而且在行为上可被识别的数字人视频，忠实复现其说话节奏、手势习惯和表情动态，仍是一项开放性挑战。现有方法主要依赖单张静态图像作为条件输入，这缺乏足够的身份信息且无法捕捉动态运动特征，而标准的像素级损失函数对决定数字人保真度的感知关键面部区域关注不足。我们提出Avatar V——一个生产级框架，通过视频参考条件身份建模解决上述局限。该模型不再将身份信息压缩为固定维度嵌入，而是直接以参考视频的完整标记序列为条件，通过注意力机制从参考上下文中学习复制静态身份属性（面部几何、皮肤纹理）与动态行为模式（说话节奏、微表情）。我们引入稀疏参考注意力（Sparse Reference Attention），这是一种非对称机制，能够以线性复杂度对任意长度的参考视频进行条件控制；同时提出运动表征流，实现闭环的说话风格迁移；以及继承完整参考条件的身份感知超分辨率精炼器。这些技术依托于数据引擎——从5000万原始视频中精选超过1亿训练片段，以及五阶段训练流程：流匹配预训练、个性微调、两阶段蒸馏（实现超10倍加速）和基于强化学习人类反馈的对齐，部署于数千块GPU上。Avatar V可生成不限时长的1080p视频，在我们的跨场景基准测试中，其在身份保留、唇形同步和生成质量上达到最优，并在自动化指标和人工评估中持续优于Seedance 2.0、Kling O3 Pro、Veo 3.1及OmniHuman 1.5等领先系统。

English

Generating avatar videos that are not merely visually similar to a target individual but behaviorally recognizable, faithfully reproducing their talking rhythm, gestural tendencies, and expression dynamics, remains an open challenge. Existing methods predominantly condition on single static images, which provide insufficient identity information and cannot capture dynamic motion traits, while standard pixel-level objectives underserve the perceptually critical facial regions that determine avatar fidelity. We present Avatar V, a production-scale framework that addresses these limitations through video-reference-conditioned identity modeling. Rather than compressing identity into fixed-size embeddings, the model conditions directly on the full token sequence of a reference video, learning to reproduce both static identity attributes (facial geometry, skin texture) and dynamic behavioral patterns (talking rhythm, micro-expressions) through attention over the reference context. We introduce Sparse Reference Attention, an asymmetric mechanism achieving linear-complexity conditioning on arbitrarily long references; a motion representation stream enabling closed-loop talking style transfer; and an identity-aware super-resolution refiner inheriting the full reference conditioning. These are supported by a data engine curating 100M+ training clips from 50M raw videos, and a five-stage training pipeline with flow matching pre-training, personality fine-tuning, two-phase distillation (>10x acceleration), and RLHF alignment, deployed across thousands of GPUs. Avatar V generates 1080p videos of unlimited duration, achieving state-of-the-art identity preservation, lip synchronization, and generation quality on our cross-scene benchmark, consistently outperforming leading systems including Seedance 2.0, Kling O3 Pro, Veo 3.1, and OmniHuman 1.5 in both automated metrics and human evaluation.