LiveAnimate：实时稳定长时程流式人体动画

摘要

姿态驱动的人体动画根据单张参考图像和驱动姿态流合成目标人物的视频。实时生成对于直播、远程临场和虚拟化身等交互式应用至关重要，然而基于扩散的系统生成单个片段需要数分钟到数小时，无法实现响应式交互。我们提出LiveAnimate，据我们所知，这是首个将实时流式生成与十亿参数规模下稳定长序列生成相结合的动画系统，基于一个140亿参数的视频扩散Transformer（DiT）。两阶段训练流程首先通过参考锚定的教师强制适应，将预训练的双向DiT适配为块因果自回归生成器，再通过块级自强制蒸馏将采样预算降至三步。为在长时间流式生成中保持外观一致，我们引入姿态检索Sink注意力（PR-Sink），这是一种有界KV缓存机制，结合了永久锚定首个生成块的静态Sink、持有姿态检索历史块的动态Sink，以及一个三槽滚动窗口。当某个姿态重复出现时，PR-Sink能恢复相关外观上下文而无须保留整个序列，因此内存占用和每块延迟均保持恒定，与流式时长无关。结合Ulysses序列并行与算子融合，这些设计使系统在两块NVIDIA H100 GPU上实现19.63 FPS的流式推理。在三分钟基准测试中，LiveAnimate从最初30秒到最后一分钟几乎保持恒定的感知质量和身份一致性，而此前系统对同样的长序列生成要么显著退化，要么需要数小时的离线计算。这些结果为交互式全身动画在质量、延迟和时长方面确立了新的工作点。

English

Pose-driven human animation synthesizes a video of a target person from a single reference image and a driving pose stream. Real-time generation is essential for interactive applications such as live streaming, telepresence, and virtual avatars, yet diffusion-based systems require minutes to hours per clip, precluding responsive interaction. We present LiveAnimate, to our knowledge the first animation system to combine real-time streaming with stable long-form generation at billion scale, built on a 14B-parameter video Diffusion Transformer (DiT). A two-stage training pipeline first adapts a pretrained bidirectional DiT into a block-causal autoregressive generator through Reference-Anchored Teacher-Forcing Adaptation, and then reduces the sampling budget to three steps through Block-wise Self-Forcing Distillation. To preserve appearance over extended streams, we introduce Pose-Retrieval Sink Attention (PR-Sink), a bounded KV-cache mechanism combining a Static Sink that permanently anchors the first generated block, a Dynamic Sink that holds a pose-retrieved historical block, and a three-slot Rolling Window. When a pose recurs, PR-Sink restores the relevant appearance context without retaining the entire sequence, so memory and per-block latency remain constant regardless of stream duration. Together with Ulysses sequence parallelism and operator fusion, these designs enable 19.63\,FPS streaming inference on two NVIDIA H100 GPUs. On a three-minute benchmark, LiveAnimate maintains nearly constant perceptual quality and identity from the first 30 seconds to the final minute, while prior systems degrade substantially or require hours of offline computation for the same rollout. These results establish a new operating point in quality, latency, and duration for interactive full-body animation.