FlashPortrait：基于自适应潜变量预测的6倍速无限肖像动画
FlashPortrait: 6x Faster Infinite Portrait Animation with Adaptive Latent Prediction
提出基于高阶潜变量导数的未来步预测方法，可跳过多个去噪步实现6倍加速，该技术可迁移到其他扩散模型加速场景；同时归一化表情块与动态滑动窗口策略为长视频生成中的身份一致性提供了可复用方案。
原文依据 FlashPortrait utilizes higher-order latent derivatives at the current timestep to directly predict latents at future timesteps, thereby skipping several denoising steps and achieving 6xspeed acceleration.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论当前基于扩散的长肖像动画加速方法难以保证身份（ID）一致性。本文提出FlashPortrait，一种端到端的视频扩散Transformer，能够合成保持身份一致的无限长视频，同时实现高达6倍的推理加速。具体而言，FlashPortrait首先使用现成的提取器计算与身份无关的面部表情特征。然后引入归一化面部表情块，通过分别用均值和方差对特征进行归一化，将面部特征与扩散潜变量对齐，从而提高面部建模中的身份稳定性。在推理过程中，FlashPortrait采用动态滑动窗口方案，在重叠区域进行加权混合，确保长动画中的平滑过渡和身份一致性。在每个上下文窗口中，基于特定时间步的潜变量变化率和扩散层之间的导数幅度比，FlashPortrait利用当前时间步的高阶潜变量导数直接预测未来时间步的潜变量，从而跳过若干去噪步骤，实现6倍速度加速。基准实验在定性和定量上均证明了FlashPortrait的有效性。
英文原文摘要 1304 字符
Current diffusion-based acceleration methods for long-portrait animation struggle to ensure identity (ID) consistency. This paper presents FlashPortrait, an end-to-end video diffusion transformer capable of synthesizing ID-preserving, infinite-length videos while achieving up to 6xacceleration in inference speed. In particular, FlashPortrait begins by computing the identity-agnostic facial expression features with an off-the-shelf extractor. It then introduces a Normalized Facial Expression Block to align facial features with diffusion latents by normalizing them with their respective means and variances, thereby improving identity stability in facial modeling. During inference, FlashPortrait adopts a dynamic sliding-window scheme with weighted blending in overlapping areas, ensuring smooth transitions and ID consistency in long animations. In each context window, based on the latent variation rate at particular timesteps and the derivative magnitude ratio among diffusion layers, FlashPortrait utilizes higher-order latent derivatives at the current timestep to directly predict latents at future timesteps, thereby skipping several denoising steps and achieving 6xspeed acceleration. Experiments on benchmarks show the effectiveness of FlashPortrait both qualitatively and quantitatively.