让视频生成在2-4步内快速出高清结果，解决模糊抖动问题。
Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation
- 通过端点一致性约束优化多步去噪过程，避免运动漂移
- 利用缓存质量作为条件，引导低质输出向高质量参考靠拢
- 兼容多种缓存机制，适配实时视频生成场景
将视频生成模型压缩至极低推理预算（如2–4次去噪步骤）对实时部署至关重要，但面临挑战。轨迹一致性蒸馏在复杂动态下易趋于保守，导致画面过平滑、运动弱化；分布匹配蒸馏（DMD）可恢复清晰、模式聚焦的样本，但其局部训练信号未显式规范去噪更新在时间步间的组合方式，使连续推演易产生漂移。为此，本文提出自洽分布匹配蒸馏（SC-DMD），显式规范连续去噪更新的端点一致性组合。针对实时自回归视频生成，进一步将键值缓存（KV cache）视为质量参数化条件，提出缓存-分布感知训练。该方案在多步推演中应用SC-DMD，引入缓存条件特征对齐目标，引导低质量输出向高质量参考对齐。在非自回归骨干（如Wan 2.1）和自回归实时范式（如Self Forcing）上广泛实验表明，所提方法Salt在低NFE条件下持续提升视频生成质量，且与多种缓存记忆机制兼容。
原文摘要 · Abstract (English)
Distilling video generation models to extremely low inference budgets (e.g., 2--4 NFEs) is crucial for real-time deployment, yet remains challenging. Trajectory-style consistency distillation often becomes conservative under complex video dynamics, yielding an over-smoothed appearance and weak motion. Distribution matching distillation (DMD) can recover sharp, mode-seeking samples, but its local training signals do not explicitly regularize how denoising updates compose across timesteps, making composed rollouts prone to drift. To overcome this challenge, we propose Self-Consistent Distribution Matching Distillation (SC-DMD), which explicitly regularizes the endpoint-consistent composition of consecutive denoising updates. For real-time autoregressive video generation, we further treat the KV cache as a quality parameterized condition and propose Cache-Distribution-Aware training. This training scheme applies SC-DMD over multi-step rollouts and introduces a cache-conditioned feature alignment objective that steers low-quality outputs toward high-quality references. Across extensive experiments on both non-autoregressive backbones (e.g., Wan~2.1) and autoregressive real-time paradigms (e.g., Self Forcing), our method, dubbed \textbf{Salt}, consistently improves low-NFE video generation quality while remaining compatible with diverse KV-cache memory mechanisms. Project page: https://xingtongge.github.io/Salt
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。