FastLightGen：更少步数与参数的高效轻量视频生成
FastLightGen: Fast and Light Video Generation with Fewer Steps and Parameters
把「少步采样蒸馏」与「参数剪枝」放进同一个教师-学生框架里联合优化，并指出先构造一个最优教师模型是关键；做视频扩散加速时可以直接复用这套联合蒸馏流程与 4 步 + 30% 剪枝的配置经验。
原文依据 a generator using 4-step sampling and 30% parameter pruning achieves optimal visual quality under a constrained inference budget
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期，Hunyuan、WanX、Veo3、Kling 等强大视频生成模型的出现，为该领域开启了新时代。然而，这些模型的实际部署受到其巨大计算开销的严重阻碍，这种开销源于庞大的参数规模以及推理时所需的迭代式多步采样过程。此前的生成模型加速研究主要沿两条不同路线展开：减少采样步数（如 LCM、DMD 和 MagicDistillation），或压缩模型规模以实现更高效的推理（如 ICMD）。同时压缩二者以构建快速轻量模型的潜力，仍是一条尚未探索的路径。本文提出 FastLightGen，一种将大型、计算昂贵的模型转化为快速轻量对应模型的算法。其核心思想是在一个同时蒸馏模型规模与推理步数的协同框架内，构造一个最优教师模型，该教师模型被设计为最大化学生模型的性能。我们在 HunyuanVideo-ATI2V 和 WanX-TI2V 上的大量实验表明，在受限的推理预算下，采用 4 步采样与 30% 参数剪枝的生成器可达到最优视觉质量。此外，FastLightGen 始终优于所有对比方法，在高效视频生成方面确立了新的最优水平。
英文原文摘要 1422 字符
The recent advent of powerful video generation models, such as Hunyuan, WanX, Veo3, and Kling, has inaugurated a new era in the field. However, the practical deployment of these models is severely impeded by their substantial computational overhead, which stems from enormous parameter counts and the iterative, multi-step sampling process required during inference. Prior research on accelerating generative models has predominantly followed two distinct trajectories: reducing the number of sampling steps (e.g., LCM, DMD, and MagicDistillation) or compressing the model size for more efficient inference (e.g., ICMD). The potential of simultaneously compressing both to create a fast and lightweight model remains an unexplored avenue. In this paper, we propose _**FastLightGen**_, an algorithm that transforms large, computationally expensive models into fast, lightweight counterparts. The core idea is to construct an optimal teacher model, one engineered to maximize student performance, within a synergistic framework for distilling both model size and inference steps. Our extensive experiments on HunyuanVideo-ATI2V and WanX-TI2V reveal that a generator using 4-step sampling and 30% parameter pruning achieves optimal visual quality under a constrained inference budget. Furthermore, FastLightGen consistently outperforms all competing methods, establishing a new state-of-the-art in efficient video generation.