动态分配时空计算资源，实现视频生成加速且几乎不损失质量
Dynamic Video Generation: Shaping Video Generation Across Time and Space
- 根据内容自动选择时空计算策略，无需人工调参
- 在 HunyuanVideo 上最快达 7 倍加速，结合蒸馏可达 18 倍
- 适用于多模型多任务，可作为大模型高效生成核心组件
扩散模型在视频生成中表现优异，但其迭代去噪过程因每步处理大量标记而计算成本高。近期渐进式分辨率采样通过降低早期潜空间分辨率实现加速，但在视频生成中面临挑战：额外的时间维度导致不同视频的时空需求差异大，仅压缩单一维度常致加速有限或质量下降。为此，我们提出 DVG 动态视频生成框架，联合分配时间和空间的计算资源，自动选择内容感知的加速策略，无需手动调参或重训练。DVG 在多种模型和任务上实现近乎无损加速，在 HunyuanVideo 与 HunyuanVideo-1.5 上最高达 7 倍速度提升，结合蒸馏后更达 18 倍，展现出其作为当前大规模高效视频生成系统关键组件的巨大潜力。代码已置于补充材料，并将在 GitHub 上发布。
原文摘要 · Abstract (English)
Diffusion models have achieved impressive performance in video generation, but their iterative denoising process remains computationally expensive due to the large number of tokens processed at each timestep. Recently, progressive resolution sampling has emerged as a promising acceleration approach by reducing latent resolution in early stages. However, scaling this idea to video generation remains challenging, as the additional temporal dimension introduces diverse spatio-temporal demands across different videos, and compressing only a single dimension often leads to limited acceleration or degraded quality. Therefore, we propose DVG, a Dynamic Video Generation framework that jointly allocates computation across time and space, automatically selecting content-aware acceleration strategies without manual tuning or retraining. DVG achieves near-lossless acceleration across models and tasks, reaching up to 7 times speedup on HunyuanVideo and HunyuanVideo-1.5, and 18 times when combined with distillation, demonstrating its potential as a key component in today's large-scale efficient video generation systems. Our code is in supplementary material and will be released on Github.
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。