提出自适应块级注意力，让视频生成更快更省资源。
NABLA: Neighborhood Adaptive Block-Level Attention
- 用动态稀疏阈值控制块级注意力，自动聚焦重要区域。
- 训练推理速度提升2.7倍，质量损失几乎为零。
- 无需特殊代码，可直接接入PyTorch，适合视频生成研究者。
基于Transformer的架构在视频生成任务中表现优异，但全注意力机制的二次复杂度成为瓶颈，尤其在高分辨率和长时序视频上。本文提出NABLA——一种新型邻域自适应块级注意力机制，能动态适应视频扩散模型中的稀疏模式。通过块级注意力结合自适应稀疏驱动阈值，NABLA在不牺牲生成质量的前提下显著降低计算开销。该方法无需定制底层算子，可无缝集成至PyTorch的Flex Attention操作中。实验表明，NABLA在几乎不损失定量指标（CLIP分数、VBench分数、人类评估分数）和视觉质量的情况下，实现高达2.7倍的训练与推理加速。代码与模型权重已公开：https://github.com/gen-ai-team/Wan2.1-NABLA。
原文摘要 · Abstract (English)
Recent progress in transformer-based architectures has demonstrated remarkable success in video generation tasks. However, the quadratic complexity of full attention mechanisms remains a critical bottleneck, particularly for high-resolution and long-duration video sequences. In this paper, we propose NABLA, a novel Neighborhood Adaptive Block-Level Attention mechanism that dynamically adapts to sparsity patterns in video diffusion transformers (DiTs). By leveraging block-wise attention with adaptive sparsity-driven threshold, NABLA reduces computational overhead while preserving generative quality. Our method does not require custom low-level operator design and can be seamlessly integrated with PyTorch's Flex Attention operator. Experiments demonstrate that NABLA achieves up to 2.7x faster training and inference compared to baseline almost without compromising quantitative metrics (CLIP score, VBench score, human evaluation score) and visual quality drop. The code and model weights are available here: https://github.com/gen-ai-team/Wan2.1-NABLA
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。