通过共享相似图像的采样步骤，加速扩散模型生成并提升质量。
SAGE: Semantic-Aware Shared Sampling for Efficient Diffusion
- 同一类图像共享早期采样过程，减少重复计算。
- 采样成本降低25.5%，FID降5.0%，多样性提升160%。
- 适合需要快速生成且注重质量的视觉应用开发者。
扩散模型在多个领域表现出显著优势，但其高采样成本——需数十次顺序模型评估——仍是主要瓶颈。以往方法主要通过优化求解器或知识蒸馏加速，且对每个查询独立处理。本文提出SAGE，一种语义感知的共享采样框架，通过共享语义相似查询的早期采样阶段，在不牺牲生成质量的前提下降低总采样步数。SAGE结合共享采样机制与定制训练策略，实现效率与质量兼顾。大量实验表明，SAGE使采样成本降低25.5%，生成质量提升：FID降低5.0%，CLIP得分提高5.4%，多样性提升160%（相比基线）。
原文摘要 · Abstract (English)
Diffusion models manifest evident benefits across diverse domains, yet their high sampling cost, requiring dozens of sequential model evaluations, remains a major limitation. Prior efforts mainly accelerate sampling via optimized solvers or distillation, which treat each query independently. In contrast, we reduce total number of steps by sharing early-stage sampling across semantically similar queries. To enable such efficiency gains without sacrificing quality, we propose SAGE, a semantic-aware shared sampling framework that integrates a shared sampling scheme for efficiency and a tailored training strategy for quality preservation. Extensive experiments show that SAGE reduces sampling cost by 25.5%, while improving generation quality with 5.0% lower FID, 5.4% higher CLIP, and 160% higher diversity over baselines.
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。