通过并行迭代提升扩散模型采样速度，不牺牲生成质量。
Self-Refining Diffusion Samplers: Enabling Parallelization via Parareal Iterations
- 用并行化时间积分思路改进采样流程，先粗略估计再并行精修。
- 在25步的StableDiffusion-v2上提速1.7倍，长轨迹最高达4.3倍。
- 适合需要高速生成且有并行计算资源的部署场景。
扩散模型通过迭代精修生成样本，需数百次串行模型调用。现有方法多通过减少步数或蒸馏来提速，但损失样本质量。本文提出自精炼扩散采样器（SRDS），在保持高质量的同时，以额外并行计算为代价降低延迟。受数值求解微分方程的Parareal算法启发，SRDS先快速生成粗略样本，再通过并行的Parareal迭代逐步精修。该方法保证能准确求解常微分方程并收敛至串行解，同时实现扩散轨迹的并行化，支持批量推理与流水线处理。实验表明，对预训练扩散模型而言，该精修过程早期收敛显著减少所需步数：在25步的StableDiffusion-v2基准上加速1.7倍，长轨迹最高可达4.3倍。
原文摘要 · Abstract (English)
In diffusion models, samples are generated through an iterative refinement process, requiring hundreds of sequential model evaluations. Several recent methods have introduced approximations (fewer discretization steps or distillation) to trade off speed at the cost of sample quality. In contrast, we introduce Self-Refining Diffusion Samplers (SRDS) that retain sample quality and can improve latency at the cost of additional parallel compute. We take inspiration from the Parareal algorithm, a popular numerical method for parallel-in-time integration of differential equations. In SRDS, a quick but rough estimate of a sample is first created and then iteratively refined in parallel through Parareal iterations. SRDS is not only guaranteed to accurately solve the ODE and converge to the serial solution but also benefits from parallelization across the diffusion trajectory, enabling batched inference and pipelining. As we demonstrate for pre-trained diffusion models, the early convergence of this refinement procedure drastically reduces the number of steps required to produce a sample, speeding up generation for instance by up to 1.7x on a 25-step StableDiffusion-v2 benchmark and up to 4.3x on longer trajectories.
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。