通过可学习参数统一优化扩散模型采样，显著降低计算量
Dual-Solver: A Generalized ODE Solver for Diffusion Models with Dual Prediction
- 引入可学习参数动态调节预测类型与积分区间
- 在3到9次函数求值下提升图像质量与相似度
- 适用于多种生成模型，适合追求高效推理的开发者
扩散模型虽能生成高质量图像，但推理时需大量函数求值（NFE），成本高昂。传统数值方法因预测类型与积分域选择不同，导致采样行为差异。本文提出Dual-Solver，通过可学习参数连续实现：(i) 预测类型的插值，(ii) 积分域的选择，(iii) 残差项调整。保留标准预测-校正结构并维持二阶局部精度。参数通过冻结预训练分类器（如MobileNet、CLIP）的分类目标进行学习。在ImageNet条件生成（DiT、GM-DiT）和文生图（SANA、PixArt-α）任务中，双倍减少函数求值次数（NFE在3≤NFE≤9范围内），均取得更优的FID与CLIP分数。
原文摘要 · Abstract (English)
Diffusion models achieve state-of-the-art image quality. However, sampling is costly at inference time because it requires a large number of function evaluations (NFEs). To reduce NFEs, classical ODE numerical methods have been adopted. Yet, the choice of prediction type and integration domain leads to different sampling behaviors. To address these issues, we introduce Dual-Solver, which generalizes multistep samplers through learnable parameters that continuously (i) interpolate among prediction types, (ii) select the integration domain, and (iii) adjust the residual terms. It retains the standard predictor-corrector structure while preserving second-order local accuracy. These parameters are learned via a classification-based objective using a frozen pretrained classifier (e.g., MobileNet or CLIP). For ImageNet class-conditional generation (DiT, GM-DiT) and text-to-image generation (SANA, PixArt-$α$), Dual-Solver improves FID and CLIP scores in the low-NFE regime ($3 \le$ NFE $\le 9$) across backbones.
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。