The substantial computational costs of diffusion models, particularly due to the repeated denoising steps crucial for high-quality image generation, present a major obstacle to their widespread adoption. While several studies have attempted to address this issue by reducing the number of score function evaluations using advanced ODE solvers without fine-tuning, the decreased number of denoising iterations misses the opportunity to update fine details, resulting in noticeable quality degradation. In our work, we introduce an advanced acceleration technique that leverages the temporal redundancy inherent in diffusion models. Reusing feature maps with high temporal similarity opens up a new opportunity to save computation without sacrificing output quality. To realize the practical benefits of this intuition, we conduct an extensive analysis and propose a novel method, FRDiff. FRDiff is designed to harness the advantages of both reduced NFE and feature reuse, achieving a Pareto frontier that balances fidelity and latency trade-offs in various generative tasks.

引入一种高级加速技术——FRDiff，通过利用扩散模型中固有的时间冗余，重复使用具有高时间相似性的特征图，实现了在各种生成任务中在保真度和延迟折衷之间平衡的Pareto前沿。

FRDiff: 精细的零编码加速扩散模型的特征复用