通过复用验证时的精确特征，加速扩散模型生成过程。
FeatFix: Reuse What You Verify through Local Exact-Feature Correction for Faster Cached Diffusion Inference
- 在特定层-时间点用精确特征替换草稿输出，避免重复计算。
- 实测最高提速6.70倍，图像视频生成质量保持良好。
- 适合追求推理速度且无需训练的扩散模型使用者。
扩散模型广泛用于生成高质量图像和视频，但其迭代去噪过程计算成本高。一类无需训练的加速方法通过重用缓存的中间特征或预测未来特征来降低开销。为控制草稿偏差，这些方法有时会计算精确块特征进行验证，但该特征通常仅用于误差检测或决策引导后即丢弃。我们发现，该精确特征可被重用于修正：在验证位置转发它可重置局部草稿残差，减少下游特征误差。基于此，提出FeatFix，一种针对缓存扩散推理的局部精确特征修正方法。FeatFix在固定的稀疏层-时间点集上运行，每个选定点用相同输入状态计算出的精确输出替换完整草稿块输出，避免逐标记或逐通道的部分替换及整时间步重算。跨四个图像与视频骨干网络的实验表明，FeatFix持续加速生成，相比基线最高提速6.70倍，同时保持竞争力的输出质量。
原文摘要 · Abstract (English)
Diffusion models are widely used to generate high-quality images and videos, but their iterative denoising process remains computationally intensive. A growing class of training-free accelerators reduces this cost by reusing cached intermediate features or forecasting future ones. To control draft drift, these methods sometimes compute an exact block feature for verification. Yet the resulting exact feature is typically used only to measure discrepancy or guide a later decision and is then discarded. We find that this previously computed feature can instead be reused for correction. Forwarding it at the verification site resets the local draft residual and reduces downstream feature error. Based on this observation, we introduce FeatFix, a local exact-feature correction method for cached diffusion inference. FeatFix operates at a fixed sparse set of layer--timestep sites. At each selected site, it replaces the complete draft block output with the exact output computed from the same incoming state, avoiding token- or channel-level partial replacement and full-timestep recomputation. Experiments across four image and video backbones show that FeatFix consistently accelerates generation, achieving a speedup of up to $6.70\times$ over Vanilla while maintaining competitive output quality.
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。