ETC：基于误差感知趋势一致性的免训练扩散模型加速方法
ETC: training-free diffusion models acceleration with Error-aware Trend Consistency
AI总结：
针对免训练扩散模型加速方法存在的轨迹偏差与结果不一致问题，提出含一致性趋势预测器和误差容忍搜索机制的ETC框架，在FLUX上实现2.65倍加速且性能损失极小。
摘要：
扩散模型已取得卓越的生成质量，但仍受限于高昂的迭代采样成本。近期的免训练方法通过复用模型输出来加速扩散过程，然而这类方法忽略了去噪趋势，且缺乏针对模型特定容忍度的误差控制，导致多步复用下出现轨迹偏差，加剧生成结果的不一致性。为解决这些问题，我们提出误差感知趋势一致性（Error-aware Trend Consistency，ETC）框架：（1）引入一致性趋势预测器，利用扩散轨迹的平滑连续性，将历史去噪模式投影到稳定的未来方向，并逐步分配到多个近似步骤中，在不偏离轨迹的前提下实现加速；（2）提出模型特定的误差容忍搜索机制，通过识别从易变语义规划到稳定质量细化的转折点来推导校正阈值。实验表明，ETC在FLUX上实现了2.65倍加速，且一致性下降可忽略不计（SSIM分数降低0.074）。
英文摘要：
Diffusion models have achieved remarkable generative quality but remain bottlenecked by costly iterative sampling. Recent training-free methods accelerate diffusion process by reusing model outputs. However, these methods ignore denoising trends and lack error control for model-specific tolerance, leading to trajectory deviations under multi-step reuse and exacerbating inconsistencies in the generated results. To address these issues, we introduce Error-aware Trend Consistency (ETC), a framework that (1) introduces a consistent trend predictor that leverages the smooth continuity of diffusion trajectories, projecting historical denoising patterns into stable future directions and progressively distributing them across multiple approximation steps to achieve acceleration without deviating; (2) proposes a model-specific error tolerance search mechanism that derives corrective thresholds by identifying transition points from volatile semantic planning to stable quality refinement. Experiments show that ETC achieves a 2.65x acceleration over FLUX with negligible (-0.074 SSIM score) degradation of consistency.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
