FlowConsist: 使您的流与真实轨迹一致
FlowConsist: Make Your Flow Consistent with Real Trajectory
AI总结：
FlowConsist通过强制轨迹一致性解决快速流模型中的轨迹漂移和误差积累问题，仅需一次采样步即在ImageNet 256×256上取得新的SOTA性能。
摘要：
快速流模型通过学习直接预测ODE路径积分来加速迭代采样过程，从而实现一步或几步生成。然而，我们认为当前快速流训练范式存在两个根本性问题。第一，由随机配对的噪声-数据样本构造的条件速度引入系统轨迹漂移，阻碍模型跟随一致的ODE路径。第二，模型的近似误差随时间步积累，导致长时间间隔内出现严重偏差。为解决这些问题，我们提出了FlowConsist，一种旨在强制快速流中轨迹一致性的训练框架。我们提出了一种原理性替代方法，用模型自身预测的边际速度替代条件速度，使优化与真实轨迹对齐。为进一步解决时间步上的误差积累问题，我们引入了一种轨迹校正策略，在轨迹的每个时间步上对生成样本和真实样本的边际分布进行对齐。我们的方法在ImageNet 256×256上建立了新的状态-of-the-art，仅用1次采样步就达到了FID为1.52的性能。
英文摘要：
Fast flow models accelerate the iterative sampling process by learning to directly predict ODE path integrals, enabling one-step or few-step generation. However, we argue that current fast-flow training paradigms suffer from two fundamental issues. First, conditional velocities constructed from randomly paired noise-data samples introduce systematic trajectory drift, preventing models from following a consistent ODE path. Second, the model's approximation errors accumulate over time steps, leading to severe deviations across long time intervals. To address these issues, we propose FlowConsist, a training framework designed to enforce trajectory consistency in fast flows. We propose a principled alternative that replaces conditional velocities with the marginal velocities predicted by the model itself, aligning optimization with the true trajectory. To further address error accumulation over time steps, we introduce a trajectory rectification strategy that aligns the marginal distributions of generated and real samples at every time step along the trajectory. Our method establishes a new state-of-the-art on ImageNet 256$\times$256, achieving an FID of 1.52 with only 1 sampling step.
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。
