让快速生成模型轨迹更真实，仅一步生成就达顶级质量
FlowConsist: Make Your Flow Consistent with Real Trajectory
- 用模型自预测的边际速度替代随机配对的条件速度，确保路径一致
- 在ImageNet 256×256上仅用1步采样即达到FID 1.52，创纪录
- 适合追求高效高质图像生成的研究者和应用开发者
快速流模型通过学习直接预测常微分方程（ODE）路径积分，实现一步或少量步骤生成。然而，当前快速流训练范式存在两个根本问题：其一，由随机配对噪声-数据样本构造的条件速度引入系统性轨迹漂移，使模型无法遵循一致的ODE路径；其二，模型近似误差随时间步累积，导致长时间区间严重偏离。为此，我们提出FlowConsist训练框架，旨在强制快速流中的轨迹一致性。该方法提出一种原则性替代方案，将条件速度替换为模型自身预测的边际速度，使优化目标与真实轨迹对齐。为进一步缓解时间步误差累积问题，引入轨迹校正策略，在轨迹每个时间步对齐生成样本与真实样本的边际分布。该方法在ImageNet 256×256上建立新基准，仅需1次采样步即达到FID 1.52。
原文摘要 · Abstract (English)
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.
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。