MeanFlowNFT让平均速度生成器也能用上强化学习，4步生成效果比50步的RL模型还好，值得试。
MeanFlowNFT是一种新方法，将前向过程强化学习（RL）框架DiffusionNFT扩展到平均速度生成器（MeanFlow）。它利用MeanFlow身份构建瞬时速度预测器，在保持平均速度采样（实现快速少步生成）的同时进行奖励优化。实验在图像和视频生成上证明，MeanFlowNFT在SD3.5-M的8项指标中提升6项，优于先前最先进的少步RL生成器。在Wan 2.1视频模型上，4步MeanFlowNFT达到VBench 84.33分，超过50步LongCat-Video RL的82.57分。
MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators
MeanFlow generators achieve fast few-step sampling by predicting average velocities over time intervals, making them attractive for efficient generation. Reinforcement learning (RL) has become a powerful way to align diffusion and flow models with human preferences and task-specific objectives. In particular, DiffusionNFT offers an efficient forward-process RL framework that does not require reverse-process trajectories or likelihood estimation. However, applying such RL methods to MeanFlow remains underexplored. DiffusionNFT optimizes instantaneous velocities, whereas MeanFlow samples with average velocities. To bridge this gap, we introduce MeanFlowNFT. Inspired by the MeanFlow identity, which bridges average and instantaneous velocities, we construct an induced instantaneous-velocity predictor. We apply the DiffusionNFT objective to this predictor, making reward optimization well-defined for MeanFlow. Sampling remains based on the average velocity, preserving MeanFlow's fast few-step generation. We further prove that MeanFlowNFT inherits DiffusionNFT's strict policy-improvement guarantee. Experiments on image and video generation show that MeanFlowNFT consistently improves baselines. Moreover, it outperforms prior state-of-the-art RL-tuned few-step generators on most metrics ($6$ of $8$ on SD3.5-M), and can even surpass multi-step RL-tuned diffusion while using only a few sampling steps. For instance, on Wan 2.1, $4$-step MeanFlowNFT reaches a VBench score of $84.33$, surpassing $50$-step LongCat-Video RL ($82.57$).