MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE
This work addresses a specific bottleneck in training efficiency for flow-based models in image generation, offering incremental improvements over existing methods like FlowGRPO and DanceGRPO.
The paper tackles the inefficiency of flow-based GRPO methods in human preference alignment for image generation by proposing MixGRPO, which uses mixed ODE-SDE sampling with a sliding window to reduce optimization overhead, resulting in up to 71% lower training time while maintaining or improving performance.
Although GRPO substantially enhances flow matching models in human preference alignment of image generation, methods such as FlowGRPO still exhibit inefficiency due to the necessity of sampling and optimizing over all denoising steps specified by the Markov Decision Process (MDP). In this paper, we propose $\textbf{MixGRPO}$, a novel framework that leverages the flexibility of mixed sampling strategies through the integration of stochastic differential equations (SDE) and ordinary differential equations (ODE). This streamlines the optimization process within the MDP to improve efficiency and boost performance. Specifically, MixGRPO introduces a sliding window mechanism, using SDE sampling and GRPO-guided optimization only within the window, while applying ODE sampling outside. This design confines sampling randomness to the time-steps within the window, thereby reducing the optimization overhead, and allowing for more focused gradient updates to accelerate convergence. Additionally, as time-steps beyond the sliding window are not involved in optimization, higher-order solvers are supported for sampling. So we present a faster variant, termed $\textbf{MixGRPO-Flash}$, which further improves training efficiency while achieving comparable performance. MixGRPO exhibits substantial gains across multiple dimensions of human preference alignment, outperforming DanceGRPO in both effectiveness and efficiency, with nearly 50% lower training time. Notably, MixGRPO-Flash further reduces training time by 71%. Codes and models are available at $\href{https://github.com/Tencent-Hunyuan/MixGRPO}{MixGRPO}$.