Bellman Optimal Stepsize Straightening of Flow-Matching Models
This addresses computational challenges for low-resource scenarios in image synthesis using flow-matching models, representing an incremental improvement.
The paper tackles the computational inefficiency of flow-matching generative models during fine-tuning and sampling by introducing Bellman Optimal Stepsize Straightening (BOSS), which optimizes step sizes and refines the velocity network to straighten generation paths. Results show BOSS achieves substantial efficiency gains while maintaining competitive sample quality, effectively bridging low-resource constraints with model demands.
Flow matching is a powerful framework for generating high-quality samples in various applications, especially image synthesis. However, the intensive computational demands of these models, especially during the finetuning process and sampling processes, pose significant challenges for low-resource scenarios. This paper introduces Bellman Optimal Stepsize Straightening (BOSS) technique for distilling flow-matching generative models: it aims specifically for a few-step efficient image sampling while adhering to a computational budget constraint. First, this technique involves a dynamic programming algorithm that optimizes the stepsizes of the pretrained network. Then, it refines the velocity network to match the optimal step sizes, aiming to straighten the generation paths. Extensive experimental evaluations across image generation tasks demonstrate the efficacy of BOSS in terms of both resource utilization and image quality. Our results reveal that BOSS achieves substantial gains in efficiency while maintaining competitive sample quality, effectively bridging the gap between low-resource constraints and the demanding requirements of flow-matching generative models. Our paper also fortifies the responsible development of artificial intelligence, offering a more sustainable generative model that reduces computational costs and environmental footprints. Our code can be found at https://github.com/nguyenngocbaocmt02/BOSS.