StreamFlow: Theory, Algorithm, and Implementation for High-Efficiency Rectified Flow Generation
This work addresses a bottleneck in generative model efficiency for researchers and practitioners, offering a significant performance improvement over incremental approaches.
The paper tackles the inefficiency of existing acceleration methods for Rectified Flow models by proposing a comprehensive acceleration pipeline, achieving up to 611% speedup in 512*512 image generation compared to 18% from current methods.
New technologies such as Rectified Flow and Flow Matching have significantly improved the performance of generative models in the past two years, especially in terms of control accuracy, generation quality, and generation efficiency. However, due to some differences in its theory, design, and existing diffusion models, the existing acceleration methods cannot be directly applied to the Rectified Flow model. In this article, we have comprehensively implemented an overall acceleration pipeline from the aspects of theory, design, and reasoning strategies. This pipeline uses new methods such as batch processing with a new velocity field, vectorization of heterogeneous time-step batch processing, and dynamic TensorRT compilation for the new methods to comprehensively accelerate related models based on flow models. Currently, the existing public methods usually achieve an acceleration of 18%, while experiments have proved that our new method can accelerate the 512*512 image generation speed to up to 611%, which is far beyond the current non-generalized acceleration methods.