In generative models, the challenge lies in sampling and forming images from an original distribution, which can be reframed as a problem of transforming one distribution into another. To address this, some generative models, including normalizing flow, score matching models, and the recent flow matching methods are introduced, involving a mapping between a fixed distribution (Gaussian distribution) and a target distribution. The Schrödinger bridge (SB) problem considers the most likely path between an initial and target distribution under a given reference process. In this project, we plan to develop a new approach to tackle the Schrödinger Bridge problem within the context of flow matching. This envisioned approach involves incorporating concepts from fluid dynamics into the Schrödinger Bridge framework, aiming to establish an optimal pathway for transporting data from the initial distribution to the desired target distribution. This integration has the potential to enhance the model's interpretive clarity, improve the model performance and simultaneously streamline the computational complexity associated with its implementation.