Flow Matching for Generative Modeling
This work addresses the problem of efficient and stable generative modeling for researchers and practitioners, offering a novel paradigm that improves upon existing diffusion models.
The authors tackled the challenge of scaling Continuous Normalizing Flows (CNFs) for generative modeling by introducing Flow Matching, a simulation-free training method that regresses vector fields of conditional probability paths, resulting in better performance on ImageNet in terms of likelihood and sample quality compared to diffusion-based methods.
We introduce a new paradigm for generative modeling built on Continuous Normalizing Flows (CNFs), allowing us to train CNFs at unprecedented scale. Specifically, we present the notion of Flow Matching (FM), a simulation-free approach for training CNFs based on regressing vector fields of fixed conditional probability paths. Flow Matching is compatible with a general family of Gaussian probability paths for transforming between noise and data samples -- which subsumes existing diffusion paths as specific instances. Interestingly, we find that employing FM with diffusion paths results in a more robust and stable alternative for training diffusion models. Furthermore, Flow Matching opens the door to training CNFs with other, non-diffusion probability paths. An instance of particular interest is using Optimal Transport (OT) displacement interpolation to define the conditional probability paths. These paths are more efficient than diffusion paths, provide faster training and sampling, and result in better generalization. Training CNFs using Flow Matching on ImageNet leads to consistently better performance than alternative diffusion-based methods in terms of both likelihood and sample quality, and allows fast and reliable sample generation using off-the-shelf numerical ODE solvers.