Variational Flow Models: Flowing in Your Style

Code

• github.com/clarken92/vfm
  OfficialIn paperpytorch★ 2

Abstract

We propose a systematic training-free method to transform the probability flow of a "linear" stochastic process characterized by the equation X_t=a_tX_0+ _tX_1 into a straight constant-speed (SC) flow, reminiscent of Rectified Flow. This transformation facilitates fast sampling along the original probability flow via the Euler method without training a new model of the SC flow. The flexibility of our approach allows us to extend our transformation to inter-convert two posterior flows of two distinct linear stochastic processes. Moreover, we can easily integrate high-order numerical solvers into the transformed SC flow, further enhancing the sampling accuracy and efficiency. Rigorous theoretical analysis and extensive experimental results substantiate the advantages of our framework. Our code is available at this [https://github.com/clarken92/VFM||link].

Tasks

Reproductions