FlowAlign: Trajectory-Regularized, Inversion-Free Flow-based Image Editing
This addresses consistency issues in text-driven image editing for users of flow-based models, representing an incremental improvement over prior inversion-free methods.
The paper tackles the problem of unstable editing trajectories and poor source consistency in inversion-free, flow-based image editing methods by proposing FlowAlign, which introduces terminal point regularization to balance semantic alignment with edit prompts and structural consistency with source images. Experiments show FlowAlign outperforms existing methods in both source preservation and editing controllability.
Recent inversion-free, flow-based image editing methods such as FlowEdit leverages a pre-trained noise-to-image flow model such as Stable Diffusion 3, enabling text-driven manipulation by solving an ordinary differential equation (ODE). While the lack of exact latent inversion is a core advantage of these methods, it often results in unstable editing trajectories and poor source consistency. To address this limitation, we propose {\em FlowAlign}, a novel inversion-free flow-based framework for consistent image editing with optimal control-based trajectory control. Specifically, FlowAlign introduces source similarity at the terminal point as a regularization term to promote smoother and more consistent trajectories during the editing process. Notably, our terminal point regularization is shown to explicitly balance semantic alignment with the edit prompt and structural consistency with the source image along the trajectory. Furthermore, FlowAlign naturally supports reverse editing by simply reversing the ODE trajectory, highliting the reversible and consistent nature of the transformation. Extensive experiments demonstrate that FlowAlign outperforms existing methods in both source preservation and editing controllability.