TryOn-Refiner: Conditional Rectified-Flow-Based TryOn Refiner for More Accurate Detail Reconstruction

Abstract

Diffusion techniques has significantly advanced the development of virtual try-on. However, these methods often struggle to preserve intricate details, such as patterns, texts and faces, etc. To tackle this challenge, we introduce a plug-and-play module named as "TryOn-Refiner", which can refine the detailed artifacts for any try-on results in only 1~10 steps.Instead of the previous diffusion-based refine module, TryOn-Refiner employs the conditional rectified-flow-based mechanism for better leveraging prior information from coarse try-on results. Specifically, TryOn-Refiner transforms the traditional refinement framework from a noise-to-image paradigm into a flow mapping framework that directly maps coarse images to refined images, essentially avoiding introducing uncertainty in the refinement process.Moreover, we propose a training data construction pipeline, which can efficiently generate paired training data and includes a data smoothing strategy to overcome the blocking artifact.Extended experimental results demonstrate our TryOn-Refiner consistently improves performance with only a few inference steps for all evaluated existing try-on methods.