OmniStyle2: Scalable and High Quality Artistic Style Transfer Data Generation via Destylization
This addresses the data scarcity problem in artistic style transfer for researchers and practitioners, offering a scalable supervision paradigm.
The paper tackles the lack of ground-truth data in artistic style transfer by introducing destylization to generate a large-scale dataset, DST-100K, and trains a model, OmniStyle2, that surpasses state-of-the-art methods in benchmarks.
OmniStyle2 introduces a novel approach to artistic style transfer by reframing it as a data problem. Our key insight is destylization, reversing style transfer by removing stylistic elements from artworks to recover natural, style-free counterparts. This yields DST-100K, a large-scale dataset that provides authentic supervision signals by aligning real artistic styles with their underlying content. To build DST-100K, we develop (1) DST, a text-guided destylization model that reconstructs stylefree content, and (2) DST-Filter, a multi-stage evaluation model that employs Chain-of-Thought reasoning to automatically discard low-quality pairs while ensuring content fidelity and style accuracy. Leveraging DST-100K, we train OmniStyle2, a simple feed-forward model based on FLUX.1-dev. Despite its simplicity, OmniStyle2 consistently surpasses state-of-the-art methods across both qualitative and quantitative benchmarks. Our results demonstrate that scalable data generation via destylization provides a reliable supervision paradigm, overcoming the fundamental challenge posed by the lack of ground-truth data in artistic style transfer.