English

MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping

Computer Vision and Pattern Recognition 2026-04-21 v2

Abstract

In this paper, we introduce MegaStyle, a novel and scalable data curation pipeline that constructs an intra-style consistent, inter-style diverse and high-quality style dataset. We achieve this by leveraging the consistent text-to-image style mapping capability of current large generative models, which can generate images in the same style from a given style description. Building on this foundation, we curate a diverse and balanced prompt gallery with 170K style prompts and 400K content prompts, and generate a large-scale style dataset MegaStyle-1.4M via content-style prompt combinations. With MegaStyle-1.4M, we propose style-supervised contrastive learning to fine-tune a style encoder MegaStyle-Encoder for extracting expressive, style-specific representations, and we also train a FLUX-based style transfer model MegaStyle-FLUX. Extensive experiments demonstrate the importance of maintaining intra-style consistency, inter-style diversity and high-quality for style dataset, as well as the effectiveness of the proposed MegaStyle-1.4M. Moreover, when trained on MegaStyle-1.4M, MegaStyle-Encoder and MegaStyle-FLUX provide reliable style similarity measurement and generalizable style transfer, making a significant contribution to the style transfer community. More results are available at our project website https://jeoyal.github.io/MegaStyle/.

Keywords

Cite

@article{arxiv.2604.08364,
  title  = {MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping},
  author = {Junyao Gao and Sibo Liu and Jiaxing Li and Yanan Sun and Yuanpeng Tu and Fei Shen and Weidong Zhang and Cairong Zhao and Jun Zhang},
  journal= {arXiv preprint arXiv:2604.08364},
  year   = {2026}
}

Comments

project website https://jeoyal.github.io/MegaStyle/

R2 v1 2026-07-01T12:01:23.223Z