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

Junyao Gao; Sibo Liu; Jiaxing Li; Yanan Sun; Yuanpeng Tu; Fei Shen; Weidong Zhang; Cairong Zhao

cs.CVApr 9, 2026

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

Authors: Junyao Gao, Sibo Liu, Jiaxing Li, Yanan Sun, Yuanpeng Tu, Fei Shen, Weidong Zhang, Cairong Zhao,

Organizations: Tongji Univeristy · Tencent · Nanyang Technological University · Hong Kong University of Science and Technology ·

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/.

Figures & tables

Figure 2: Illustrations of (a) artworks by Vincent van Gogh ; (b) style images in OmniStyle-150K generated by SOTA style transfer methods [ 5 , 10 , 55 , 2 , 17 , 60 ] from a reference style image; and (c) images generated by Qwen-Image using the same style description.

Figure 3: Overview of our data curation pipeline. We first collect style and content images from open-source datasets. Next, we apply carefully designed instructions to generate style and content prompts with Qwen3-VL, together with balance sampling. Finally, we use Qwen-Image to generate style images using content-style prompt combinations. Please note that we use simplified content and style prompts for illustrative purposes only .

Figure 4: Visualizations of style reproductions. We first use Qwen3-VL to caption a style prompt from the reference style image, and then generate style reproductions on content–style combinations using Qwen-Image.

Figure 5: Distribution analysis of overall artistic styles in the style prompts. We present the proportions of the top 30 overall artistic styles.

Datasets	Intra-style Consistency	Overall Style	Fine-grained Style	Style Image Number
WikiArt	✗	27	—	80K
JourneyDB	✗	—	300K	4.4M
Style30K	✗	—	1K	30K
IMAGStyle	✓	14	15K	210K
OmniStyle-150K	✓	—	1K	150K
MegaStyle-1.4M	✓	8,355	170K	1.4M

Table 1: Comparison of style datasets. ✓/✗ indicate whether intra-style consistency is provided and — indicates that the statistic is unavailable.

Figure 6: Visualizations of style pairs in MegaStyle-1.4M, where each row shows the same style with different contents.

Figure 7: The architecture of MegaStyle-FLUX.

Figure 8: Visual comparison of top-1 matched style retrieval results between MegaStyle-Encoder, SigLIP, and CSD. The red and green borders indicate incorrect and correct matches, respectively.

		mAP@k $\uparrow$		Recall@k $\uparrow$
Methods	Backbone	1	10	1	10
CLIP	ViT-L	9.29	6.46	9.29	31.56
CSD	ViT-L	45.60	37.78	45.60	79.18
MegaStyle-Encoder	ViT-L	87.26	85.98	87.26	97.61
SigLIP	SoViT	10.43	7.83	10.43	36.32
MegaStyle-Encoder	SoViT	88.46	86.77	88.46	97.66

Table 2: Comparison of MegaStyle-Encoder with other style encoders on the StyleRetrieval benchmark. The best results are highlighted in bold .

Figure 9: Qualitative comparison between MegaStyle-FLUX and SOTA style transfer methods. MegaStyle-FLUX achieves the superior performance compared to baseline methods.

Metrics	StyleCrafter	DEADiff	Attn-Distill	InstantStyle	CSGO	StyleAligned	StyleShot	MegaStyle-FLUX
Style $\uparrow$	48.59	51.34	85.59	71.41	55.02	59.80	63.42	76.16
Text $\uparrow$	21.39	23.13	20.29	20.77	23.05	21.31	21.79	23.20
Human Style $\uparrow$	3.41	3.05	13.97	18.19	7.34	7.46	15.21	31.37
Human Text $\uparrow$	8.87	11.13	6.31	10.98	16.18	4.12	13.69	28.72

Table 3: Quantitative comparison of style and text alignment with SOTA style transfer methods. Style and Text denote the cosine distance in the feature spaces of MegaStyle-Encoder and CLIP, respectively. The prefix Human indicates human preference scores. Best result is marked in bold , and the second-best result is highlighted in underline .

Figure 10: Visual results of MegaStyle-FLUX trained on different style datasets.

Figure 11: Visual results of MegaStyle-FLUX and fine-tuned StyleShot.

Metrics	JourneyDB	OmniStyle-150K	MegaStyle-1.4M
Style $\uparrow$	34.56	51.49	76.16
Text $\uparrow$	21.12	23.02	23.20

Table 4: Quantitative comparison of style datasets. Best is marked in bold .

	StyleBench				FLUX-Retrieval				OmniStyle-150K
	mAP@k $\uparrow$		Recall@k $\uparrow$		mAP@k $\uparrow$		Recall@k $\uparrow$		mAP@k $\uparrow$		Recall@k $\uparrow$
Methods	1	10	1	10	1	10	1	10	1	10	1	10
CLIP	40.00	30.85	40.00	82.50	2.42	1.55	2.42	9.68	1.68	1.35	1.68	10.39
CSD	70.00	51.65	70.00	97.50	14.16	9.91	14.16	40.08	60.86	48.24	60.86	89.71
MegaStyle-Encoder	85.00	54.15	85.00	100.00	22.70	18.38	22.70	51.87	78.89	60.18	78.89	94.07

Table 5: Comparison of MegaStyle-Encoder with other style encoders on the StyleBench, FLUX-Retrieval and OmniStyle-150K. The best results are highlighted in bold .

Metrics	StyleShot-FLUX	StyleShot-FLUX-Mega	MegaStyle-FLUX
Style $\uparrow$	57.06	67.73	76.16
Text $\uparrow$	21.86	23.27	23.20

Table 6: Quantitative comparison between MegaStyle-FLUX and fine-tuned StyleShot. Best is marked in bold .

Figure 12: Visualizations of retrieval benchmark WikiArt and our StyleRetrieval, where each row shows the same style during retrieval.

Figure 13: Visual results between MegaStyle-FLUX and Qwen-Image-Edit.

Metrics	Qwen-Image-Edit	MegaStyle-FLUX
Style $\uparrow$	43.03	76.16
Text $\uparrow$	24.24	23.20

Table 7: Quantitative comparison between MegaStyle-FLUX and Qwen-Image-Edit. Best is marked in bold .

Figure 14: Visualizations of association bias in Qwen-Image.

Figure 15: Additional visualizations of style pairs in MegaStyle-1.4M, where each row shows the same style with different contents.

Figure 16: Additional visualizations of style pairs in MegaStyle-1.4M, where each row shows the same style with different contents.

Figure 17: Additional visualizations of style pairs in MegaStyle-1.4M, where each row shows the same style with different contents.

Figure 18: Additionaly qualitative comparison between MegaStyle-FLUX and SOTA style transfer methods.

Figure 19: Additionaly qualitative comparison between MegaStyle-FLUX and SOTA style transfer methods.

Figure 20: Stylized results of MegaStyle-FLUX.

Figure 21: Stylized results of MegaStyle-FLUX.

Figure 22: Stylized results of MegaStyle-FLUX.

Figure 23: Stylized results of MegaStyle-FLUX.

Image Style Transfer

Image style transfer changes an image’s visual appearance to match an artistic, photographic, or other reference while preserving its content.

See all 61 papers

MegaStyle++: Scaling Image Style Space through Hierarchical Style Definition
Sep 1, 2026Junyao Gao, Sibo Liu, Jiaxing Li +4Image Style Transfer
Tongji University · Tencent · Nanyang Technological University +1
Style-CCL: Content-Preserving Style Transfer via Curriculum Continual Learning
Jun 4, 2026Shiwen Zhang, Haoyuan Wang, Xianghao Zang +3Diffusion Transformer Continual Learning
Institute of Artificial Intelligence (TeleAI), China Telecom.
Towards In-Context Tone Style Transfer with A Large-Scale Triplet Dataset
Apr 17, 2026Yuhai Deng, Huimin She, Wei Shen +4Image Style Transfer Diffusion-Based Image Editing
VCIP, School of Computer Science, Nankai University · OPPO AI Center, OPPO Inc. · Nankai International Advanced Research Institute (Shenzhen Futian)

Sep 1, 2026J/K move · Enter open · S save

MegaStyle++: Scaling Image Style Space through Hierarchical Style Definition

Junyao Gao, Sibo Liu, Jiaxing Li, Yanan Sun+3

Tongji University · Tencent · Nanyang Technological University+1

Image Style Transfer

Open paper AskPDF arXiv

Image style is a highly abstract, human-constructed concept shaped by a range of visual factors and intrinsically entangled with content, yet a unified and explicit definition of image style remains lacking. In this work, we first discuss the fundamental question of what is style and then propose a hierarchical style definition that describes image style from an overall style identity to fine-grained visual attributes, providing a more structured, transferable, and interpretable style representation. Based on this definition, we refine the style annotation pipeline of MegaStyle and construct MegaStyle++-8M, a large-scale style dataset containing 150K overall style identities, 1M fine-grained style prompts, and 8M stylized images. Extensive analyses demonstrate that our hierarchical definition substantially expands the style space in both diversity and semantic breadth, while precisely capturing intrinsic visual style of reference images. The dataset and code will be updated at https://github.com/Tencent/MegaStyle, we hope MegaStyle++ provides a scalable foundation for studying and modeling diverse image styles.

Abstract

Image Style Transfer

Explore similar work

MegaStyle++: Scaling Image Style Space through Hierarchical Style Definition

Style-CCL: Content-Preserving Style Transfer via Curriculum Continual Learning

Towards In-Context Tone Style Transfer with A Large-Scale Triplet Dataset