OmniStyle: Filtering High Quality Style Transfer Data at Scale
Ye Wang, Ruiqi Liu, Jiang Lin, Fei Liu, Zili Yi, Yilin Wang, Rui Ma
Abstract
Illustration Examples Content (a) Instruction-Guided Style Transfer Make this image into XXX Style Travis Foster iPad white-carve Rococo-style oil painting magic color illustration natural wood style flat design Chinese ancient art sketch Style Content (b) Image-Guided Style Transfer Figure 1. OmniStyle enables high-quality (a) instruction-guided style transfer and (b) reference image-guided style transfer, covering a diverse range of styles, including but not limited to comics, vector art, oil painting, sketch, and Chinese ancient art. Note that in (a), a style image of the style descriptions is provided for illustration, and our method only takes a text instruction and a content image as input. In (b), results are generated in a traditional manner of style transfer, in which the model takes both the content and style images as input.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 0716ac90-0f90-4eb5-b5a0-e460644acf7dCited by top-tier papers11
- FFP-300K: Scaling First-Frame Propagation for Generalizable Video EditingXijie Huang, Chengming Xu, Donghao Luo, Xiaobin Hu et al.CVPR 2026 · 5 citations
- DreamStyle: A Unified Framework for Video StylizationMengtian Li, Jinshu Chen, Songtao Zhao, Wanquan Feng et al.CVPR 2026 · 4 citations
- EmoStyle: Emotion-Driven Image StylizationJingyuan Yang, Zihuan Bai, Hui HuangCVPR 2026 · 2 citations
- Premier: Personalized Preference Modulation with Learnable User Embedding in Text-to-Image GenerationZihao Wang, Yuxiang Wei, Xinpeng Zhou, Tianyu Zhang et al.CVPR 2026 · 1 citation
- Mixture of Style Experts for Diverse Image StylizationShihao Zhu, Ziheng Ouyang, Yijia Kang, Qilong Wang et al.CVPR 2026 · 1 citation
Builds on20
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- Scalable Diffusion Models with TransformersWilliam Peebles, Saining XieICCV 2023 · 5,568 citations
- StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion ModelsZhizhong Wang, Lei Zhao, Wei XingICCV 2023 · 219 citations
- Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain GeneralizationYabin Zhang, Minghan Li, Ruihuang Li, Kui Jia et al.CVPR 2022 · 217 citations
- Domain Enhanced Arbitrary Image Style Transfer via Contrastive LearningYuxin Zhang, Fan Tang, Weiming Dong, Haibin Huang et al.SIGGRAPH 2022 · 211 citations
Related papers
- StyleStudio: Text-Driven Style Transfer with Selective Control of Style ElementsMingkun Lei, Xue Song, Beier Zhu, Hao Wang et al.CVPR 2025
- Inversion-based Style Transfer with Diffusion ModelsYuxin Zhang, Nisha Huang, Fan Tang, Haibin Huang et al.CVPR 2023
- Z*: Zero-shot Style Transfer via Attention ReweightingYingying Deng, Xiangyu He, Fan Tang, Weiming DongCVPR 2024
- Diverse Image Style Transfer via Invertible Cross-Space MappingHaibo Chen, Lei Zhao, Huiming Zhang, Zhizhong Wang et al.ICCV 2021 · 42 citations
- Learning Dynamic Style Kernels for Artistic Style TransferWenju Xu, Chengjiang Long, Yongwei NieCVPR 2023
