{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:03:50Z","timestamp":1765008230843,"version":"3.46.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T00:00:00Z","timestamp":1763769600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T00:00:00Z","timestamp":1763769600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Pattern Anal Applic"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s10044-025-01577-9","type":"journal-article","created":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T00:59:07Z","timestamp":1763773147000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Stylized image generation based on multi-attribute decomposition"],"prefix":"10.1007","volume":"28","author":[{"given":"Shuai","family":"Yang","sequence":"first","affiliation":[]},{"given":"Xinyue","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Jing","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Kai","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yongzhen","family":"Ke","sequence":"additional","affiliation":[]},{"given":"Xingjian","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,22]]},"reference":[{"key":"1577_CR1","doi-asserted-by":"crossref","unstructured":"Rombach R et al (2022) High-resolution image synthesis with latent diffusion models. in Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"1577_CR2","doi-asserted-by":"crossref","unstructured":"Zhang Y et al (2023) Inversion-based style transfer with diffusion models. in Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR52729.2023.00978"},{"key":"1577_CR3","unstructured":"Gal R et al An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion. The Eleventh International Conference on Learning Representations(ICLR).2023"},{"key":"1577_CR4","unstructured":"Sohn K et al (2023) NeurIPS., StyleDrop: Text-to-Image Generation in Any Style. Neural Information Processing Systems 2023"},{"key":"1577_CR5","doi-asserted-by":"crossref","unstructured":"Gatys LA et al (2017) Controlling Perceptual Factors in Neural Style Transfer. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016: pp. 3730\u20133738","DOI":"10.1109\/CVPR.2017.397"},{"key":"1577_CR6","doi-asserted-by":"crossref","unstructured":"Chen J et al (2023) ControlStyle: Text-Driven Stylized Image Generation Using Diffusion Priors. Proceedings of the 31st ACM International Conference on Multimedia","DOI":"10.1145\/3581783.3612524"},{"key":"1577_CR7","unstructured":"Wang Z et al (2023) Styleadapter: A single-pass lora-free model for stylized image generation. arXiv preprint arXiv:2309.01770"},{"key":"1577_CR8","first-page":"4450","volume":"2022","author":"Z Pan","year":"2023","unstructured":"Pan Z, Zhou X, Tian H (2023) Arbitrary style guidance for enhanced Diffusion-Based Text-to-Image generation. IEEE\/CVF Winter Conf Appl Comput Vis (WACV) 2022:4450\u20134460","journal-title":"IEEE\/CVF Winter Conf Appl Comput Vis (WACV)"},{"key":"1577_CR9","doi-asserted-by":"crossref","unstructured":"Lei M et al (2025) StyleStudio: Text-Driven Style Transfer with Selective Control of Style Elements. Proceedings of the Computer Vision and Pattern Recognition Conference(CVPR). : 23443\u201323452","DOI":"10.1109\/CVPR52734.2025.02183"},{"key":"1577_CR10","unstructured":"Jeong J et al (2024) Visual style prompting with swapping Self-Attention. ArXiv. abs\/2402.12974"},{"key":"1577_CR11","unstructured":"Kong S et al (2016) Photo aesthetics ranking network with attributes and content adaptation. in Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I 14. Springer"},{"key":"1577_CR12","unstructured":"Zhang R et al (2021) Tip-Adapter: Training-free CLIP-Adapter for better Vision-Language modeling. ArXiv. abs\/2111.03930"},{"key":"1577_CR13","unstructured":"Mansimov E et al Generating Images from Captions with Attention. International Conference on Learning Representations(ICLR).2016"},{"key":"1577_CR14","unstructured":"Reed S, Akata Z, Yan X et al (2016) Generative adversarial text to image synthesis.International conference on machine learning(ICML), : 1060\u20131069"},{"key":"1577_CR15","unstructured":"Ding M et al (2021) CogView: Mastering Text-to-Image Generation via Transformers. in Neural Information Processing Systems"},{"key":"1577_CR16","unstructured":"Ramesh A et al (2021) Zero-shot text-to-image generation. International conference on machine learning(ICML), : 8821\u20138831"},{"key":"1577_CR17","doi-asserted-by":"crossref","unstructured":"Wu C et al (2022) N\u00fcwa: Visual synthesis pre-training for neural visual world creation. European conference on computer vision(ECCV), : 720\u2013736","DOI":"10.1007\/978-3-031-19787-1_41"},{"key":"1577_CR18","unstructured":"Yu J et al (2022) Scaling Autoregressive Models for Content-Rich Text-to-Image Generation. Trans. Mach. Learn. Res., 2022"},{"key":"1577_CR19","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho J, Jain A, Abbeel P (2020) Denoising diffusion probabilistic models. Adv Neural Inform Process systems(NIPS) 33:6840\u20136851","journal-title":"Adv Neural Inform Process systems(NIPS)"},{"key":"1577_CR20","unstructured":"Sohl-Dickstein JN et al (2015) Deep unsupervised learning using nonequilibrium thermodynamics. International conference on machine learning(ICML), : 2256\u20132265"},{"key":"1577_CR21","unstructured":"Song J, Meng C, Ermon S (2021) Denoising Diffusion Implicit Models. International Conference on Learning Representations(ICLR)"},{"key":"1577_CR22","doi-asserted-by":"crossref","unstructured":"Avrahami O, Lischinski D, Fried O (2021) Blended Diffusion for Text-driven Editing of Natural Images. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), : pp. 18187\u201318197","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"1577_CR23","doi-asserted-by":"crossref","unstructured":"Saharia C et al (2021) Palette: Image-to-Image Diffusion Models. ACM SIGGRAPH 2022 Conference Proceedings","DOI":"10.1145\/3528233.3530757"},{"key":"1577_CR24","first-page":"4713","volume":"45","author":"C Saharia","year":"2021","unstructured":"Saharia C et al (2021) Image Super-Resolution via iterative refinement. IEEE Trans Pattern Anal Mach Intell 45:4713\u20134726","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1577_CR25","unstructured":"Wang C et al (2021) S3RP: Self-Supervised Super-Resolution and prediction for Advection-Diffusion process. ArXiv. abs\/2111.04639"},{"key":"1577_CR26","unstructured":"Meng C et al (2021) SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations. in International Conference on Learning Representations"},{"key":"1577_CR27","doi-asserted-by":"crossref","unstructured":"Lugmayr A et al (2022) RePaint: Inpainting using Denoising Diffusion Probabilistic Models. IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022: pp. 11451\u201311461","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"1577_CR28","doi-asserted-by":"crossref","unstructured":"Romero A et al (2022) NTIRE 2022 Image Inpainting Challenge: Report. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), : pp. 1149\u20131181","DOI":"10.1109\/CVPRW56347.2022.00124"},{"key":"1577_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3618342","volume":"42","author":"Y-x Zhang","year":"2023","unstructured":"Zhang Y-x et al (2023) ProSpect: prompt spectrum for Attribute-Aware personalization of diffusion models. ACM Trans Graphics (TOG) 42:1\u201314","journal-title":"ACM Trans Graphics (TOG)"},{"key":"1577_CR30","doi-asserted-by":"crossref","unstructured":"Zhang L, Rao A, Agrawala M (2023) Adding Conditional Control to Text-to-Image Diffusion Models [J]. 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), : 3813-24","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"1577_CR31","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556"},{"key":"1577_CR32","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. in Proceedings of the IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2018.00745"},{"key":"1577_CR33","unstructured":"Houlsby N et al (2019) Parameter-efficient transfer learning for NLP. in International conference on machine learning. PMLR"},{"key":"1577_CR34","unstructured":"Li J et al (2023) Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. in International conference on machine learning. PMLR"},{"key":"1577_CR35","doi-asserted-by":"crossref","unstructured":"Zeng Y et al (2024) What Matters in Training a GPT4-Style Language Model with Multimodal Inputs? in Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)","DOI":"10.18653\/v1\/2024.naacl-long.440"},{"key":"1577_CR36","unstructured":"Han Z et al (2024) Stylebooth: Image style editing with multimodal instruction. arXiv preprint arXiv:2404.12154"},{"key":"1577_CR37","doi-asserted-by":"crossref","unstructured":"Karayev S et al (2014) Recognizing Image Style. Proceedings of the British Machine Vision Conference (BMVC)","DOI":"10.5244\/C.28.122"},{"key":"1577_CR38","unstructured":"Radford A et al (2021) Learning Transferable Visual Models From Natural Language Supervision. in International Conference on Machine Learning"},{"key":"1577_CR39","unstructured":"Heusel M et al (2017) Gans trained by a two time-scale update rule converge to a local Nash equilibrium. Adv Neural Inf Process Syst, 30"},{"key":"1577_CR40","unstructured":"Xing P, Wang H, Sun Y et al Csgo: Content-style composition in text-to-image generation. The Eleventh International Conference on Learning Representations(ICLR).2025"},{"key":"1577_CR41","doi-asserted-by":"crossref","unstructured":"Rombach R et al (2021) High-Resolution Image Synthesis with Latent Diffusion Models. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), : pp. 10674\u201310685","DOI":"10.1109\/CVPR52688.2022.01042"}],"container-title":["Pattern Analysis and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-025-01577-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10044-025-01577-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-025-01577-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T07:59:43Z","timestamp":1765007983000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10044-025-01577-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,22]]},"references-count":41,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["1577"],"URL":"https:\/\/doi.org\/10.1007\/s10044-025-01577-9","relation":{},"ISSN":["1433-7541","1433-755X"],"issn-type":[{"type":"print","value":"1433-7541"},{"type":"electronic","value":"1433-755X"}],"subject":[],"published":{"date-parts":[[2025,11,22]]},"assertion":[{"value":"12 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"202"}}