{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,21]],"date-time":"2026-06-21T08:48:47Z","timestamp":1782031727151,"version":"3.54.5"},"reference-count":39,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100017607","name":"Shenzhen Basic Research Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100017607","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012156","name":"Shenzen Municipal Technical Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012156","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62576364"],"award-info":[{"award-number":["62576364"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.patcog.2026.113093","type":"journal-article","created":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T00:10:39Z","timestamp":1769040639000},"page":"113093","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":4,"special_numbering":"C","title":["FreeStyle: Free lunch for text-guided style transfer using diffusion models"],"prefix":"10.1016","volume":"175","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1038-8238","authenticated-orcid":false,"given":"Feihong","family":"He","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9520-0141","authenticated-orcid":false,"given":"Gang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5341-0158","authenticated-orcid":false,"given":"Fuhui","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6732-1608","authenticated-orcid":false,"given":"Mengyuan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7735-6676","authenticated-orcid":false,"given":"Lingyu","family":"Si","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3972-1575","authenticated-orcid":false,"given":"Xiaoyan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5659-3464","authenticated-orcid":false,"given":"Li","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113093_bib0001","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10684","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2022"},{"key":"10.1016\/j.patcog.2026.113093_bib0002","unstructured":"D. Podell, Z. English, K. Lacey, A. Blattmann, T. Dockhorn, J. M\u00fcller, J. Penna, R. Rombach, Sdxl: improving latent diffusion models for high-resolution image synthesis, (2023). arXiv preprint arXiv: 2307.01952."},{"key":"10.1016\/j.patcog.2026.113093_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.110034","article-title":"Generative adversarial networks via a composite annealing of noise and diffusion","volume":"146","author":"Nakamura","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113093_bib0004","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"7677","article-title":"Stylediffusion: controllable disentangled style transfer via diffusion models","author":"Wang","year":"2023"},{"key":"10.1016\/j.patcog.2026.113093_bib0005","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10146","article-title":"Inversion-based style transfer with diffusion models","author":"Zhang","year":"2023"},{"key":"10.1016\/j.patcog.2026.113093_bib0006","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6038","article-title":"Null-text inversion for editing real images using guided diffusion models","author":"Mokady","year":"2023"},{"key":"10.1016\/j.patcog.2026.113093_bib0007","unstructured":"C. Schuhmann, R. Vencu, R. Beaumont, R. Kaczmarczyk, C. Mullis, A. Katta, T. Coombes, J. Jitsev, A. Komatsuzaki, Laion-400m: open dataset of clip-filtered 400 million image-text pairs, (2021). arXiv preprint arXiv: 2111.02114."},{"key":"10.1016\/j.patcog.2026.113093_bib0008","series-title":"ACM SIGGRAPH 2024 Conference Papers","first-page":"1","article-title":"Cross-image attention for zero-shot appearance transfer","author":"Alaluf","year":"2024"},{"key":"10.1016\/j.patcog.2026.113093_bib0009","series-title":"Dictionary Learning for Image Style Transfer","author":"Seo","year":"2020"},{"key":"10.1016\/j.patcog.2026.113093_bib0010","series-title":"Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany, October 5\u20139, 2015, Proceedings, Part III 18","first-page":"234","article-title":"U-net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"10.1016\/j.patcog.2026.113093_bib0011","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"18062","article-title":"Clipstyler: image style transfer with a single text condition","author":"Kwon","year":"2022"},{"key":"10.1016\/j.patcog.2026.113093_bib0012","series-title":"ACM SIGGRAPH 2022 Conference Proceedings","first-page":"1","article-title":"Domain enhanced arbitrary image style transfer via contrastive learning","author":"Zhang","year":"2022"},{"key":"10.1016\/j.patcog.2026.113093_bib0013","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11326","article-title":"Stytr2: image style transfer with transformers","author":"Deng","year":"2022"},{"key":"10.1016\/j.patcog.2026.113093_bib0014","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"1900","article-title":"Uncovering the disentanglement capability in text-to-image diffusion models","author":"Wu","year":"2023"},{"key":"10.1016\/j.patcog.2026.113093_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109988","article-title":"Controllable style transfer via test-time training of implicit neural representation","volume":"146","author":"Kim","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113093_bib0016","first-page":"2672","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113093_bib0017","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"2223","article-title":"Unpaired image-to-image translation using cycle-consistent adversarial networks","author":"Zhu","year":"2017"},{"key":"10.1016\/j.patcog.2026.113093_bib0018","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113093_bib0019","series-title":"International Conference on Machine Learning","first-page":"1060","article-title":"Generative adversarial text to image synthesis","author":"Reed","year":"2016"},{"key":"10.1016\/j.patcog.2026.113093_bib0020","unstructured":"Z.C. Lipton, J. Berkowitz, C. Elkan, A critical review of recurrent neural networks for sequence learning, (2015). arXiv preprint arXiv: 1506.00019."},{"key":"10.1016\/j.patcog.2026.113093_bib0021","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111022","article-title":"FICE: text-conditioned fashion-image editing with guided GAN inversion","volume":"158","author":"Pernu\u0161","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113093_bib0022","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.patcog.2026.113093_bib0023","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110438","article-title":"Adaptive multi-text union for stable text-to-image synthesis learning","volume":"152","author":"Zhou","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113093_bib0024","doi-asserted-by":"crossref","first-page":"36479","DOI":"10.52202\/068431-2643","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113093_bib0025","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109458","article-title":"Where you edit is what you get: text-guided image editing with region-based attention","volume":"139","author":"Xiao","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113093_bib0026","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2866","article-title":"Improving image restoration through removing degradations in textual representations","author":"Lin","year":"2024"},{"key":"10.1016\/j.patcog.2026.113093_bib0027","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","article-title":"Structure and content-guided video synthesis with diffusion models","author":"Esser","year":"2023"},{"key":"10.1016\/j.patcog.2026.113093_bib0028","series-title":"European Conference on Computer Vision","first-page":"717","article-title":"Language-driven artistic style transfer","author":"Fu","year":"2022"},{"key":"10.1016\/j.patcog.2026.113093_bib0029","unstructured":"W. Li, Y. Peng, M. Zhang, L. Ding, H. Hu, L. Shen, Deep model fusion: a survey, (2023). arXiv preprint arXiv: 2309.15698."},{"key":"10.1016\/j.patcog.2026.113093_bib0030","series-title":"The Eleventh International Conference on Learning Representations","article-title":"Git re-basin: merging models modulo permutation symmetries","author":"Ainsworth","year":"2022"},{"key":"10.1016\/j.patcog.2026.113093_bib0031","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113093_bib0032","unstructured":"J. Achiam, S. Adler, S. Agarwal, L. Ahmad, I. Akkaya, F.L. Aleman, D. Almeida, J. Altenschmidt, S. Altman, S. Anadkat, et al. Gpt-4 technical report, (2023). arXiv preprint arXiv: 2303.08774."},{"issue":"140","key":"10.1016\/j.patcog.2026.113093_bib0033","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.patcog.2026.113093_bib0034","series-title":"Proceedings of naacL-HLT","article-title":"Bert: pre-training of deep bidirectional transformers for language understanding","volume":"1","author":"Kenton","year":"2019"},{"key":"10.1016\/j.patcog.2026.113093_bib0035","series-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","first-page":"270","article-title":"Parameter-efficient weight ensembling facilitates task-level knowledge transfer","author":"Lv","year":"2023"},{"issue":"209","key":"10.1016\/j.patcog.2026.113093_bib0036","first-page":"1","article-title":"Ranking and tuning pre-trained models: a new paradigm for exploiting model hubs","volume":"23","author":"You","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.patcog.2026.113093_bib0037","series-title":"International Conference on Machine Learning","first-page":"9626","article-title":"Zoo-tuning: adaptive transfer from a zoo of models","author":"Shu","year":"2021"},{"key":"10.1016\/j.patcog.2026.113093_bib0038","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4733","article-title":"Freeu: free lunch in diffusion u-net","author":"Si","year":"2024"},{"key":"10.1016\/j.patcog.2026.113093_bib0039","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"674","article-title":"Dreamstyler: paint by style inversion with text-to-image diffusion models","volume":"38","author":"Ahn","year":"2024"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326000567?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326000567?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,21]],"date-time":"2026-06-21T08:33:54Z","timestamp":1782030834000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326000567"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":39,"alternative-id":["S0031320326000567"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113093","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"FreeStyle: Free lunch for text-guided style transfer using diffusion models","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113093","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"113093"}}