{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:17:59Z","timestamp":1777886279479,"version":"3.51.4"},"reference-count":55,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100020595","name":"National Science and Technology Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100020595","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Visual Communication and Image Representation"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1016\/j.jvcir.2026.104759","type":"journal-article","created":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T15:57:56Z","timestamp":1772207876000},"page":"104759","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Dp-LoRA: An enhanced Concept Slider for high-fidelity editing on original images"],"prefix":"10.1016","volume":"117","author":[{"given":"Chenxuan","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4059-6358","authenticated-orcid":false,"given":"Wei-Chuen","family":"Yau","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3498-8489","authenticated-orcid":false,"given":"Y.S.","family":"Gan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3867-1964","authenticated-orcid":false,"given":"Sze-Teng","family":"Liong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7733-1690","authenticated-orcid":false,"given":"Changsaar","family":"Chai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.jvcir.2026.104759_b1","first-page":"1","article-title":"Application of generative artificial intelligence AIGC technology under neural network algorithm in game character art design","author":"Li","year":"2024","journal-title":"J. Knowl. Econ."},{"key":"10.1016\/j.jvcir.2026.104759_b2","series-title":"2023 4th International Conference on Intelligent Design","first-page":"129","article-title":"A new art design method based on AIGC: Analysis from the perspective of creation efficiency","author":"Rao","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104759_b3","series-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2022"},{"key":"10.1016\/j.jvcir.2026.104759_b4","series-title":"Controllable textual inversion for personalized text-to-image generation","author":"Yang","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104759_b5","doi-asserted-by":"crossref","unstructured":"T. Brooks, A. Holynski, A.A. Efros, Instructpix2pix: Learning to follow image editing instructions, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 18392\u201318402.","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"10.1016\/j.jvcir.2026.104759_b6","series-title":"Reasonpix2pix: instruction reasoning dataset for advanced image editing","author":"Jin","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104759_b7","first-page":"03017","article-title":"From PGC to UGC to AIGC: Change of content paradigm","volume":"vol. 199","author":"Gao","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104759_b8","series-title":"Openai","year":"2025"},{"key":"10.1016\/j.jvcir.2026.104759_b9","series-title":"Deepseek-v3 technical report","author":"Liu","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104759_b10","series-title":"Sora: A review on background, technology, limitations, and opportunities of large vision models","author":"Liu","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104759_b11","series-title":"Ediff-i: Text-to-image diffusion models with an ensemble of expert denoisers","author":"Balaji","year":"2022"},{"key":"10.1016\/j.jvcir.2026.104759_b12","series-title":"Dreamllm: Synergistic multimodal comprehension and creation","author":"Dong","year":"2023"},{"issue":"6","key":"10.1016\/j.jvcir.2026.104759_b13","doi-asserted-by":"crossref","first-page":"4409","DOI":"10.1109\/TPAMI.2025.3541625","article-title":"Diffusion model-based image editing: A survey","volume":"47","author":"Huang","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.jvcir.2026.104759_b14","doi-asserted-by":"crossref","unstructured":"S. Wang, C. Saharia, C. Montgomery, J. Pont-Tuset, S. Noy, S. Pellegrini, Y. Onoe, S. Laszlo, D.J. Fleet, R. Soricut, et al., Imagen editor and editbench: Advancing and evaluating text-guided image inpainting, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 18359\u201318369.","DOI":"10.1109\/CVPR52729.2023.01761"},{"key":"10.1016\/j.jvcir.2026.104759_b15","doi-asserted-by":"crossref","unstructured":"W. Dong, S. Xue, X. Duan, S. Han, Prompt tuning inversion for text-driven image editing using diffusion models, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 7430\u20137440.","DOI":"10.1109\/ICCV51070.2023.00683"},{"key":"10.1016\/j.jvcir.2026.104759_b16","doi-asserted-by":"crossref","unstructured":"R. Mokady, A. Hertz, K. Aberman, Y. Pritch, D. Cohen-Or, Null-text inversion for editing real images using guided diffusion models, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 6038\u20136047.","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"10.1016\/j.jvcir.2026.104759_b17","series-title":"European Conference on Computer Vision","first-page":"172","article-title":"Concept sliders: Lora adaptors for precise control in diffusion models","author":"Gandikota","year":"2024"},{"issue":"2","key":"10.1016\/j.jvcir.2026.104759_b18","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models.","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"10.1016\/j.jvcir.2026.104759_b19","doi-asserted-by":"crossref","unstructured":"M. Jones, S.-Y. Wang, N. Kumari, D. Bau, J.-Y. Zhu, Customizing text-to-image models with a single image pair, in: SIGGRAPH Asia 2024 Conference Papers, 2024, pp. 1\u201313.","DOI":"10.1145\/3680528.3687642"},{"key":"10.1016\/j.jvcir.2026.104759_b20","series-title":"UnZipLoRA: Separating content and style from a single image","author":"Liu","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104759_b21","series-title":"European Conference on Computer Vision","first-page":"422","article-title":"Ziplora: Any subject in any style by effectively merging loras","author":"Shah","year":"2024"},{"issue":"11","key":"10.1016\/j.jvcir.2026.104759_b22","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1145\/3422622","article-title":"Generative adversarial networks","volume":"63","author":"Goodfellow","year":"2020","journal-title":"Commun. ACM"},{"key":"10.1016\/j.jvcir.2026.104759_b23","series-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2021"},{"key":"10.1016\/j.jvcir.2026.104759_b24","series-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104759_b25","first-page":"25278","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jvcir.2026.104759_b26","series-title":"Diffusiondb: A large-scale prompt gallery dataset for text-to-image generative models","author":"Wang","year":"2022"},{"issue":"1","key":"10.1016\/j.jvcir.2026.104759_b27","first-page":"295","article-title":"Promptmagician: Interactive prompt engineering for text-to-image creation","volume":"30","author":"Feng","year":"2023","journal-title":"IEEE Trans. Vis. Comput. Graphics"},{"key":"10.1016\/j.jvcir.2026.104759_b28","series-title":"Human preference score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis","author":"Wu","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104759_b29","doi-asserted-by":"crossref","unstructured":"S. Ge, T. Park, J.-Y. Zhu, J.-B. Huang, Expressive text-to-image generation with rich text, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 7545\u20137556.","DOI":"10.1109\/ICCV51070.2023.00694"},{"key":"10.1016\/j.jvcir.2026.104759_b30","first-page":"4296","article-title":"T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models","volume":"vol. 38","author":"Mou","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104759_b31","series-title":"Information theoretic text-to-image alignment","author":"Wang","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104759_b32","article-title":"Diffstyler: Controllable dual diffusion for text-driven image stylization","author":"Huang","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.jvcir.2026.104759_b33","series-title":"Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.jvcir.2026.104759_b34","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4401","article-title":"A style-based generator architecture for generative adversarial networks","author":"Karras","year":"2019"},{"key":"10.1016\/j.jvcir.2026.104759_b35","series-title":"Lora+: Efficient low rank adaptation of large models","author":"Hayou","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104759_b36","series-title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","first-page":"10225","article-title":"MagicTailor: Component-controllable personalization in text-to-image diffusion models","author":"Zhou","year":"2025"},{"key":"10.1016\/j.jvcir.2026.104759_b37","series-title":"TARA: Token-aware LoRA for composable personalization in diffusion models","author":"Peng","year":"2025"},{"key":"10.1016\/j.jvcir.2026.104759_b38","doi-asserted-by":"crossref","first-page":"10088","DOI":"10.52202\/075280-0441","article-title":"Qlora: Efficient finetuning of quantized llms","volume":"36","author":"Dettmers","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jvcir.2026.104759_b39","series-title":"Longqlora: Efficient and effective method to extend context length of large language models","author":"Yang","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104759_b40","doi-asserted-by":"crossref","unstructured":"Q. Liu, X. Wu, X. Zhao, Y. Zhu, D. Xu, F. Tian, Y. Zheng, When moe meets llms: Parameter efficient fine-tuning for multi-task medical applications, in: Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2024, pp. 1104\u20131114.","DOI":"10.1145\/3626772.3657722"},{"key":"10.1016\/j.jvcir.2026.104759_b41","series-title":"Make LoRA great again: Boosting LoRA with adaptive singular values and mixture-of-experts optimization alignment","author":"Fan","year":"2025"},{"key":"10.1016\/j.jvcir.2026.104759_b42","series-title":"2025 IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"660","article-title":"Dual-Schedule Inversion: Training- and Tuning-Free Inversion for Real Image Editing","author":"Huang","year":"2025"},{"key":"10.1016\/j.jvcir.2026.104759_b43","series-title":"InstantBooth: Personalized text-to-image generation without test-time finetuning","author":"Shi","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104759_b44","series-title":"Progressive growing of gans for improved quality, stability, and variation","author":"Karras","year":"2017"},{"key":"10.1016\/j.jvcir.2026.104759_b45","series-title":"European Conference on Computer Vision","first-page":"181","article-title":"Implicit style-content separation using b-lora","author":"Frenkel","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104759_b46","series-title":"Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 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.jvcir.2026.104759_b47","series-title":"MRStyle: A unified framework for color style transfer with multi-modality reference","author":"Huang","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104759_b48","series-title":"Autolora: Automatically tuning matrix ranks in low-rank adaptation based on meta learning","author":"Zhang","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104759_b49","series-title":"Stable diffusion prompt: a definitive guide - stable diffusion art","author":"Andrew","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104759_b50","doi-asserted-by":"crossref","DOI":"10.1016\/j.metrad.2023.100047","article-title":"Review of large vision models and visual prompt engineering","author":"Wang","year":"2023","journal-title":"Meta-Radiology"},{"key":"10.1016\/j.jvcir.2026.104759_b51","series-title":"Unleashing the potential of prompt engineering in large language models: a comprehensive review","author":"Chen","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104759_b52","series-title":"Multi-lora composition for image generation","author":"Zhong","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104759_b53","doi-asserted-by":"crossref","unstructured":"R. Zhang, P. Isola, A.A. Efros, E. Shechtman, O. Wang, The unreasonable effectiveness of deep features as a perceptual metric, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 586\u2013595.","DOI":"10.1109\/CVPR.2018.00068"},{"issue":"4","key":"10.1016\/j.jvcir.2026.104759_b54","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: from error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.jvcir.2026.104759_b55","series-title":"Clipscore: A reference-free evaluation metric for image captioning","author":"Hessel","year":"2021"}],"container-title":["Journal of Visual Communication and Image Representation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320326000544?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320326000544?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T03:32:25Z","timestamp":1777606345000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1047320326000544"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":55,"alternative-id":["S1047320326000544"],"URL":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104759","relation":{},"ISSN":["1047-3203"],"issn-type":[{"value":"1047-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Dp-LoRA: An enhanced Concept Slider for high-fidelity editing on original images","name":"articletitle","label":"Article Title"},{"value":"Journal of Visual Communication and Image Representation","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104759","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104759"}}