{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T01:13:20Z","timestamp":1783559600600,"version":"3.55.0"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032222664","type":"print"},{"value":"9783032222671","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-22267-1_32","type":"book-chapter","created":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:15:32Z","timestamp":1783556132000},"page":"402-413","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["D$$^2$$-Diff: Controllable Fashion Image Generation with\u00a0Disentangled Style and\u00a0Content"],"prefix":"10.1007","author":[{"given":"Fei","family":"Fang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawen","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heng","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruhan","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jia","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinrong","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,2]]},"reference":[{"key":"32_CR1","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. Adv. Neural. Inf. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"32_CR2","unstructured":"Gal, R., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618 (2022)"},{"key":"32_CR3","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"32_CR4","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"32_CR5","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance (2022)"},{"key":"32_CR6","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models (2021)"},{"key":"32_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1007\/978-3-319-46475-6_43","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Johnson","year":"2016","unstructured":"Johnson, J., Alahi, A., Fei-Fei, L.: perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 694\u2013711. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_43"},{"key":"32_CR8","doi-asserted-by":"crossref","unstructured":"Kumari, N., Zhang, B., Zhang, R., Shechtman, E., Zhu, J.Y.: Multi-concept customization of text-to-image diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1931\u20131941 (2023)","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"32_CR9","doi-asserted-by":"crossref","unstructured":"Li, D., Li, J., Hoi, S.C.H.: Blip-diffusion: pre-trained subject representation for controllable text-to-image generation and editing (2023)","DOI":"10.52202\/075280-1312"},{"key":"32_CR10","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.H.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models (2023)"},{"key":"32_CR11","unstructured":"Liu, G., et al.: StyleCrafter: enhancing stylized text-to-video generation with style adapter (2023)"},{"key":"32_CR12","doi-asserted-by":"crossref","unstructured":"Lu, H., Tunanyan, H., Wang, K., Navasardyan, S., Wang, Z., Shi, H.: Specialist diffusion: plug-and-play sample-efficient fine-tuning of text-to-image diffusion models to learn any unseen style. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14267\u201314276 (2023)","DOI":"10.1109\/CVPR52729.2023.01371"},{"key":"32_CR13","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1016\/j.neucom.2022.07.028","volume":"508","author":"H Luo","year":"2022","unstructured":"Luo, H., et al.: CLIP4Clip: an empirical study of clip for end to end video CLIP retrieval and captioning. Neurocomputing 508, 293\u2013304 (2022)","journal-title":"Neurocomputing"},{"key":"32_CR14","doi-asserted-by":"crossref","unstructured":"Mou, C., et al.: T2I-adapter: learning adapters to dig out more controllable ability for text-to-image diffusion models (2023)","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"32_CR15","doi-asserted-by":"crossref","unstructured":"Qi, T., et al.: DEADiff: an efficient stylization diffusion model with disentangled representations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8693\u20138702 (2024)","DOI":"10.1109\/CVPR52733.2024.00830"},{"key":"32_CR16","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: Proceedings of the International Conference on Machine Learning, pp. 8748\u20138763 (2021)"},{"key":"32_CR17","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents (2022)"},{"key":"32_CR18","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"32_CR19","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: DreamBooth: fine tuning text-to-image diffusion models for subject-driven generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22500\u201322510 (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"32_CR20","doi-asserted-by":"crossref","unstructured":"Sohn, K., et\u00a0al.: StyleDrop: text-to-image generation in any style (2023)","DOI":"10.52202\/075280-2920"},{"key":"32_CR21","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models (2020)"},{"key":"32_CR22","unstructured":"Wang, Z., et al.: StyleAdapter: a single-pass lora-free model for stylized image generation (2023)"},{"key":"32_CR23","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhao, L., Xing, W.: StyleDiffusion: controllable disentangled style transfer via diffusion models (2023)","DOI":"10.1109\/ICCV51070.2023.00706"},{"key":"32_CR24","unstructured":"Ye, H., Zhang, J., Liu, S., Han, X., Yang, W.: IP-adapter: text compatible image prompt adapter for text-to-image diffusion models (2023)"},{"key":"32_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"32_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: Inversion-based style transfer with diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10146\u201310156 (2023)","DOI":"10.1109\/CVPR52729.2023.00978"},{"key":"32_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: Domain enhanced arbitrary image style transfer via contrastive learning. In: ACM SIGGRAPH 2022 Conference Proceedings, pp.\u00a01\u20138 (2022)","DOI":"10.1145\/3528233.3530736"},{"key":"32_CR28","unstructured":"Zhu, D., et al.: MiniGPT-4: enhancing vision-language understanding with advanced large language models (2023)"},{"key":"32_CR29","doi-asserted-by":"publisher","first-page":"3375","DOI":"10.1109\/TMM.2022.3160060","volume":"25","author":"T Zhu","year":"2022","unstructured":"Zhu, T., Li, L., Yang, J., Zhao, S., Liu, H., Qian, J.: Multimodal sentiment analysis with image-text interaction network. IEEE Trans. Multimed. 25, 3375\u20133385 (2022)","journal-title":"IEEE Trans. Multimed."}],"container-title":["Lecture Notes in Computer Science","Advances in Computer Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-22267-1_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:15:36Z","timestamp":1783556136000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-22267-1_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032222664","9783032222671"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-22267-1_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors declare that they have no known competing financial interests or personal relationships that could have appeared to influence the work reported in this paper.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"CGI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Computer Graphics International Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hong Kong","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"42","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cgi2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.cgs-network.org\/cgi25","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}