{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T19:10:09Z","timestamp":1745608209251,"version":"3.40.4"},"publisher-location":"Singapore","reference-count":35,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819658114","type":"print"},{"value":"9789819658121","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-5812-1_12","type":"book-chapter","created":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T18:45:18Z","timestamp":1745606718000},"page":"219-233","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SingleDream: Attribute-Driven T2I Customization from\u00a0a\u00a0Single Reference Image"],"prefix":"10.1007","author":[{"given":"Ye","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruiqi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zili","family":"Yi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tieru","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,26]]},"reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Alaluf, Y., Garibi, D., Patashnik, O., Averbuch-Elor, H., Cohen-Or, D.: Cross-image attention for zero-shot appearance transfer. arXiv preprint arXiv:2311.03335 (2023)","DOI":"10.1145\/3641519.3657423"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Avrahami, O., Aberman, K., Fried, O., Cohen-Or, D., Lischinski, D.: Break-a-scene: Extracting multiple concepts from a single image. arXiv preprint arXiv:2305.16311 (2023)","DOI":"10.1145\/3610548.3618154"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Bansal, A., et al.: Universal guidance for diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 843\u2013852 (2023)","DOI":"10.1109\/CVPRW59228.2023.00091"},{"key":"12_CR4","first-page":"25005","volume":"35","author":"A Bar","year":"2022","unstructured":"Bar, A., Gandelsman, Y., Darrell, T., Globerson, A., Efros, A.: Visual prompting via image inpainting. Adv. Neural. Inf. Process. Syst. 35, 25005\u201325017 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"12_CR5","unstructured":"Chen, W., Hu, H., Li, Y., Rui, N., Jia, X., Chang, M.W., Cohen, W.W.: Subject-driven text-to-image generation via apprenticeship learning. arXiv preprint arXiv:2304.00186 (2023)"},{"key":"12_CR6","unstructured":"Chen, W., et al.: Subject-driven text-to-image generation via apprenticeship learning. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"12_CR7","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":"12_CR8","doi-asserted-by":"crossref","unstructured":"Gal, R., Arar, M., Atzmon, Y., Bermano, A.H., Chechik, G., Cohen-Or, D.: Designing an encoder for fast personalization of text-to-image models. arXiv preprint arXiv:2302.12228 (2023)","DOI":"10.1145\/3610548.3618173"},{"issue":"4","key":"12_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592133","volume":"42","author":"R Gal","year":"2023","unstructured":"Gal, R., Arar, M., Atzmon, Y., Bermano, A.H., Chechik, G., Cohen-Or, D.: Encoder-based domain tuning for fast personalization of text-to-image models. ACM Trans. Graph. (TOG) 42(4), 1\u201313 (2023)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"12_CR10","unstructured":"Goel, V., et al.: Pair-diffusion: object-level image editing with structure-and-appearance paired diffusion models. arXiv preprint arXiv:2303.17546 (2023)"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Han, L., Li, Y., Zhang, H., Milanfar, P., Metaxas, D., Yang, F.: Svdiff: compact parameter space for diffusion fine-tuning. arXiv preprint arXiv:2303.11305 (2023)","DOI":"10.1109\/ICCV51070.2023.00673"},{"key":"12_CR12","unstructured":"Jia, X., et al.: Taming encoder for zero fine-tuning image customization with text-to-image diffusion models. arXiv preprint arXiv:2304.02642 (2023)"},{"key":"12_CR13","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":"12_CR14","unstructured":"Ma, Y., Yang, H., Wang, W., Fu, J., Liu, J.: Unified multi-modal latent diffusion for joint subject and text conditional image generation. arXiv preprint arXiv:2303.09319 (2023)"},{"key":"12_CR15","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. arXiv preprint arXiv:2302.08453 (2023)","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"12_CR16","unstructured":"Nguyen, T., Li, Y., Ojha, U., Lee, Y.J.: Visual instruction inversion: image editing via visual prompting. arXiv preprint arXiv:2307.14331 (2023)"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Qi, T., et al.: Deadiff: an efficient stylization diffusion model with disentangled representations. arXiv preprint arXiv:2403.06951 (2024)","DOI":"10.1109\/CVPR52733.2024.00830"},{"key":"12_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":"12_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":"12_CR20","doi-asserted-by":"crossref","unstructured":"Ruiz, N., et al.: Hyperdreambooth: hypernetworks for fast personalization of text-to-image models. arXiv preprint arXiv:2307.06949 (2023)","DOI":"10.1109\/CVPR52733.2024.00624"},{"key":"12_CR21","unstructured":"Ryu, S.: Low-rank adaptation for fast text-to-image diffusion fine-tuning (2023)"},{"key":"12_CR22","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Shi, J., Xiong, W., Lin, Z., Jung, H.J.: Instantbooth: personalized text-to-image generation without test-time finetuning. arXiv preprint arXiv:2304.03411 (2023)","DOI":"10.1109\/CVPR52733.2024.00816"},{"key":"12_CR24","unstructured":"Sohn, K., et\u00a0al.: Styledrop: text-to-image generation in any style. arXiv preprint arXiv:2306.00983 (2023)"},{"key":"12_CR25","unstructured":"Sun, Y., et al.: Imagebrush: learning visual in-context instructions for exemplar-based image manipulation. arXiv preprint arXiv:2308.00906 (2023)"},{"key":"12_CR26","doi-asserted-by":"crossref","unstructured":"Tumanyan, N., Bar-Tal, O., Bagon, S., Dekel, T.: Splicing vit features for semantic appearance transfer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10748\u201310757 (2022)","DOI":"10.1109\/CVPR52688.2022.01048"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Valevski, D., Lumen, D., Matias, Y., Leviathan, Y.: Face0: instantaneously conditioning a text-to-image model on a face. In: SIGGRAPH Asia 2023 Conference Papers, pp. 1\u201310 (2023)","DOI":"10.1145\/3610548.3618249"},{"key":"12_CR28","unstructured":"Voynov, A., Chu, Q., Cohen-Or, D., Aberman, K.: $$ p+ $$: extended textual conditioning in text-to-image generation. arXiv preprint arXiv:2303.09522 (2023)"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Wei, Y., Zhang, Y., Ji, Z., Bai, J., Zhang, L., Zuo, W.: Elite: encoding visual concepts into textual embeddings for customized text-to-image generation. arXiv preprint arXiv:2302.13848 (2023)","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"12_CR30","doi-asserted-by":"crossref","unstructured":"Xiao, G., Yin, T., Freeman, W.T., Durand, F., Han, S.: Fastcomposer: tuning-free multi-subject image generation with localized attention. arXiv preprint arXiv:2305.10431 (2023)","DOI":"10.1007\/s11263-024-02227-z"},{"key":"12_CR31","doi-asserted-by":"crossref","unstructured":"Xu, X., Guo, J., Wang, Z., Huang, G., Essa, I., Shi, H.: Prompt-free diffusion: taking\" text\" out of text-to-image diffusion models. arXiv preprint arXiv:2305.16223 (2023)","DOI":"10.1109\/CVPR52733.2024.00829"},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"Yang, B., et al.: Paint by example: exemplar-based image editing with diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18381\u201318391 (2023)","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"12_CR33","unstructured":"Ye, H., Zhang, J., Liu, S., Han, X., Yang, W.: Ip-adapter: text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:2308.06721 (2023)"},{"key":"12_CR34","unstructured":"Yuan, G., et al.: Inserting anybody in diffusion models via celeb basis. arXiv preprint arXiv:2306.00926 (2023)"},{"key":"12_CR35","unstructured":"Zhang, Y., et al.: Prospect: expanded conditioning for the personalization of attribute-aware image generation. arXiv preprint arXiv:2305.16225 (2023)"}],"container-title":["Lecture Notes in Computer Science","Computational Visual Media"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-5812-1_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T18:45:32Z","timestamp":1745606732000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-5812-1_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819658114","9789819658121"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-5812-1_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"26 April 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CVM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Visual Media","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hong Kong SAR","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":"19 April 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 April 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cvm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iccvm.org\/2025\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}