{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:37:08Z","timestamp":1778081828187,"version":"3.51.4"},"publisher-location":"Cham","reference-count":57,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726835","type":"print"},{"value":"9783031726842","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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\/978-3-031-72684-2_11","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T19:02:45Z","timestamp":1730574165000},"page":"181-198","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":51,"title":["Implicit Style-Content Separation Using B-LoRA"],"prefix":"10.1007","author":[{"given":"Yarden","family":"Frenkel","sequence":"first","affiliation":[]},{"given":"Yael","family":"Vinker","sequence":"additional","affiliation":[]},{"given":"Ariel","family":"Shamir","sequence":"additional","affiliation":[]},{"given":"Daniel","family":"Cohen-Or","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"11_CR1","unstructured":"Agarwal, A., Karanam, S., Shukla, T., Srinivasan, B.V.: An image is worth multiple words: multi-attribute inversion for constrained text-to-image synthesis. ArXiv abs\/2311.11919 (2023). https:\/\/api.semanticscholar.org\/CorpusID:265295502"},{"key":"11_CR2","unstructured":"Alaluf, Y., Garibi, D., Patashnik, O., Averbuch-Elor, H., Cohen-Or, D.: Cross-image attention for zero-shot appearance transfer. ArXiv abs\/2311.03335 (2023). https:\/\/api.semanticscholar.org\/CorpusID:265043677"},{"issue":"6","key":"11_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3618322","volume":"42","author":"Y Alaluf","year":"2023","unstructured":"Alaluf, Y., Richardson, E., Metzer, G., Cohen-Or, D.: A neural space-time representation for text-to-image personalization. ACM Trans. Graph. (TOG) 42(6), 1\u201310 (2023)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"11_CR4","unstructured":"Arar, M., et al.: PALP: prompt aligned personalization of text-to-image models. ArXiv abs\/2401.06105 (2024). https:\/\/api.semanticscholar.org\/CorpusID:266933184"},{"key":"11_CR5","doi-asserted-by":"publisher","unstructured":"Avrahami, O., Aberman, K., Fried, O., Cohen-Or, D., Lischinski, D.: Break-a-scene: extracting multiple concepts from a single image. In: SIGGRAPH Asia 2023 Conference Papers, SA 2023. Association for Computing Machinery, New York (2023). https:\/\/doi.org\/10.1145\/3610548.3618154","DOI":"10.1145\/3610548.3618154"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Avrahami, O., Fried, O., Lischinski, D.: Blended latent diffusion. ACM Trans. Graph. (TOG) 42, 1\u201311 (2022). https:\/\/api.semanticscholar.org\/CorpusID:249394540","DOI":"10.1145\/3592450"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Avrahami, O., et al.: The chosen one: consistent characters in text-to-image diffusion models. arXiv preprint arXiv:2311.10093 (2023)","DOI":"10.1145\/3641519.3657430"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9630\u20139640 (2021). https:\/\/api.semanticscholar.org\/CorpusID:233444273","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"11_CR9","unstructured":"Chang, H., et al.: Muse: text-to-image generation via masked generative transformers. ArXiv abs\/2301.00704 (2023). https:\/\/api.semanticscholar.org\/CorpusID:255372955"},{"key":"11_CR10","unstructured":"Chen, M., Laina, I., Vedaldi, A.: Training-free layout control with cross-attention guidance. ArXiv abs\/2304.03373 (2023). https:\/\/api.semanticscholar.org\/CorpusID:258041377"},{"key":"11_CR11","unstructured":"Couairon, G., Verbeek, J., Schwenk, H., Cord, M.: DiffEdit: diffusion-based semantic image editing with mask guidance. ArXiv abs\/2210.11427 (2022). https:\/\/api.semanticscholar.org\/CorpusID:253018768"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Efros, A.A., Freeman, W.T.: Image quilting for texture synthesis and transfer. In: Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques (2001). https:\/\/api.semanticscholar.org\/CorpusID:9334387","DOI":"10.1145\/383259.383296"},{"key":"11_CR13","unstructured":"Epstein, D., Jabri, A., Poole, B., Efros, A.A., Holynski, A.: Diffusion self-guidance for controllable image generation. ArXiv abs\/2306.00986 (2023). https:\/\/api.semanticscholar.org\/CorpusID:258999106"},{"key":"11_CR14","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":"11_CR15","unstructured":"Gandikota, R., Materzynska, J., Zhou, T., Torralba, A., Bau, D.: Concept sliders: LoRA adaptors for precise control in diffusion models. ArXiv abs\/2311.12092 (2023). https:\/\/api.semanticscholar.org\/CorpusID:265308675"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Gatys, L.A., Ecker, A.S., Bethge, M.: Image style transfer using convolutional neural networks. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2414\u20132423 (2016). https:\/\/api.semanticscholar.org\/CorpusID:206593710","DOI":"10.1109\/CVPR.2016.265"},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"Goodfellow, I.J., et al.: Generative adversarial networks. Commun. ACM 63, 139\u2013144 (2014). https:\/\/api.semanticscholar.org\/CorpusID:1033682","DOI":"10.1145\/3422622"},{"key":"11_CR18","unstructured":"Gu, Y., et al.: Mix-of-show: decentralized low-rank adaptation for multi-concept customization of diffusion models. ArXiv abs\/2305.18292 (2023). https:\/\/api.semanticscholar.org\/CorpusID:258960192"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Han, L., Li, Y., Zhang, H., Milanfar, P., Metaxas, D.N., Yang, F.: SVDiff: compact parameter space for diffusion fine-tuning. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 7289\u20137300 (2023). https:\/\/api.semanticscholar.org\/CorpusID:257631648","DOI":"10.1109\/ICCV51070.2023.00673"},{"key":"11_CR20","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J.M., Aberman, K., Pritch, Y., Cohen-Or, D.: Prompt-to-prompt image editing with cross attention control. ArXiv abs\/2208.01626 (2022). https:\/\/api.semanticscholar.org\/CorpusID:251252882"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Hertz, A., Voynov, A., Fruchter, S., Cohen-Or, D.: Style aligned image generation via shared attention. arXiv preprint arXiv:2312.02133 (2023)","DOI":"10.1109\/CVPR52733.2024.00457"},{"key":"11_CR22","doi-asserted-by":"publisher","unstructured":"Hertzmann, A., Jacobs, C.E., Oliver, N., Curless, B., Salesin, D.H.: Image analogies, pp. 327\u2013340 (2001). https:\/\/doi.org\/10.1145\/383259.383295","DOI":"10.1145\/383259.383295"},{"key":"11_CR23","unstructured":"Houlsby, N., et al.: Parameter-efficient transfer learning for NLP. ArXiv abs\/1902.00751 (2019). https:\/\/api.semanticscholar.org\/CorpusID:59599816"},{"key":"11_CR24","unstructured":"Hu, J.E., et al.: LoRA: low-rank adaptation of large language models. ArXiv abs\/2106.09685 (2021). https:\/\/api.semanticscholar.org\/CorpusID:235458009"},{"key":"11_CR25","doi-asserted-by":"crossref","unstructured":"Huang, X., Belongie, S.J.: Arbitrary style transfer in real-time with adaptive instance normalization. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 1510\u20131519 (2017). https:\/\/api.semanticscholar.org\/CorpusID:6576859","DOI":"10.1109\/ICCV.2017.167"},{"key":"11_CR26","doi-asserted-by":"publisher","unstructured":"Ilharco, G., et al.: OpenCLIP (2021). https:\/\/doi.org\/10.5281\/zenodo.5143773","DOI":"10.5281\/zenodo.5143773"},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5967\u20135976 (2016). https:\/\/api.semanticscholar.org\/CorpusID:6200260","DOI":"10.1109\/CVPR.2017.632"},{"key":"11_CR28","doi-asserted-by":"crossref","unstructured":"Jing, Y., Yang, Y., Feng, Z., Ye, J., Song, M.: Neural style transfer: a review. IEEE Trans. Vis. Comput. Graph. 26, 3365\u20133385 (2017). https:\/\/api.semanticscholar.org\/CorpusID:4875951","DOI":"10.1109\/TVCG.2019.2921336"},{"key":"11_CR29","doi-asserted-by":"crossref","unstructured":"Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. ArXiv abs\/1603.08155 (2016). https:\/\/api.semanticscholar.org\/CorpusID:980236","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"11_CR30","doi-asserted-by":"publisher","unstructured":"Katzir, O., Lischinski, D., Cohen-Or, D.: Cross-domain cascaded deep translation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 673-685. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_40, https:\/\/api.semanticscholar.org\/CorpusID:209315529","DOI":"10.1007\/978-3-030-58536-5_40"},{"key":"11_CR31","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: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 1931\u20131941 (2022). https:\/\/api.semanticscholar.org\/CorpusID:254408780","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"11_CR32","unstructured":"Li, S., et al.: StyleDiffusion: prompt-embedding inversion for text-based editing. ArXiv abs\/2303.15649 (2023). https:\/\/api.semanticscholar.org\/CorpusID:257771440"},{"key":"11_CR33","unstructured":"mkshing: Ziplora-pytorch. https:\/\/github.com\/mkshing\/ziplora-pytorch"},{"key":"11_CR34","doi-asserted-by":"publisher","unstructured":"Mokady, R., Hertz, A., Aberman, K., Pritch, Y., Cohen-Or, D.: Null-text inversion for editing real images using guided diffusion models. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, 17\u201324 June 2023, pp. 6038\u20136047. IEEE (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.00585","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"11_CR35","doi-asserted-by":"publisher","unstructured":"Park, T., Efros, A.A., Zhang, R., Zhu, J.-Y.: Contrastive learning for unpaired image-to-image translation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 319\u2013345. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_19, https:\/\/api.semanticscholar.org\/CorpusID:220871180","DOI":"10.1007\/978-3-030-58545-7_19"},{"key":"11_CR36","doi-asserted-by":"crossref","unstructured":"Parmar, G., Singh, K.K., Zhang, R., Li, Y., Lu, J., Zhu, J.Y.: Zero-shot image-to-image translation. In: ACM SIGGRAPH 2023 Conference Proceedings (2023). https:\/\/api.semanticscholar.org\/CorpusID:256616002","DOI":"10.1145\/3588432.3591513"},{"key":"11_CR37","unstructured":"Po, R., Yang, G., Aberman, K., Wetzstein, G.: Orthogonal adaptation for modular customization of diffusion models. ArXiv abs\/2312.02432 (2023). https:\/\/api.semanticscholar.org\/CorpusID:265659333"},{"key":"11_CR38","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. ArXiv abs\/2307.01952 (2023). https:\/\/api.semanticscholar.org\/CorpusID:259341735"},{"key":"11_CR39","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (2021). https:\/\/api.semanticscholar.org\/CorpusID:231591445"},{"key":"11_CR40","unstructured":"Research, F.: Cog SDXL canny ControlNet with LoRA support. https:\/\/replicate.com\/batouresearch\/sdxl-controlnet-lora"},{"key":"11_CR41","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10674\u201310685 (2021). https:\/\/api.semanticscholar.org\/CorpusID:245335280","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"11_CR42","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":"11_CR43","unstructured":"Ryu, S.: Low-rank adaptation for fast text-to-image diffusion fine-tuning. https:\/\/github.com\/cloneofsimo\/lora"},{"key":"11_CR44","doi-asserted-by":"crossref","unstructured":"Shah, V., et al.: ZipLoRA: any subject in any style by effectively merging LoRAs. arXiv preprint arXiv:2311.13600 (2023)","DOI":"10.1007\/978-3-031-73232-4_24"},{"key":"11_CR45","unstructured":"Sohn, K., et al.: StyleDrop: text-to-image generation in any style (2023)"},{"key":"11_CR46","unstructured":"Tenenbaum, J., Freeman, W.: Separating style and content. In: Mozer, M., Jordan, M., Petsche, T. (eds.) Advances in Neural Information Processing Systems, vol.\u00a09. MIT Press (1996). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/1996\/file\/70222949cc0db89ab32c9969754d4758-Paper.pdf"},{"key":"11_CR47","doi-asserted-by":"crossref","unstructured":"Tumanyan, N., Geyer, M., Bagon, S., Dekel, T.: Plug-and-play diffusion features for text-driven image-to-image translation. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 1921\u20131930 (2022). https:\/\/api.semanticscholar.org\/CorpusID:253801961","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"11_CR48","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Neural Information Processing Systems (2017). https:\/\/api.semanticscholar.org\/CorpusID:13756489"},{"key":"11_CR49","doi-asserted-by":"publisher","unstructured":"Vinker, Y., Voynov, A., Cohen-Or, D., Shamir, A.: Concept decomposition for visual exploration and inspiration. ACM Trans. Graph. 42(6) (2023). https:\/\/doi.org\/10.1145\/3618315","DOI":"10.1145\/3618315"},{"key":"11_CR50","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":"11_CR51","unstructured":"Wang, H., Spinelli, M., Wang, Q., Bai, X., Qin, Z., Chen, A.: InstantStyle: free lunch towards style-preserving in text-to-image generation. ArXiv abs\/2404.02733 (2024). https:\/\/api.semanticscholar.org\/CorpusID:268876474"},{"key":"11_CR52","doi-asserted-by":"crossref","unstructured":"Yang, S., Joo Hwang, H., Ye, J.C.: Zero-shot contrastive loss for text-guided diffusion image style transfer. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 22816\u201322825 (2023). https:\/\/api.semanticscholar.org\/CorpusID:257532402","DOI":"10.1109\/ICCV51070.2023.02091"},{"key":"11_CR53","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 abs\/2308.06721 (2023). https:\/\/api.semanticscholar.org\/CorpusID:260886966"},{"key":"11_CR54","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3813\u20133824 (2023). https:\/\/api.semanticscholar.org\/CorpusID:256827727","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"11_CR55","doi-asserted-by":"crossref","unstructured":"Xin Zhang, Y., et al.: Inversion-based style transfer with diffusion models. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10146\u201310156 (2022). https:\/\/api.semanticscholar.org\/CorpusID:257427673","DOI":"10.1109\/CVPR52729.2023.00978"},{"issue":"6","key":"11_CR56","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3618342","volume":"42","author":"Y Zhang","year":"2023","unstructured":"Zhang, Y., et al.: ProSpect: prompt spectrum for attribute-aware personalization of diffusion models. ACM Trans. Graph. (TOG) 42(6), 1\u201314 (2023)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"11_CR57","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2242\u20132251 (2017). https:\/\/api.semanticscholar.org\/CorpusID:206770979","DOI":"10.1109\/ICCV.2017.244"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72684-2_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T19:06:01Z","timestamp":1730574361000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72684-2_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9783031726835","9783031726842"],"references-count":57,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72684-2_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}