{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:47:16Z","timestamp":1772905636736,"version":"3.50.1"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031731150","type":"print"},{"value":"9783031731167","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"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\/978-3-031-73116-7_14","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:15:38Z","timestamp":1730301338000},"page":"233-250","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Tuning-Free Image Customization with\u00a0Image and\u00a0Text Guidance"],"prefix":"10.1007","author":[{"given":"Pengzhi","family":"Li","sequence":"first","affiliation":[]},{"given":"Qiang","family":"Nie","sequence":"additional","affiliation":[]},{"given":"Ying","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Xi","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Kai","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Yuhuan","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Yong","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Jinlong","family":"Peng","sequence":"additional","affiliation":[]},{"given":"Chengjie","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Feng","family":"Zheng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"key":"14_CR1","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"},{"issue":"4","key":"14_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592450","volume":"42","author":"O Avrahami","year":"2023","unstructured":"Avrahami, O., Fried, O., Lischinski, D.: Blended latent diffusion. ACM Trans. Graph. 42(4), 1\u201311 (2023)","journal-title":"ACM Trans. Graph."},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Avrahami, O., Lischinski, D., Fried, O.: Blended diffusion for text-driven editing of natural images. In: CVPR, pp. 18208\u201318218 (2022)","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: Instructpix2pix: learning to follow image editing instructions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18392\u201318402 (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Cao, M., Wang, X., Qi, Z., Shan, Y., Qie, X., Zheng, Y.: Masactrl: tuning-free mutual self-attention control for consistent image synthesis and editing. arXiv preprint arXiv:2304.08465 (2023)","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Chefer, H., Alaluf, Y., Vinker, Y., Wolf, L., Cohen-Or, D.: Attend-and-excite: attention-based semantic guidance for text-to-image diffusion models. arXiv preprint arXiv:2301.13826 (2023)","DOI":"10.1145\/3592116"},{"key":"14_CR8","unstructured":"Chen, W., et al.: Subject-driven text-to-image generation via apprenticeship learning. arXiv preprint arXiv:2304.00186 (2023)"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Chen, X., Huang, L., Liu, Y., Shen, Y., Zhao, D., Zhao, H.: Anydoor: zero-shot object-level image customization. arXiv preprint arXiv:2307.09481 (2023)","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Cong, W., et al.: Dovenet: deep image harmonization via domain verification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8394\u20138403 (2020)","DOI":"10.1109\/CVPR42600.2020.00842"},{"key":"14_CR11","unstructured":"Couairon, G., Verbeek, J., Schwenk, H., Cord, M.: Diffedit: diffusion-based semantic image editing with mask guidance. arXiv preprint arXiv:2210.11427 (2022)"},{"key":"14_CR12","doi-asserted-by":"publisher","first-page":"4759","DOI":"10.1109\/TIP.2020.2975979","volume":"29","author":"X Cun","year":"2020","unstructured":"Cun, X., Pun, C.M.: Improving the harmony of the composite image by spatial-separated attention module. IEEE Trans. Image Process. 29, 4759\u20134771 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"14_CR13","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":"14_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":"14_CR15","unstructured":"Han, I., Yang, S., Kwon, T., Ye, J.C.: Highly personalized text embedding for image manipulation by stable diffusion. arXiv preprint arXiv:2303.08767 (2023)"},{"key":"14_CR16","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":"14_CR17","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-Or, D.: Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:2208.01626 (2022)"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Hong, Y., Niu, L., Zhang, J.: Shadow generation for composite image in real-world scenes. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 914\u2013922 (2022)","DOI":"10.1609\/aaai.v36i1.19974"},{"key":"14_CR19","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":"14_CR20","doi-asserted-by":"crossref","unstructured":"Kawar, B., et al.: Imagic: text-based real image editing with diffusion models. arXiv preprint arXiv:2210.09276 (2022)","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"14_CR21","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":"14_CR22","doi-asserted-by":"crossref","unstructured":"Li, P., Huang, Q., Ding, Y., Li, Z.: Layerdiffusion:layered controlled image editing with diffusion models. arXiv preprint arXiv:2305.18676 (2023)","DOI":"10.1145\/3610543.3626172"},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft coco: common objects in context. In: ECCV 2014, Part V 13, pp. 740\u2013755. Springer, Cham (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Liu, D., Long, C., Zhang, H., Yu, H., Dong, X., Xiao, C.: Arshadowgan: shadow generative adversarial network for augmented reality in single light scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8139\u20138148 (2020)","DOI":"10.1109\/CVPR42600.2020.00816"},{"key":"14_CR25","unstructured":"Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., Zhu, J.: Dpm-solver++: fast solver for guided sampling of diffusion probabilistic models. arXiv preprint arXiv:2211.01095 (2022)"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"Lu, S., Liu, Y., Kong, A.W.K.: Tf-icon: diffusion-based training-free cross-domain image composition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2294\u20132305 (2023)","DOI":"10.1109\/ICCV51070.2023.00218"},{"key":"14_CR27","unstructured":"Meng, C., Song, Y., Song, J., Wu, J., Zhu, J.Y., Ermon, S.: Sdedit: image synthesis and editing with stochastic differential equations. arXiv preprint arXiv:2108.01073 (2021)"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Mokady, R., Hertz, A., Aberman, K., Pritch, Y., Cohen-Or, D.: Null-text inversion for editing real images using guided diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6038\u20136047 (2023)","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"14_CR29","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"14_CR30","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"14_CR31","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"14_CR32","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: MICCAI 2015, Part III 18, pp. 234\u2013241. Springer, Cham (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"14_CR33","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. arXiv preprint arXiv:2208.12242 (2022)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"14_CR34","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":"14_CR35","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)"},{"key":"14_CR36","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: International Conference on Learning Representations (2020)"},{"key":"14_CR37","doi-asserted-by":"crossref","unstructured":"Tripathi, S., Chandra, S., Agrawal, A., Tyagi, A., Rehg, J.M., Chari, V.: Learning to generate synthetic data via compositing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 461\u2013470 (2019)","DOI":"10.1109\/CVPR.2019.00055"},{"key":"14_CR38","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. arXiv preprint arXiv:2211.12572 (2022)","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"14_CR39","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":"14_CR40","doi-asserted-by":"crossref","unstructured":"Xie, S., Zhang, Z., Lin, Z., Hinz, T., Zhang, K.: Smartbrush: text and shape guided object inpainting with diffusion model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22428\u201322437 (2023)","DOI":"10.1109\/CVPR52729.2023.02148"},{"key":"14_CR41","doi-asserted-by":"publisher","unstructured":"Xue, B., Ran, S., Chen, Q., Jia, R., Zhao, B., Tang, X.: DCCF: deep comprehensible color filter learning framework for\u00a0high-resolution image harmonization. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022, Part VII, pp. 300\u2013316. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20071-7_18","DOI":"10.1007\/978-3-031-20071-7_18"},{"key":"14_CR42","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":"14_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"566","DOI":"10.1007\/978-3-030-58601-0_34","volume-title":"Computer Vision \u2013 ECCV 2020","author":"L Zhang","year":"2020","unstructured":"Zhang, L., Wen, T., Min, J., Wang, J., Han, D., Shi, J.: Learning object placement by inpainting for compositional data augmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12358, pp. 566\u2013581. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58601-0_34"},{"key":"14_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, L., Wen, T., Shi, J.: Deep image blending. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 231\u2013240 (2020)","DOI":"10.1109\/WACV45572.2020.9093632"},{"key":"14_CR45","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":"14_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"14_CR47","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","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73116-7_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:22:24Z","timestamp":1730301744000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73116-7_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031731150","9783031731167"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73116-7_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 October 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"}}]}}