{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T03:38:09Z","timestamp":1775533089789,"version":"3.50.1"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T00:00:00Z","timestamp":1775520000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T00:00:00Z","timestamp":1775520000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2022ZD0117000"],"award-info":[{"award-number":["2022ZD0117000"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62202426"],"award-info":[{"award-number":["62202426"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1007\/s11263-026-02801-7","type":"journal-article","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T02:42:41Z","timestamp":1775529761000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Rethinking Personalized T2I Diffusion Models from the Perspective of Redundancy"],"prefix":"10.1007","volume":"134","author":[{"given":"Xierui","family":"Wang","sequence":"first","affiliation":[]},{"given":"Bohan","family":"Lei","sequence":"additional","affiliation":[]},{"given":"Xiaoyin","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Fei","family":"Wu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2560-2430","authenticated-orcid":false,"given":"Min","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,4,7]]},"reference":[{"issue":"6","key":"2801_CR1","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1145\/3618322","volume":"42","author":"Y Alaluf","year":"2023","unstructured":"Alaluf, Y., Richardson, E., Metzer, G., & Cohen-Or, D. (2023). A neural space-time representation for text-to-image personalization. ACM TOG, 42(6), 243\u2013124310.","journal-title":"ACM TOG"},{"key":"2801_CR2","first-page":"3","volume":"2","author":"J Betker","year":"2023","unstructured":"Betker, J., Goh, G., Jing, L., Brooks, T., Wang, J., Li, L., Ouyang, L., Zhuang, J., Lee, J., Guo, Y., et al. (2023). Improving image generation with better captions. Computer Science., 2, 3.","journal-title":"Computer Science."},{"key":"2801_CR3","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., & Efros, A. A. (2023). Instructpix2pix: Learning to follow image editing instructions. In: CVPR, pp. 18392\u201318402.","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"2801_CR4","doi-asserted-by":"crossref","unstructured":"Baldrati, A., Morelli, D., Cartella, G., Cornia, M., Bertini, M., & Cucchiara, R. (2023). Multimodal garment designer: Human-centric latent diffusion models for fashion image editing. In: ICCV, pp. 23336\u201323345.","DOI":"10.1109\/ICCV51070.2023.02138"},{"key":"2801_CR5","doi-asserted-by":"crossref","unstructured":"Bao, F., Nie, S., Xue, K., Cao, Y., Li, C., Su, H., & Zhu, J. (2023). All are worth words: A vit backbone for diffusion models. In: CVPR, pp. 22669\u201322679.","DOI":"10.1109\/CVPR52729.2023.02171"},{"issue":"4","key":"2801_CR6","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1145\/3592116","volume":"42","author":"H Chefer","year":"2023","unstructured":"Chefer, H., Alaluf, Y., Vinker, Y., Wolf, L., & Cohen-Or, D. (2023). Attend-and-excite: Attention-based semantic guidance for text-to-image diffusion models. ACM TOG, 42(4), 148\u2013114810.","journal-title":"ACM TOG"},{"key":"2801_CR7","unstructured":"Chung, H. W., Hou, L., Longpre, S., Zoph, B., Tay, Y., Fedus, W., Li, Y., Wang, X., Dehghani, M., & Brahma, S., et al. (2022). Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416."},{"key":"2801_CR8","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021). Emerging properties in self-supervised vision transformers. In: ICCV, pp. 9630\u20139640.","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"2801_CR9","doi-asserted-by":"crossref","unstructured":"Cai, Y., Wei, Y., Ji, Z., Bai, J., Han, H., & Zuo, W. (2024). Decoupled textual embeddings for customized image generation. In: Wooldridge, M. J., Dy, J.G., Natarajan, S. (eds.) AAAI, pp. 909\u2013917.","DOI":"10.1609\/aaai.v38i2.27850"},{"key":"2801_CR10","doi-asserted-by":"crossref","unstructured":"Chen, J., Yu, J., Ge, C., Yao, L., Xie, E., Wang, Z., Kwok, J.T., Luo, P., Lu, H., & Li, Z. (2024). Pixart-$$\\alpha $$: Fast training of diffusion transformer for photorealistic text-to-image synthesis. In: ICLR.","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"2801_CR11","unstructured":"Chang, H., Zhang, H., Barber, J., Maschinot, A., Lezama, J., Jiang, L., Yang, M., Murphy, K.P., Freeman, W. T., Rubinstein, M., Li, Y., & Krishnan, D. (2023). Muse: Text-to-image generation via masked generative transformers. In: ICML. Proceedings of Machine Learning Research, (Vol. 202, pp. 4055\u20134075)."},{"key":"2801_CR12","unstructured":"Chen, H., Zhang, Y., Wu, S., Wang, X., Duan, X., Zhou, Y., & Zhu, W. (2023). Disenbooth: Identity-preserving disentangled tuning for subject-driven text-to-image generation. In: ICLR."},{"key":"2801_CR13","unstructured":"Diao, E., Wang, G., Zhang, J., Yang, Y., Ding, J., & Tarokh, V. (2023). Pruning deep neural networks from a sparsity perspective. In: ICLR."},{"key":"2801_CR14","unstructured":"Gal, R., Alaluf, Y., Atzmon, Y., Patashnik, O., Bermano, A. H., Chechik, G., & Cohen-Or, D. (2023). An image is worth one word: Personalizing text-to-image generation using textual inversion. In: ICLR."},{"issue":"11","key":"2801_CR15","doi-asserted-by":"publisher","first-page":"5372","DOI":"10.1007\/s11263-024-02137-0","volume":"132","author":"H He","year":"2024","unstructured":"He, H., Chen, X., Wang, C., Liu, J., Du, B., Tao, D., & Qiao, Y. (2024). Diff-font: Diffusion model for robust one-shot font generation. IJCV, 132(11), 5372\u20135386.","journal-title":"IJCV"},{"key":"2801_CR16","doi-asserted-by":"crossref","unstructured":"Han, L., Li, Y., Zhang, H., Milanfar, P., Metaxas, D. N., & Yang, F. (2023). Svdiff: Compact parameter space for diffusion fine-tuning. In: ICCV, pp. 7289\u20137300.","DOI":"10.1109\/ICCV51070.2023.00673"},{"key":"2801_CR17","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., & Cohen-Or, D. (2023). Prompt-to-prompt image editing with cross-attention control. In: ICLR."},{"key":"2801_CR18","unstructured":"Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., & Chen, W. (2022). Lora: Low-rank adaptation of large language models. In: ICLR."},{"key":"2801_CR19","doi-asserted-by":"crossref","unstructured":"Jin, J., Yu, Z., Shen, Y., Fu, Z., & Yang, J. (2025). Latexblend: Scaling multi-concept customized generation with latent textual blending. In: CVPR, pp. 23585\u201323594.","DOI":"10.1109\/CVPR52734.2025.02196"},{"key":"2801_CR20","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A. C., Lo, W., Doll\u00e1r, P., & Girshick, R. B. (2023). Segment anything. In: ICCV, pp. 3992\u20134003.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"2801_CR21","doi-asserted-by":"crossref","unstructured":"Kawar, B., Zada, S., Lang, O., Tov, O., Chang, H., Dekel, T., Mosseri, I., & Irani, M. (2023). Imagic: Text-based real image editing with diffusion models. In: CVPR, pp. 6007\u20136017.","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"2801_CR22","doi-asserted-by":"crossref","unstructured":"Kumari, N., Zhang, B., Wang, S. -Y., Shechtman, E., Zhang, R., & Zhu, J. -Y. (2023). Ablating concepts in text-to-image diffusion models. In: ICCV, pp. 22691\u201322702.","DOI":"10.1109\/ICCV51070.2023.02074"},{"key":"2801_CR23","doi-asserted-by":"crossref","unstructured":"Kumari, N., Zhang, B., Zhang, R., Shechtman, E., & Zhu, J. (2023). Multi-concept customization of text-to-image diffusion. In: CVPR, pp. 1931\u20131941.","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"2801_CR24","unstructured":"Liu, Z., Feng, R., Zhu, K., Zhang, Y., Zheng, K., Liu, Y., Zhao, D., Zhou, J., & Cao, Y. (2023). Cones: Concept neurons in diffusion models for customized generation. In: Krause, A., Brunskill, E., Cho, K., Engelhardt, B., Sabato, S., Scarlett, J. (eds.) ICML. Proceedings of Machine Learning Research, (Vol. 202, pp. 21548\u201321566)."},{"key":"2801_CR25","unstructured":"Li, D., Li, J., & Hoi, S. C. H. (2023). Blip-diffusion: Pre-trained subject representation for controllable text-to-image generation and editing. In: NeurIPS."},{"key":"2801_CR26","unstructured":"Liu, B., Zhu, Y., Song, K., & Elgammal, A. (2021). Towards faster and stabilized GAN training for high-fidelity few-shot image synthesis. In: ICLR."},{"key":"2801_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Y., Zhu, L., Yamada, M., & Yang, Y. (2020). Semantic correspondence as an optimal transport problem. In: CVPR, pp. 4462\u20134471.","DOI":"10.1109\/CVPR42600.2020.00452"},{"key":"2801_CR28","doi-asserted-by":"crossref","unstructured":"Mokady, R., Hertz, A., Aberman, K., Pritch, Y., & Cohen-Or, D. (2023). Null-text inversion for editing real images using guided diffusion models. In: CVPR, pp. 6038\u20136047.","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"2801_CR29","unstructured":"Meng, C., He, Y., Song, Y., Song, J., Wu, J., Zhu, J. -Y., & Ermon, S. (2022). Sdedit: Guided image synthesis and editing with stochastic differential equations. In: ICLR."},{"key":"2801_CR30","unstructured":"Podell, D., English, Z., Lacey, K., Blattmann, A., Dockhorn, T., M\u00fcller, J., Penna, J., & Rombach, R. (2024). SDXL: improving latent diffusion models for high-resolution image synthesis. In: ICLR."},{"key":"2801_CR31","unstructured":"Pernias, P., Rampas, D., Richter, M. L., Pal, C., & Aubreville, M. (2024). W\u00fcrstchen: An efficient architecture for large-scale text-to-image diffusion models. In: ICLR."},{"key":"2801_CR32","doi-asserted-by":"crossref","unstructured":"Peebles, W., & Xie, S. (2023). Scalable diffusion models with transformers. In: ICCV, pp. 4195\u20134205.","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"2801_CR33","unstructured":"Qiu, Z., Liu, W., Feng, H., Xue, Y., Feng, Y., Liu, Z., Zhang, D., Weller, A., & Sch\u00f6lkopf, B. (2023). Controlling text-to-image diffusion by orthogonal finetuning. In: NeurIPS."},{"key":"2801_CR34","doi-asserted-by":"crossref","unstructured":"Qiao, P., Shang, L., Liu, C., Sun, B., Ji, X., & Chen, J. (2024). Facechain-sude: Building derived class to inherit category attributes for one-shot subject-driven generation. In: CVPR, pp. 7215\u20137224.","DOI":"10.1109\/CVPR52733.2024.00689"},{"key":"2801_CR35","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-resolution image synthesis with latent diffusion models. In: CVPR, pp. 10674\u201310685.","DOI":"10.1109\/CVPR52688.2022.01042"},{"issue":"2","key":"2801_CR36","first-page":"3","volume":"1","author":"A Ramesh","year":"2022","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., & Chen, M. (2022). Hierarchical text-conditional image generation with clip latents., 1(2), 3. arXiv:2204.06125.","journal-title":"Hierarchical text-conditional image generation with clip latents."},{"key":"2801_CR37","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., & Sutskever, I. (2021). Learning transferable visual models from natural language supervision. In: ICML. Proceedings of Machine Learning Research, (Vol. 139, pp. 8748\u20138763)."},{"key":"2801_CR38","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., & Aberman, K. (2023). Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation. In: CVPR, pp. 22500\u201322510.","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"2801_CR39","unstructured":"Saharia, C., Chan, W., Saxena, S., Li, L., Whang, J., Denton, E. L., Ghasemipour, S. K. S., Lopes, R. G., Ayan, B. K., Salimans, T., Ho, J., Fleet, D. J., & Norouzi, M. (2022). Photorealistic text-to-image diffusion models with deep language understanding. In: NeurIPS."},{"issue":"4","key":"2801_CR40","doi-asserted-by":"publisher","first-page":"402","DOI":"10.2307\/2314570","volume":"74","author":"R Sinkhorn","year":"1967","unstructured":"Sinkhorn, R. (1967). Diagonal equivalence to matrices with prescribed row and column sums. The American Mathematical Monthly, 74(4), 402\u2013405.","journal-title":"The American Mathematical Monthly"},{"key":"2801_CR41","doi-asserted-by":"crossref","unstructured":"Shah, V., Ruiz, N., Cole, F., Lu, E., Lazebnik, S., Li, Y., & Jampani, V. (2024). Ziplora: Any subject in any style by effectively merging loras. In: ECCV. Lecture Notes in Computer Science, (Vol. 15059, pp. 422\u2013438).","DOI":"10.1007\/978-3-031-73232-4_24"},{"key":"2801_CR42","unstructured":"Sohl-Dickstein, J., Weiss, E. A., Maheswaranathan, N., & Ganguli, S. (2015). Deep unsupervised learning using nonequilibrium thermodynamics. In: ICML. JMLR Workshop and Conference Proceedings, (Vol. 37, pp. 2256\u20132265)."},{"key":"2801_CR43","doi-asserted-by":"crossref","unstructured":"Shi, J., Xiong, W., Lin, Z., & Jung, H. J. (2024). Instantbooth: Personalized text-to-image generation without test-time finetuning. In: CVPR, pp. 8543\u20138552.","DOI":"10.1109\/CVPR52733.2024.00816"},{"key":"2801_CR44","doi-asserted-by":"crossref","unstructured":"Tang, R., Liu, L., Pandey, A., Jiang, Z., Yang, G., Kumar, K., Stenetorp, P., Lin, J., & Ture, F. (2023). What the DAAM: interpreting stable diffusion using cross attention. In: ACL, pp. 5644\u20135659.","DOI":"10.18653\/v1\/2023.acl-long.310"},{"key":"2801_CR45","unstructured":"Tan, Z., Liu, S., Yang, X., Xue, Q., & Wang, X. (2025). Ominicontrol: Minimal and universal control for diffusion transformer. In: ICCV, pp. 14940\u201314950."},{"key":"2801_CR46","unstructured":"Tan, Z., Zhang, Y., Yang, J., & Yuan, Y. (2024). Contrastive learning is spectral clustering on similarity graph. In: ICLR."},{"key":"2801_CR47","unstructured":"Oord, A., Li, Y., & Vinyals, O. (2018). Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748."},{"key":"2801_CR48","unstructured":"Platen, P., Patil, S., Lozhkov, A., Cuenca, P., Lambert, N., Rasul, K., Davaadorj, M., & Wolf, T. (2022). Diffusers: State-of-the-art diffusion models. https:\/\/github.com\/huggingface\/diffusers."},{"key":"2801_CR49","unstructured":"Wang, Q., Bai, X., Wang, H., Qin, Z., & Chen, A. (2024). Instantid: Zero-shot identity-preserving generation in seconds. arXiv preprint arXiv:2401.07519."},{"key":"2801_CR50","unstructured":"Wu, S., Huang, M., Wu, W., Cheng, Y., Ding, F., & He, Q. (2025). Less-to-more generalization: Unlocking more controllability by in-context generation. arXiv preprint arXiv:2504.02160."},{"key":"2801_CR51","doi-asserted-by":"crossref","unstructured":"Wang, H., Lin, G., Molino, A. G., Wang, A., Feng, J., & Shen, Z. (2024). Maniclip: Multi-attribute face manipulation from text. IJCV,132(10), 4616\u20134632.","DOI":"10.1007\/s11263-024-02088-6"},{"issue":"12","key":"2801_CR52","doi-asserted-by":"publisher","first-page":"5929","DOI":"10.1007\/s11263-024-02168-7","volume":"132","author":"J Wang","year":"2024","unstructured":"Wang, J., Yue, Z., Zhou, S., Chan, K. C. K., & Loy, C. C. (2024). Exploiting diffusion prior for real-world image super-resolution. IJCV, 132(12), 5929\u20135949.","journal-title":"IJCV"},{"key":"2801_CR53","doi-asserted-by":"crossref","unstructured":"Wei, Y., Zhang, Y., Ji, Z., Bai, J., Zhang, L., & Zuo, W. (2023) ELITE: encoding visual concepts into textual embeddings for customized text-to-image generation. In: ICCV, pp. 15897\u201315907.","DOI":"10.1109\/ICCV51070.2023.01461"},{"issue":"3","key":"2801_CR54","doi-asserted-by":"publisher","first-page":"1175","DOI":"10.1007\/s11263-024-02227-z","volume":"133","author":"G Xiao","year":"2025","unstructured":"Xiao, G., Yin, T., Freeman, W. T., Durand, F., & Han, S. (2025). Fastcomposer: Tuning-free multi-subject image generation with localized attention. IJCV, 133(3), 1175\u20131194.","journal-title":"IJCV"},{"key":"2801_CR55","unstructured":"Yeh, S., Hsieh, Y., Gao, Z., Yang, B. B. W., Oh, G., & Gong, Y. (2024). Navigating text-to-image customization: From lycoris fine-tuning to model evaluation. In: ICLR."},{"key":"2801_CR56","unstructured":"Ye, H., Zhang, J., Liu, S., Han, X., & Yang, W. (2023). Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:2308.06721."},{"key":"2801_CR57","unstructured":"Zhang, Q., Chen, M., Bukharin, A., He, P., Cheng, Y., Chen, W., & Zhao, T. (2023). Adaptive budget allocation for parameter-efficient fine-tuning. In: ICLR."},{"key":"2801_CR58","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., & Agrawala, M. (2023). Adding conditional control to text-to-image diffusion models. In: ICCV, pp. 3813\u20133824.","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"2801_CR59","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Song, Y., Liu, J., Wang, R., Yu, J., Tang, H., Li, H., Tang, X., Hu, Y., & Pan, H., et al. (2024). Ssr-encoder: Encoding selective subject representation for subject-driven generation. In: CVPR, pp. 8069\u20138078.","DOI":"10.1109\/CVPR52733.2024.00771"},{"issue":"10","key":"2801_CR60","first-page":"4379","volume":"132","author":"K Zhang","year":"2024","unstructured":"Zhang, K., Sun, M., Sun, J., Zhang, K., Sun, Z., & Tan, T. (2024). Open-vocabulary text-driven human image generation. IJCV, 132(10), 4379\u20134397.","journal-title":"Open-vocabulary text-driven human image generation. IJCV"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02801-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-026-02801-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02801-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T02:42:56Z","timestamp":1775529776000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-026-02801-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,7]]},"references-count":60,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["2801"],"URL":"https:\/\/doi.org\/10.1007\/s11263-026-02801-7","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,7]]},"assertion":[{"value":"9 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Based on DreamBooth, the purpose of our work is to provide users with a more effective and flexible personalized text-to-image generation approach. Besides synthesizing specific subjects with high fidelity, ARBooth is capable of transferring the characteristics of one subject to another. This is extremely useful for creating new subjects with conditions. However, it might also be exploited to produce indistinguishable fake images and inexistent deceptive concepts, which remains to be resolved in future research.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}}],"article-number":"203"}}