{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,29]],"date-time":"2026-10-29T16:15:07Z","timestamp":1793290507327,"version":"4.5.0"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031736605","type":"print"},{"value":"9783031736612","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,10]],"date-time":"2024-11-10T00:00:00Z","timestamp":1731196800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,10]],"date-time":"2024-11-10T00:00:00Z","timestamp":1731196800000},"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\/978-3-031-73661-2_7","type":"book-chapter","created":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T11:09:35Z","timestamp":1731150575000},"page":"117-132","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["MoMA: Multimodal LLM Adapter for\u00a0Fast Personalized Image Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2439-4263","authenticated-orcid":false,"given":"Kunpeng","family":"Song","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8050-2235","authenticated-orcid":false,"given":"Yizhe","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2886-8915","authenticated-orcid":false,"given":"Bingchen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4814-839X","authenticated-orcid":false,"given":"Qing","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2761-4822","authenticated-orcid":false,"given":"Ahmed","family":"Elgammal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2411-3594","authenticated-orcid":false,"given":"Xiao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,10]]},"reference":[{"key":"7_CR1","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"7_CR2","unstructured":"Joshi, A.: Realistic vision v40 (2024). https:\/\/huggingface.co\/stablediffusionapi\/realistic-vision-v40. Accessed 06 Mar 2024"},{"key":"7_CR3","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. In: SIGGRAPH Asia 2023 Conference Papers, pp. 1\u201312 (2023)","DOI":"10.1145\/3610548.3618154"},{"key":"7_CR4","unstructured":"Balaji, Y., et\u00a0al.: eDiffi: text-to-image diffusion models with an ensemble of expert denoisers. arXiv preprint arXiv:2211.01324 (2022)"},{"key":"7_CR5","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":"7_CR6","unstructured":"Chen, L., et\u00a0al.: PhotoVerse: tuning-free image customization with text-to-image diffusion models. arXiv preprint arXiv:2309.05793 (2023)"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Chen, X., Huang, L., Liu, Y., Shen, Y., Zhao, D., Zhao, H.: AnyDoor: zero-shot object-level image customization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6593\u20136602 (2024)","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"7_CR8","unstructured":"Civitai: Civitai (2024). https:\/\/civitai.com\/. Accessed 06 Mar 2024"},{"key":"7_CR9","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":"7_CR10","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. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7323\u20137334 (2023)","DOI":"10.1109\/ICCV51070.2023.00673"},{"key":"7_CR11","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"7_CR12","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"7_CR13","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":"7_CR14","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4015\u20134026 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"7_CR15","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"},{"issue":"7","key":"7_CR16","doi-asserted-by":"publisher","first-page":"1956","DOI":"10.1007\/s11263-020-01316-z","volume":"128","author":"A Kuznetsova","year":"2020","unstructured":"Kuznetsova, A., et al.: The open images dataset v4: unified image classification, object detection, and visual relationship detection at scale. Int. J. Comput. Vis. 128(7), 1956\u20131981 (2020)","journal-title":"Int. J. Comput. Vis."},{"key":"7_CR17","unstructured":"Li, D., Li, J., Hoi, S.: Blip-diffusion: pre-trained subject representation for controllable text-to-image generation and editing. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"7_CR18","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"7_CR19","unstructured":"Nichol, A., et al.: Glide: towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)"},{"key":"7_CR20","unstructured":"OneRing: era-esthetic retro anime (2024). https:\/\/civitai.com\/models\/137781\/era-esthetic-retro-anime. Accessed 06 Mar 2024"},{"key":"7_CR21","unstructured":"Pan, X., Dong, L., Huang, S., Peng, Z., Chen, W., Wei, F.: Kosmos-G: generating images in context with multimodal large language models. arXiv preprint arXiv:2310.02992 (2023)"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4195\u20134205 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"7_CR23","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"7_CR24","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":"7_CR25","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125, 1(2), 3 (2022)"},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Razzhigaev, A., et al.: Kandinsky: an improved text-to-image synthesis with image prior and latent diffusion. arXiv preprint arXiv:2310.03502 (2023)","DOI":"10.18653\/v1\/2023.emnlp-demo.25"},{"key":"7_CR27","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":"7_CR28","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":"7_CR29","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. In: Advances in Neural Information Processing Systems, vol. 35, pp. 36479\u201336494 (2022)"},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Shi, J., Xiong, W., Lin, Z., Jung, H.J.: InstantBooth: personalized text-to-image generation without test-time finetuning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8543\u20138552 (2024)","DOI":"10.1109\/CVPR52733.2024.00816"},{"key":"7_CR31","unstructured":"Stable Unclip: Stable unclip (2024). https:\/\/huggingface.co\/docs\/diffusers\/en\/api\/pipelines\/stable_unclip. Accessed 06 Mar 2024"},{"key":"7_CR32","unstructured":"Wang, Q., Bai, X., Wang, H., Qin, Z., Chen, A.: Instantid: zero-shot identity-preserving generation in seconds. arXiv preprint arXiv:2401.07519 (2024)"},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Wang, T., et al.: Disco: disentangled control for realistic human dance generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9326\u20139336 (2024)","DOI":"10.1109\/CVPR52733.2024.00891"},{"key":"7_CR34","unstructured":"Wang, W., et\u00a0al.: CogVLM: visual expert for pretrained language models. arXiv preprint arXiv:2311.03079 (2023)"},{"key":"7_CR35","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. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15943\u201315953 (2023)","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"7_CR36","unstructured":"Xyn AI: Anything v4.0 (2024). https:\/\/huggingface.co\/xyn-ai\/anything-v4.0. Accessed 06 Mar 2024"},{"key":"7_CR37","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":"7_CR38","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (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\/978-3-031-73661-2_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T12:04:33Z","timestamp":1731153873000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73661-2_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,10]]},"ISBN":["9783031736605","9783031736612"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73661-2_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,10]]},"assertion":[{"value":"10 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"}}]}}