{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:33:30Z","timestamp":1778081610494,"version":"3.51.4"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732225","type":"print"},{"value":"9783031732232","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T00:00:00Z","timestamp":1731024000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T00:00:00Z","timestamp":1731024000000},"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\/978-3-031-73223-2_6","type":"book-chapter","created":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T18:49:07Z","timestamp":1731005347000},"page":"87-103","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["CTRLorALTer: Conditional LoRAdapter for\u00a0Efficient 0-Shot Control and Altering of\u00a0T2I Models"],"prefix":"10.1007","author":[{"given":"Nick","family":"Stracke","sequence":"first","affiliation":[]},{"given":"Stefan Andreas","family":"Baumann","sequence":"additional","affiliation":[]},{"given":"Joshua","family":"Susskind","sequence":"additional","affiliation":[]},{"given":"Miguel Angel","family":"Bautista","sequence":"additional","affiliation":[]},{"given":"Bj\u00f6rn","family":"Ommer","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,8]]},"reference":[{"key":"6_CR1","unstructured":"https:\/\/huggingface.co\/lambdalabs\/sd-image-variations-diffusers"},{"key":"6_CR2","unstructured":"Balaji, Y., et\u00a0al.: eDiffi: text-to-image diffusion models with an ensemble of expert denoisers. arXiv preprint arXiv:2211.01324 (2022)"},{"key":"6_CR3","unstructured":"Byeon, M., Park, B., Kim, H., Lee, S., Baek, W., Kim, S.: COYO-700M: image-text pair dataset. https:\/\/github.com\/kakaobrain\/coyo-dataset (2022)"},{"key":"6_CR4","doi-asserted-by":"publisher","unstructured":"Canny, J.: A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. PAMI-8(6), 679\u2013698 (1986). https:\/\/doi.org\/10.1109\/TPAMI.1986.4767851","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2D pose estimation using part affinity fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7291\u20137299 (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"6_CR6","unstructured":"Cheng, J.: ResAdapter: domain consistent resolution adapter for diffusion models (2024)"},{"key":"6_CR7","unstructured":"Denis\u00a0Zavadski, J.F.F., Rother, C.: ControlNet-XS: designing an efficient and effective architecture for controlling text-to-image diffusion models (2023)"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Gandikota, R., Materzynska, J., Zhou, T., Torralba, A., Bau, D.: Concept sliders: lora adaptors for precise control in diffusion models (2023)","DOI":"10.1007\/978-3-031-73661-2_10"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Bras, R.L., Choi, Y.: CLIPscore: a reference-free evaluation metric for image captioning. arXiv preprint arXiv:2104.08718 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"6_CR11","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"6_CR12","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"6_CR13","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"6_CR14","unstructured":"Hu, E.J., et\u00a0al.: LoRA: low-rank adaptation of large language models. In: International Conference on Learning Representations (2021)"},{"key":"6_CR15","unstructured":"Huang, L., Chen, D., Liu, Y., Shen, Y., Zhao, D., Zhou, J.: Composer: creative and controllable image synthesis with composable conditions. arXiv preprint arXiv:2302.09778 (2023)"},{"key":"6_CR16","unstructured":"Ilharco, G., et al.: Openclip. https:\/\/github.com\/mlfoundations\/open_clip (2021)"},{"key":"6_CR17","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Mao, C., Pan, Y., Han, Z., Zhang, J.: SCEdit: efficient and controllable image diffusion generation via skip connection editing. arXiv preprint arXiv:2312.11392 (2023)","DOI":"10.1109\/CVPR52733.2024.00859"},{"key":"6_CR18","unstructured":"Kopiczko, D.J., Blankevoort, T., Asano, Y.M.: VeRa: vector-based random matrix adaptation (2024)"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: GLIGEN: open-set grounded text-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 22511\u201322521 (2023)","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"6_CR20","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) Computer Vision \u2013 ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V, pp. 740\u2013755. Springer International Publishing, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"6_CR21","unstructured":"Liu, S.Y., et al.: DoRA: weight-decomposed low-rank adaptation (2024)"},{"key":"6_CR22","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"6_CR23","unstructured":"Luo, S., et al.: LCM-LoRA: a universal stable-diffusion acceleration module. arXiv preprint arXiv:2311.05556 (2023)"},{"key":"6_CR24","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":"6_CR25","doi-asserted-by":"crossref","unstructured":"Park, T., Liu, M.Y., Wang, T.C., Zhu, J.Y.: Semantic image synthesis with spatially-adaptive normalization. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2332\u20132341. IEEE (2019)","DOI":"10.1109\/CVPR.2019.00244"},{"key":"6_CR26","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":"6_CR27","unstructured":"Pernias, P., Rampas, D., Richter, M.L., Pal, C., Aubreville, M.: W\u00fcrstchen: An efficient architecture for large-scale text-to-image diffusion models. In: The Twelfth International Conference on Learning Representations (2024). https:\/\/openreview.net\/forum?id=gU58d5QeGv"},{"key":"6_CR28","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis (2023)"},{"key":"6_CR29","unstructured":"Qin, C., et\u00a0al.: UniControl: a unified diffusion model for controllable visual generation in the wild. arXiv preprint arXiv:2305.11147 (2023)"},{"key":"6_CR30","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":"6_CR31","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)"},{"issue":"3","key":"6_CR32","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1109\/TPAMI.2020.3019967","volume":"44","author":"R Ranftl","year":"2020","unstructured":"Ranftl, R., Lasinger, K., Hafner, D., Schindler, K., Koltun, V.: Towards robust monocular depth estimation: mixing datasets for zero-shot cross-dataset transfer. IEEE Trans. Pattern Anal. Mach. Intell. 44(3), 1623\u20131637 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6_CR33","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":"6_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":"6_CR35","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":"6_CR36","unstructured":"Ryu, S.: Low-rank adaptation for fast text-to-image diffusion fine-tuning. https:\/\/github.com\/cloneofsimo\/lora"},{"key":"6_CR37","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":"6_CR38","doi-asserted-by":"crossref","unstructured":"Shah, V., et al.: ZipLoRA: any subject in any style by effectively merging LoRAs (2023)","DOI":"10.1007\/978-3-031-73232-4_24"},{"key":"6_CR39","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"6_CR40","unstructured":"Witteveen, S., Andrews, M.: Investigating prompt engineering in diffusion models. arXiv preprint arXiv:2211.15462 (2022)"},{"key":"6_CR41","doi-asserted-by":"crossref","unstructured":"Xie, S., Tu, Z.: Holistically-nested edge detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1395\u20131403 (2015)","DOI":"10.1109\/ICCV.2015.164"},{"key":"6_CR42","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":"6_CR43","doi-asserted-by":"crossref","unstructured":"Xu, X., Wang, Z., Zhang, E., Wang, K., Shi, H.: Versatile diffusion: text, images and variations all in one diffusion model. arXiv preprint arXiv:2211.08332 (2022)","DOI":"10.1109\/ICCV51070.2023.00713"},{"key":"6_CR44","unstructured":"Xue, Z., et al.: Raphael: text-to-image generation via large mixture of diffusion paths. arXiv preprint arXiv:2305.18295 (2023)"},{"key":"6_CR45","unstructured":"Ye, H., Zhang, J., Liu, S., Han, X., Yang, W.: IP-Adapter: text compatible image prompt adapter for text-to-image diffusion models (2023)"},{"key":"6_CR46","unstructured":"YEH, S.Y., Hsieh, Y.G., Gao, Z., Yang, B.B.W., Oh, G., Gong, Y.: Navigating text-to-image customization: from lyCORIS fine-tuning to model evaluation. In: The Twelfth International Conference on Learning Representations (2024). https:\/\/openreview.net\/forum?id=wfzXa8e783"},{"key":"6_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"6_CR48","unstructured":"Zhang, Q., et al.: AdaLoRA: adaptive budget allocation for parameter-efficient fine-tuning (2023)"},{"key":"6_CR49","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":"6_CR50","unstructured":"Zhao, S., et al.: Uni-ControlNet: all-in-one control to text-to-image diffusion models. In: Advances in Neural Information Processing Systems (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\/978-3-031-73223-2_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T23:22:06Z","timestamp":1733008926000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73223-2_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,8]]},"ISBN":["9783031732225","9783031732232"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73223-2_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,8]]},"assertion":[{"value":"8 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"}}]}}