{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T06:51:24Z","timestamp":1780987884992,"version":"3.54.1"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729690","type":"print"},{"value":"9783031729706","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T00:00:00Z","timestamp":1732320000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T00:00:00Z","timestamp":1732320000000},"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\/978-3-031-72970-6_2","type":"book-chapter","created":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T10:51:16Z","timestamp":1732272676000},"page":"21-37","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Text-Anchored Score Composition: Tackling Condition Misalignment in\u00a0Text-to-Image Diffusion Models"],"prefix":"10.1007","author":[{"given":"Luozhou","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guibao","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhang","family":"Ge","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangyong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yijun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingcong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,23]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Avrahami, O., Lischinski, D., Fried, O.: Blended diffusion for text-driven editing of natural images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18208\u201318218 (2022)","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"2_CR2","unstructured":"Bhunia, A.K., et al.: Person image synthesis via denoising diffusion model. arXiv preprint arXiv:2211.12500 (2022)"},{"key":"2_CR3","unstructured":"Brack, M., Friedrich, F., Hintersdorf, D., Struppek, L., Schramowski, P., Kersting, K.: Sega: instructing diffusion using semantic dimensions. arXiv preprint arXiv:2301.12247 (2023)"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: Instructpix2pix: learning to follow image editing instructions. arXiv preprint arXiv:2211.09800 (2022)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"2_CR5","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":"2_CR6","doi-asserted-by":"crossref","unstructured":"Chen, M., Laina, I., Vedaldi, A.: Training-free layout control with cross-attention guidance. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 5343\u20135353 (2024)","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Choi, J., Kim, S., Jeong, Y., Gwon, Y., Yoon, S.: ILVR: conditioning method for denoising diffusion probabilistic models. arXiv preprint arXiv:2108.02938 (2021)","DOI":"10.1109\/ICCV48922.2021.01410"},{"key":"2_CR8","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis (2021)"},{"key":"2_CR9","unstructured":"Feng, W., et al.: Training-free structured diffusion guidance for compositional text-to-image synthesis. arXiv preprint arXiv:2212.05032 (2022)"},{"key":"2_CR10","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":"2_CR11","doi-asserted-by":"crossref","unstructured":"Ge, S., Park, T., Zhu, J.Y., Huang, J.B.: Expressive text-to-image generation with rich text (2023)","DOI":"10.1109\/ICCV51070.2023.00694"},{"key":"2_CR12","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":"2_CR13","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":"2_CR14","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NIPS (2020)"},{"key":"2_CR15","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"2_CR16","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"2_CR17","unstructured":"Huang, Z., Wu, T., Jiang, Y., Chan, K.C., Liu, Z.: Reversion: diffusion-based relation inversion from images. arXiv preprint arXiv:2303.13495 (2023)"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Kim, Y., Lee, J., Kim, J.H., Ha, J.W., Zhu, J.Y.: Dense text-to-image generation with attention modulation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7701\u20137711 (2023)","DOI":"10.1109\/ICCV51070.2023.00708"},{"key":"2_CR19","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: ICML (2022)"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: GLIGEN: open-set grounded text-to-image generation. In: CVPR, pp. 22511\u201322521 (2023)","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Liang, Y., Yang, X., Lin, J., Li, H., Xu, X., Chen, Y.: Luciddreamer: towards high-fidelity text-to-3D generation via interval score matching (2023)","DOI":"10.1109\/CVPR52733.2024.00623"},{"key":"2_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","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.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"2_CR23","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1007\/978-3-031-19790-1_26","volume-title":"ECCV 2022","author":"N Liu","year":"2022","unstructured":"Liu, N., Li, S., Du, Y., Torralba, A., Tenenbaum, J.B.: Compositional visual generation with composable diffusion models. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13677, pp. 423\u2013439. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19790-1_26"},{"key":"2_CR24","unstructured":"Meng, C., et al.: SDEdit: guided image synthesis and editing with stochastic differential equations. In: International Conference on Learning Representations (2021)"},{"key":"2_CR25","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. arXiv preprint arXiv:2211.09794 (2022)","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"2_CR26","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":"2_CR27","unstructured":"Nichol, A., et al.: Glide: towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)"},{"key":"2_CR28","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. arXiv preprint arXiv:2302.03027 (2023)","DOI":"10.1145\/3588432.3591513"},{"key":"2_CR29","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: Dreamfusion: text-to-3D using 2D diffusion. arXiv preprint arXiv:2209.14988 (2022)"},{"key":"2_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":"2_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 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2_CR32","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":"2_CR33","unstructured":"Saharia, C., et\u00a0al.: Photorealistic text-to-image diffusion models with deep language understanding. arXiv preprint arXiv:2205.11487 (2022)"},{"key":"2_CR34","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: International Conference on Machine Learning. PMLR (2015)"},{"key":"2_CR35","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"2_CR36","unstructured":"Song, Y., Ermon, S.: Generative modeling by estimating gradients of the data distribution. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"2_CR37","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456 (2020)"},{"key":"2_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":"2_CR39","unstructured":"Wang, J., Yuan, H., Chen, D., Zhang, Y., Wang, X., Zhang, S.: Modelscope text-to-video technical report. arXiv preprint arXiv:2308.06571 (2023)"},{"key":"2_CR40","doi-asserted-by":"crossref","unstructured":"Wang, L., Yang, S., Liu, S., Chen, Y.: Not all steps are created equal: selective diffusion distillation for image manipulation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7472\u20137481 (2023)","DOI":"10.1109\/ICCV51070.2023.00687"},{"key":"2_CR41","doi-asserted-by":"crossref","unstructured":"Wang, X., Darrell, T., Rambhatla, S.S., Girdhar, R., Misra, I.: Instancediffusion: instance-level control for image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6232\u20136242 (2024)","DOI":"10.1109\/CVPR52733.2024.00596"},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"Xie, J., et al.: Boxdiff: text-to-image synthesis with training-free box-constrained diffusion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7452\u20137461 (2023)","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"2_CR43","unstructured":"Yang, S., Chen, Y., Wang, L., Liu, S., Chen, Y.: Denoising diffusion step-aware models. arXiv preprint arXiv:2310.03337 (2023)"},{"key":"2_CR44","doi-asserted-by":"crossref","unstructured":"Zeng, Y., et al.: Scenecomposer: any-level semantic image synthesis. arXiv preprint arXiv:2211.11742 (2022)","DOI":"10.1109\/CVPR52729.2023.02152"},{"key":"2_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, L., Agrawala, M.: Adding conditional control to text-to-image diffusion models. arXiv preprint arXiv:2302.05543 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"2_CR46","doi-asserted-by":"crossref","unstructured":"Zhao, M., Bao, F., Li, C., Zhu, J.: EGSDE: unpaired image-to-image translation via energy-guided stochastic differential equations. arXiv preprint arXiv:2207.06635 (2022)","DOI":"10.1109\/CVPR46437.2021.01615"},{"key":"2_CR47","unstructured":"Zhao, S., et al.: Uni-controlnet: all-in-one control to text-to-image diffusion models (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\/978-3-031-72970-6_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T11:09:13Z","timestamp":1732273753000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72970-6_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,23]]},"ISBN":["9783031729690","9783031729706"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72970-6_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,23]]},"assertion":[{"value":"23 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"}}]}}