{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:33:27Z","timestamp":1778081607996,"version":"3.51.4"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031918377","type":"print"},{"value":"9783031918384","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-91838-4_4","type":"book-chapter","created":{"date-parts":[[2025,5,25]],"date-time":"2025-05-25T18:33:54Z","timestamp":1748198034000},"page":"54-70","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["IPAdapter-Instruct: Resolving Ambiguity in\u00a0Image-Based Conditioning Using Instruct Prompts"],"prefix":"10.1007","author":[{"given":"Ciara","family":"Rowles","sequence":"first","affiliation":[]},{"given":"Shimon","family":"Vainer","sequence":"additional","affiliation":[]},{"given":"Dante","family":"De Nigris","sequence":"additional","affiliation":[]},{"given":"Slava","family":"Elizarov","sequence":"additional","affiliation":[]},{"given":"Konstantin","family":"Kutsy","sequence":"additional","affiliation":[]},{"given":"Simon","family":"Donn\u00e9","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"4_CR1","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Ban, Y., Wang, R., Zhou, T., Cheng, M., Gong, B., Hsieh, C.J.: Understanding the impact of negative prompts: when and how do they take effect? arXiv preprint arXiv:2406.02965 (2024)","DOI":"10.1007\/978-3-031-73024-5_12"},{"key":"4_CR3","unstructured":"Beaumont, R.: Vit-h\/14 clip model (2023). https:\/\/huggingface.co\/laion\/CLIP-ViT-H-14-laion2B-s32B-b79K. Accessed 15 July 2024"},{"key":"4_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":"4_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-031-72764-1_1","volume-title":"Computer Vision \u2013 ECCV 2024: 18th European Conference, Milan, Italy, September 29\u2013October 4, 2024, Proceedings, Part XXXVI","author":"MV Conde","year":"2025","unstructured":"Conde, M.V., Geigle, G., Timofte, R.: InstructIR: high-quality image restoration following human instructions. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision \u2013 ECCV 2024: 18th European Conference, Milan, Italy, September 29\u2013October 4, 2024, Proceedings, Part XXXVI, pp. 1\u201321. Springer Nature Switzerland, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-72764-1_1"},{"key":"4_CR6","unstructured":"Esser, P., et\u00a0al.: Scaling rectified flow transformers for high-resolution image synthesis. In: Forty-first International Conference on Machine Learning (2024)"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Gokaslan, A., et al.: CommonCanvas: open diffusion models trained on creative-commons images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8250\u20138260 (2024)","DOI":"10.1109\/CVPR52733.2024.00788"},{"key":"4_CR8","unstructured":"Hao, Y., Chi, Z., Dong, L., Wei, F.: Optimizing prompts for text-to-image generation. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"4_CR9","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-Or, D.: Prompt-to-prompt image editing with cross attention control. In: Proceedings of the International Conference on Learning Representations (ICLR) (2023)"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Le\u00a0Bras, R., Choi, Y.: ClipScore: a reference-free evaluation metric for image captioning. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 7514\u20137528 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"4_CR11","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4_CR12","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. In: NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications (2021)"},{"key":"4_CR13","unstructured":"Hristoforu, E.: Midjourneyimages dataset (2024). https:\/\/huggingface.co\/datasets\/ehristoforu\/midjourney-images. Accessed 15 July 2024"},{"key":"4_CR14","unstructured":"Hu, E.J., et\u00a0al.: LoRA: low-rank adaptation of large language models. In: International Conference on Learning Representations (2022)"},{"key":"4_CR15","unstructured":"Huang, L., Chen, D., Liu, Y., Shen, Y., Zhao, D., Zhou, J.: Composer: creative and controllable image synthesis with composable conditions. In: International Conference on Machine Learning, pp. 13753\u201313773. PMLR (2023)"},{"key":"4_CR16","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.neucom.2022.01.029","volume":"479","author":"H Li","year":"2022","unstructured":"Li, H., et al.: SRDiff: single image super-resolution with diffusion probabilistic models. Neurocomputing 479, 47\u201359 (2022)","journal-title":"Neurocomputing"},{"key":"4_CR17","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: ControlNet++: improving conditional controls with efficient consistency feedback (2024). https:\/\/arxiv.org\/abs\/2404.07987","DOI":"10.1007\/978-3-031-72667-5_8"},{"key":"4_CR18","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":"4_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: Proceedings of International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.425"},{"key":"4_CR20","doi-asserted-by":"crossref","unstructured":"Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Timofte, R., Van\u00a0Gool, L.: Repaint: inpainting using denoising diffusion probabilistic models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11461\u201311471 (2022)","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"4_CR21","unstructured":"OpenAI: GPT-4o (2024). https:\/\/openai.com\/index\/hello-gpt-4o\/. Accessed 15 July 2024"},{"key":"4_CR22","unstructured":"Pan, J., et al.: JourneyDB: a benchmark for generative image understanding (2023)"},{"key":"4_CR23","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"4_CR24","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.061251(2), 3 (2022)"},{"key":"4_CR25","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":"4_CR26","unstructured":"Ruiz, N., Li, Y., Wadhwa, N., Pritch, Y., Rubinstein, M., Jacobs, D.E., Fruchter, S.: Magic insert: style-aware drag-and-drop (2024)"},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Saharia, C., et al.: Palette: image-to-image diffusion models. In: ACM SIGGRAPH 2022 Conference Proceedings, pp. 1\u201310 (2022)","DOI":"10.1145\/3528233.3530757"},{"key":"4_CR28","unstructured":"Saleh, B., Elgammal, A.: Large-scale classification of fine-art paintings: learning the right metric on the right feature. Int. J. Digit. Art History (2) (2016)"},{"key":"4_CR29","unstructured":"Saxena, S., Kar, A., Norouzi, M., Fleet, D.J.: Monocular depth estimation using diffusion models. arXiv preprint arXiv:2302.14816 (2023)"},{"key":"4_CR30","unstructured":"Schuhmann, C., et al.: LAION-5B: an open large-scale dataset for training next generation image-text models (2022). http:\/\/arxiv.org\/abs\/2210.08402v1"},{"key":"4_CR31","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: International Conference on Machine Learning, pp. 2256\u20132265. PMLR (2015)"},{"key":"4_CR32","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: International Conference on Learning Representations (2020)"},{"key":"4_CR33","unstructured":"https:\/\/huggingface.co\/h94: Pre-trained ipadapter+ weights for stable diffusion 1.5 (2024). https:\/\/huggingface.co\/h94\/IP-Adapter\/blob\/main\/models\/ip-adapter-plus_sd15.bin. Accessed 15 July 2024"},{"key":"4_CR34","unstructured":"https:\/\/huggingface.co\/h94: Pre-trained scribble controlnet weights for stable diffusion 1.5 (2024). https:\/\/huggingface.co\/lllyasviel\/sd-controlnet-scribble. Accessed 15 July 2024"},{"key":"4_CR35","unstructured":"https:\/\/huggingface.co\/lllyasviel: Pre-trained openpose controlnet weights for stable diffusion 1.5 (2024). https:\/\/huggingface.co\/lllyasviel\/control_v11p_sd15_openpose. Accessed 15 July 2024"},{"key":"4_CR36","unstructured":"Wang, H., Wang, Q., Bai, X., Qin, Z., Chen, A.: InstantStyle: free lunch towards style-preserving in text-to-image generation. arXiv preprint arXiv:2404.02733 (2024)"},{"key":"4_CR37","unstructured":"Witteveen, S., Andrews, M.: Investigating prompt engineering in diffusion models. arXiv preprint arXiv:2211.15462 (2022)"},{"key":"4_CR38","doi-asserted-by":"crossref","unstructured":"Xia, B., et al.: DiffIR: efficient diffusion model for image restoration. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13095\u201313105 (2023)","DOI":"10.1109\/ICCV51070.2023.01204"},{"key":"4_CR39","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":"4_CR40","doi-asserted-by":"crossref","unstructured":"Zamir, A.R., Sax, A., Shen, W., Guibas, L.J., Malik, J., Savarese, S.: Taskonomy: Disentangling task transfer learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3712\u20133722 (2018)","DOI":"10.1109\/CVPR.2018.00391"},{"key":"4_CR41","unstructured":"Zavadski, D., Feiden, J.F., Rother, C.: ControlNet-XS: designing an efficient and effective architecture for controlling text-to-image diffusion models. arXiv preprint arXiv:2312.06573 (2023)"},{"key":"4_CR42","doi-asserted-by":"crossref","unstructured":"Zhan, J., et al.: Prompt refinement with image pivot for text-to-image generation. arXiv preprint arXiv:2407.00247 (2024)","DOI":"10.18653\/v1\/2024.acl-long.53"},{"key":"4_CR43","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"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-91838-4_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,25]],"date-time":"2025-05-25T18:34:08Z","timestamp":1748198048000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91838-4_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031918377","9783031918384"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91838-4_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","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"}}]}}