{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:59:44Z","timestamp":1778083184321,"version":"3.51.4"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729881","type":"print"},{"value":"9783031729898","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"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\/978-3-031-72989-8_21","type":"book-chapter","created":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T17:02:04Z","timestamp":1729875724000},"page":"365-381","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["TurboEdit: Instant Text-Based Image Editing"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9190-1717","authenticated-orcid":false,"given":"Zongze","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1233-1969","authenticated-orcid":false,"given":"Nicholas","family":"Kolkin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4769-0343","authenticated-orcid":false,"given":"Jonathan","family":"Brandt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2507-4674","authenticated-orcid":false,"given":"Richard","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6783-1795","authenticated-orcid":false,"given":"Eli","family":"Shechtman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,26]]},"reference":[{"key":"21_CR1","doi-asserted-by":"crossref","unstructured":"Alaluf, Y., Patashnik, O., Cohen-Or, D.: Restyle: a residual-based StyleGAN encoder via iterative refinement. In: Proc. ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00664"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Brack, M., et al.: Ledits++: limitless image editing using text-to-image models. arXiv preprint arXiv:2311.16711 (2023)","DOI":"10.1109\/CVPR52733.2024.00846"},{"key":"21_CR3","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":"21_CR4","doi-asserted-by":"crossref","unstructured":"Cao, M., Wang, X., Qi, Z., Shan, Y., Qie, X., Zheng, Y.: Masactrl: tuning-free mutual self-attention control for consistent image synthesis and editing. arXiv preprint arXiv:2304.08465 (2023)","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"21_CR5","unstructured":"Chiang, W.L., et al.: Vicuna: an open-source chatbot impressing gpt-4 with 90%* chatgpt quality, March 2023. https:\/\/lmsys.org\/blog\/2023-03-30-vicuna\/"},{"key":"21_CR6","unstructured":"Garibi, D., Patashnik, O., Voynov, A., Averbuch-Elor, H., Cohen-Or, D.: Renoise: real image inversion through iterative noising. arXiv preprint arXiv:2403.14602 (2024)"},{"key":"21_CR7","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. Advances in neural information processing systems 27 (2014)"},{"key":"21_CR8","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":"21_CR9","doi-asserted-by":"crossref","unstructured":"Huberman-Spiegelglas, I., Kulikov, V., Michaeli, T.: An edit friendly ddpm noise space: Inversion and manipulations. arXiv preprint arXiv:2304.06140 (2023)","DOI":"10.1109\/CVPR52733.2024.01185"},{"key":"21_CR10","unstructured":"Hui, M., et al.: Hq-edit: a high-quality dataset for instruction-based image editing. arXiv preprint arXiv:2404.09990 (2024)"},{"key":"21_CR11","unstructured":"Ju, X., Zeng, A., Bian, Y., Liu, S., Xu, Q.: Direct inversion: boosting diffusion-based editing with 3 lines of code. arXiv preprint arXiv:2310.01506 (2023)"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"Kawar, B., et al.: Imagic: text-based real image editing with diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6007\u20136017 (2023)","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Kim, G., Kwon, T., Ye, J.C.: Diffusionclip: text-guided diffusion models for robust image manipulation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2426\u20132435 (2022)","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"21_CR14","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"issue":"6","key":"21_CR15","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60(6), 84\u201390 (2017)","journal-title":"Commun. ACM"},{"key":"21_CR16","unstructured":"Lin, S., Wang, A., Yang, X.: Sdxl-lightning: progressive adversarial diffusion distillation. arXiv preprint arXiv:2402.13929 (2024)"},{"key":"21_CR17","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. Advances in neural information processing systems 36 (2024)"},{"key":"21_CR18","unstructured":"Luo, S., Tan, Y., Huang, L., Li, J., Zhao, H.: Latent consistency models: Synthesizing high-resolution images with few-step inference. arXiv preprint arXiv:2310.04378 (2023)"},{"key":"21_CR19","unstructured":"Meng, C., et al.: Sdedit: guided image synthesis and editing with stochastic differential equations. arXiv preprint arXiv:2108.01073 (2021)"},{"key":"21_CR20","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. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6038\u20136047 (2023)","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"21_CR21","first-page":"27730","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al.: Training language models to follow instructions with human feedback. Adv. Neural. Inf. Process. Syst. 35, 27730\u201327744 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Parmar, G., Kumar\u00a0Singh, K., Zhang, R., Li, Y., Lu, J., Zhu, J.Y.: Zero-shot image-to-image translation. In: ACM SIGGRAPH 2023 Conference Proceedings, pp. 1\u201311 (2023)","DOI":"10.1145\/3588432.3591513"},{"key":"21_CR23","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 (2023)"},{"key":"21_CR24","unstructured":"Podell, D., et al.: Sdxl: improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"21_CR25","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":"21_CR26","doi-asserted-by":"crossref","unstructured":"Richardson, E., et al.: Encoding in style: a StyleGan encoder for image-to-image translation. In: Proc. CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00232"},{"key":"21_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":"21_CR28","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":"21_CR29","doi-asserted-by":"crossref","unstructured":"Sauer, A., Lorenz, D., Blattmann, A., Rombach, R.: Adversarial diffusion distillation. arXiv preprint arXiv:2311.17042 (2023)","DOI":"10.1007\/978-3-031-73016-0_6"},{"key":"21_CR30","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"21_CR31","doi-asserted-by":"crossref","unstructured":"Tov, O., Alaluf, Y., Nitzan, Y., Patashnik, O., Cohen-Or, D.: Designing an encoder for stylegan image manipulation. arXiv preprint arXiv:2102.02766 (2021)","DOI":"10.1145\/3450626.3459838"},{"key":"21_CR32","unstructured":"Tsaban, L., Passos, A.: Ledits: Real image editing with ddpm inversion and semantic guidance. arXiv preprint arXiv:2307.00522 (2023)"},{"key":"21_CR33","unstructured":"Wu, C.H., De\u00a0la Torre, F.: Unifying diffusion models\u2019 latent space, with applications to cyclediffusion and guidance. arXiv preprint arXiv:2210.05559 (2022)"},{"key":"21_CR34","doi-asserted-by":"crossref","unstructured":"Wu, Q., Liu, Y., Zhao, H., Kale, A., Bui, T., Yu, T., Lin, Z., Zhang, Y., Chang, S.: Uncovering the disentanglement capability in text-to-image diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1900\u20131910 (2023)","DOI":"10.1109\/CVPR52729.2023.00189"},{"key":"21_CR35","unstructured":"Xu, S., Huang, Y., Pan, J., Ma, Z., Chai, J.: Inversion-free image editing with natural language. arXiv preprint arXiv:2312.04965 (2023)"},{"key":"21_CR36","doi-asserted-by":"crossref","unstructured":"Yin, T., Gharbi, M., Zhang, R., Shechtman, E., Durand, F., Freeman, W.T., Park, T.: One-step diffusion with distribution matching distillation. arXiv preprint arXiv:2311.18828 (2023)","DOI":"10.1109\/CVPR52733.2024.00632"},{"key":"21_CR37","unstructured":"Yu, H., Luo, H., Wang, F., Zhao, F.: Uncovering the text embedding in text-to-image diffusion models. arXiv preprint arXiv:2404.01154 (2024)"},{"key":"21_CR38","unstructured":"Zhang, K., Mo, L., Chen, W., Sun, H., Su, Y.: Magicbrush: A manually annotated dataset for instruction-guided image editing. Advances in Neural Information Processing Systems 36 (2024)"},{"key":"21_CR39","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":"21_CR40","unstructured":"Zhang, S., et\u00a0al.: Hive: Harnessing human feedback for instructional visual editing. arXiv preprint arXiv:2303.09618 (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\/978-3-031-72989-8_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T08:31:26Z","timestamp":1732955486000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72989-8_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,26]]},"ISBN":["9783031729881","9783031729898"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72989-8_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,26]]},"assertion":[{"value":"26 October 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"}}]}}