{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T17:24:43Z","timestamp":1771953883697,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819755967","type":"print"},{"value":"9789819755974","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-5597-4_3","type":"book-chapter","created":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T09:10:06Z","timestamp":1722503406000},"page":"27-38","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Fine-Grained Image Editing Using ControlNet: Expanding Possibilities in Visual Manipulation"],"prefix":"10.1007","author":[{"given":"Longfei","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongbo","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yushuang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuwen","family":"Pan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaolin","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoxu","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linkai","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lishan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,2]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Saharia, C., Chan, W., Saxena, S., Li, L., Whang, J., Denton, E.L., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural Inf. Process. Syst. 35, 36479\u201336494 (2022)","DOI":"10.1145\/3528233.3530757"},{"key":"3_CR2","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.J.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"3_CR3","unstructured":"Yu, J., Xu, Y., Koh, J.Y., Luong, T., Baid, G., Wang, Z., et al.: Scaling autoregressive models for content-rich text-to-image generation. arXiv preprint arXiv:2206.10789 (2022)"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Liu, V., Chilton, L.B.: Design guidelines for prompt engineering text-to-image generative models. In: Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems, pp. 1\u201323 (2022)","DOI":"10.1145\/3491102.3501825"},{"key":"3_CR5","doi-asserted-by":"publisher","unstructured":"Bar-Tal, O., Ofri-Amar, D., Fridman, R., Kasten, Y., Dekel, T.: Text2live: Text-driven layered image and video editing. In: European conference on computer vision, pp. 707\u2013723. Springer, (2022). https:\/\/doi.org\/10.1007\/978-3-031-19784-0_41","DOI":"10.1007\/978-3-031-19784-0_41"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Bansal, A., Chu, H.M., Schwarzschild, A., Sengupta, S., Goldblum, M., Geiping, J., et al.: Universal guidance for diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 843\u2013852 (2023)","DOI":"10.1109\/CVPRW59228.2023.00091"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Saharia, C., Chan, W., Chang, H., Lee, C., Ho, J., Salimans, T., et al.: Palette: Image-to-image diffusion models. In: ACM SIGGRAPH 2022 Conference Proceedings, pp. 1\u201310 (2022)","DOI":"10.1145\/3528233.3530757"},{"key":"3_CR8","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-Or.: Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:2208.01626 (2022)"},{"key":"3_CR9","unstructured":"Epstein, D., Jabri, A., Poole, B., Efros, A., Holynski.: Diffusion self-guidance for controllable image generation. Adv. Neural Inf. Process. Syst. 36, 16222\u201316239 (2023)"},{"key":"3_CR10","unstructured":"Tang, L., Jia, M., Wang, Q., Phoo, C.P., Hariharan.: Emergent correspondence from image diffusion. Adv. Neural Inf. Process. Syst. 36, 1363\u20131389 (2023)"},{"key":"3_CR11","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":"3_CR12","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"},{"key":"3_CR13","unstructured":"Mousakhan, A., Brox, T., Tayyub.: Anomaly detection with conditioned denoising diffusion models. arXiv preprint arXiv:2305.15956 (2023)"},{"key":"3_CR14","unstructured":"Ding, M., Yang, Z., Hong, W., Zheng, W., Zhou, C., Yin, D., et al.: Cogview: Mastering text-to-image generation via transformers. Adv. Neural Inf. Process. Syst. 34, 19822\u201319835 (2021)"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Hinz, T., Heinrich, S., Wermter.: Semantic object accuracy for generative text-to-image synthesis. IEEE Trans. Pattern Anal. Mach. Intell. 44, 1552\u20131565 (2020)","DOI":"10.1109\/TPAMI.2020.3021209"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Avrahami, O., Fried, O., Lischinski.: Blended latent diffusion. ACM Trans. Graph. (TOG) 42, 1\u201311 (2023)","DOI":"10.1145\/3592450"},{"key":"3_CR17","unstructured":"Nichol, A., Dhariwal, P., Ramesh, A., Shyam, P., Mishkin, P., McGrew, B., et al.: Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Mou, C., Wang, X., Xie, L., Wu, Y., Zhang, J., Qi, Z., et al.: T2i-adapter: learning adapters to dig out more controllable ability for text-to-image diffusion models. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 4296\u20134304 (2024)","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Li, Y., Liu, H., Wu, Q., Mu, F., Yang, J., Gao, J., et al.: Gligen: Open-set grounded text-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22511\u201322521 (2023)","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"3_CR20","unstructured":"Song, J., Meng, C., Ermon.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Mao, J., Wang, X., Aizawa, K.: Guided image synthesis via initial image editing in diffusion model. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 5321\u20135329 (2023)","DOI":"10.1145\/3581783.3612191"},{"key":"3_CR22","unstructured":"Dhariwal, P., Nichol.: Diffusion models beat GANs on image synthesis. In: Adv. Neural Inf. Process. Syst. 34, 8780\u20138794 (2021)"},{"key":"3_CR23","unstructured":"Pantic, M., Valstar, M., Rademaker, R., Maat, L.: Web-based database for facial expression analysis. In: 2005 IEEE International Conference on Multimedia and Expo, pp. 5\u2212pp. IEEE, (2005)"},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Bhunia, A.K., Khan, S., Cholakkal, H., Anwer, R.M., Laaksonen, J., Shah, M., et al.: Person image synthesis via denoising diffusion model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5968\u20135976 (2023)","DOI":"10.1109\/CVPR52729.2023.00578"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Liu, K., Li, Q., Qiu.: PoseGAN: a pose-to-image translation framework for camera localization. ISPRS J. Photogrammetry Remote Sens. 166, 308\u2013315 (2020)","DOI":"10.1016\/j.isprsjprs.2020.06.010"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, J., Li, K., Lai, Y.-K., Yang, J.: PISE: Person image synthesis and editing with decoupled GAN. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7982\u20137990 (2021)","DOI":"10.1109\/CVPR46437.2021.00789"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-5597-4_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T13:14:01Z","timestamp":1732540441000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-5597-4_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819755967","9789819755974"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-5597-4_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"2 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tianjin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"5 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2024\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}