{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T07:10:05Z","timestamp":1748589005940,"version":"3.41.0"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T00:00:00Z","timestamp":1747008000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T00:00:00Z","timestamp":1747008000000},"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":["SIViP"],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1007\/s11760-025-04133-4","type":"journal-article","created":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T06:14:56Z","timestamp":1747030496000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Em-t2i: ensemble AI model for text-to-image synthesis using meta AI and microsoft copilot"],"prefix":"10.1007","volume":"19","author":[{"given":"Shagufta","family":"Faryad","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ijaz Ali","family":"Shoukat","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ubaid","family":"Ullah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Javed Ali","family":"Khan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ayesha","family":"Faryad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad Arslan","family":"Rauf","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"4133_CR1","doi-asserted-by":"crossref","unstructured":"Allmendinger, S., Hemmer, P., Queisner, M., Sauer, I., M\u00fcller, L., Jakubik, J., V\u00f6ssing, M., K\u00fchl, N.: Navigating the synthetic realm: Harnessing diffusion-based models for laparoscopic text-to-image generation. In: AI for Health Equity and Fairness: Leveraging AI to Address Social Determinants of Health, pp. 31\u201346. Springer (2024)","DOI":"10.1007\/978-3-031-63592-2_4"},{"issue":"1","key":"4133_CR2","first-page":"53","volume":"2","author":"EVP Beyan","year":"2023","unstructured":"Beyan, E.V.P., Rossy, A.G.C., et al.: A review of AI image generator: influences, challenges, and future prospects for architectural field. J. Artific. Intell. Arch. 2(1), 53\u201365 (2023)","journal-title":"J. Artific. Intell. Arch."},{"key":"4133_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124908","volume":"256","author":"MF Ahamed","year":"2024","unstructured":"Ahamed, M.F., Nahiduzzaman, M., Islam, M.R., Naznine, M., Ayari, M.A., Khandakar, A., Haider, J.: Detection of various gastrointestinal tract diseases through a deep learning method with ensemble elm and explainable ai. Expert Syst. Appl. 256, 124908 (2024)","journal-title":"Expert Syst. Appl."},{"key":"4133_CR4","doi-asserted-by":"crossref","unstructured":"Radanliev, P.: Artificial intelligence: reflecting on the past and looking towards the next paradigm shift. J. Exp. Theoret. Artific. Intell. pp. 1\u201318 (2024)","DOI":"10.1080\/0952813X.2024.2323042"},{"key":"4133_CR5","doi-asserted-by":"crossref","unstructured":"Tibebu, H., Malik, A., De Silva, V.: Text to image synthesis using stacked conditional variational autoencoders and conditional generative adversarial networks. In: Science and Information Conference, pp. 560\u2013580. Springer (2022)","DOI":"10.1007\/978-3-031-10461-9_38"},{"key":"4133_CR6","unstructured":"Carolan, K., Fennelly, L., Smeaton, A. F.: A review of multi-modal large language and vision models, arXiv preprint arXiv:2404.01322 (2024)"},{"key":"4133_CR7","doi-asserted-by":"crossref","unstructured":"Alhabeeb, S.K., Al-Shargabi, A.A.: Text-to-image synthesis with generative models: Methods, datasets, performance metrics, challenges, and future direction. IEEE Access (2024)","DOI":"10.1109\/ACCESS.2024.3365043"},{"key":"4133_CR8","doi-asserted-by":"crossref","unstructured":"Ahamed, M. F., Islam, M. R., Nahiduzzaman, M., Karim, M. J., Ayari, M. A., Khandakar, A.: Automated detection of colorectal polyp utilizing deep learning methods with explainable AI, IEEE Access (2024)","DOI":"10.1109\/ACCESS.2024.3402818"},{"key":"4133_CR9","doi-asserted-by":"crossref","unstructured":"Park, D., Na, H., Choi, D.: Performance comparison and visualization of ai-generated-image detection methods. IEEE Access (2024)","DOI":"10.1109\/ACCESS.2024.3394250"},{"issue":"8","key":"4133_CR10","doi-asserted-by":"publisher","first-page":"23839","DOI":"10.1007\/s11042-023-16377-8","volume":"83","author":"B Jiang","year":"2024","unstructured":"Jiang, B., Zeng, W., Yang, C., Wang, R., Zhang, B.: De-gan: Text-to-image synthesis with dual and efficient fusion model. Multimed. Tools. Appl. 83(8), 23839\u201323852 (2024)","journal-title":"Multimed. Tools. Appl."},{"key":"4133_CR11","unstructured":"Sohn, K., Jiang, L., Barber, J., Lee, K., Ruiz, N., Krishnan, D., Chang, H., Li, Y., Essa, I., Rubinstein, M., et al.: Styledrop: Text-to-image synthesis of any style. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"4133_CR12","unstructured":"Sohn, K., Jiang, L., Barber, J., Lee, K., Ruiz, N., Krishnan, D., Chang, H., Li, Y., Essa, I., Rubinstein, M., et al.: Styledrop: Text-to-image synthesis of any style. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"4133_CR13","unstructured":"Maerten, A.-S., Soydaner, D.: From paintbrush to pixel: A review of deep neural networks in AI-generated art, arXiv preprint arXiv:2302.10913 (2023)"},{"key":"4133_CR14","unstructured":"Gozalo-Brizuela, R., Garrido-Merchan, E. C.: Chatgpt is not all you need. A state of the art review of large generative AI models, arXiv preprint arXiv:2301.04655 (2023)"},{"key":"4133_CR15","doi-asserted-by":"crossref","unstructured":"Tan, Y.X., Lee, C.P., Neo, M., Lim, K.M., Lim, J.Y., Alqahtani, A.: Recent advances in text-to-image synthesis: Approaches, datasets and future research prospects. IEEE Access (2023)","DOI":"10.1109\/ACCESS.2023.3306422"},{"issue":"5","key":"4133_CR16","doi-asserted-by":"publisher","first-page":"2685","DOI":"10.1007\/s11831-021-09672-w","volume":"29","author":"S Tyagi","year":"2022","unstructured":"Tyagi, S., Yadav, D.: A comprehensive review on image synthesis with adversarial networks: theory, literature, and applications. Arch. Comput. Methods Eng. 29(5), 2685\u20132705 (2022)","journal-title":"Arch. Comput. Methods Eng."},{"key":"4133_CR17","doi-asserted-by":"crossref","unstructured":"Fagadau, I. D., Mariani, L., Micucci, D., Riganelli, O.: Analyzing prompt influence on automated method generation: An empirical study with copilot. In: Proceedings of the 32nd IEEE\/ACM International Conference on Program Comprehension, pp. 24\u201334 (2024)","DOI":"10.1145\/3643916.3644409"},{"key":"4133_CR18","unstructured":"Barua, S.: Exploring autonomous agents through the lens of large language models: A review, arXiv preprint arXiv:2404.04442 (2024)"},{"key":"4133_CR19","unstructured":"Carolan, K., Fennelly, L., Smeaton, A.F.: A review of multi-modal large language and vision models, arXiv preprint arXiv:2404.01322 (2024)"},{"key":"4133_CR20","unstructured":"Oppenlaender, J.: A taxonomy of prompt modifiers for text-to-image generation. Behav. Inf. Technol. pp. 1\u201314 (2023)"},{"issue":"4","key":"4133_CR21","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1007\/s11633-022-1410-8","volume":"20","author":"X Wang","year":"2023","unstructured":"Wang, X., Chen, G., Qian, G., Gao, P., Wei, X.-Y., Wang, Y., Tian, Y., Gao, W.: Large-scale multi-modal pre-trained models: a comprehensive survey. Mach. Intell. Res. 20(4), 447\u2013482 (2023)","journal-title":"Mach. Intell. Res."},{"key":"4133_CR22","doi-asserted-by":"crossref","unstructured":"Wang, Z., Huang, Y., Song, D., Ma, L., Zhang, T.: Promptcharm: Text-to-image generation through multi-modal prompting and refinement. In; Proceedings of the CHI Conference on Human Factors in Computing Systems, pp. 1\u201321 (2024)","DOI":"10.1145\/3613904.3642803"},{"key":"4133_CR23","doi-asserted-by":"crossref","unstructured":"Feng, Y., Wang, X., Wong, K. K., Wang, S., Lu, Y., Zhu, M., Wang, B., Chen, W.: Promptmagician: Interactive prompt engineering for text-to-image creation. IEEE Trans. Vis. Comput. Graph. (2023)","DOI":"10.1109\/TVCG.2023.3327168"},{"issue":"3","key":"4133_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1108\/LHTN-03-2024-0037","volume":"41","author":"DE Frederick","year":"2024","unstructured":"Frederick, D.E.: Prompt engineering-a disruption in information seeking? Library Hi Tech. News 41(3), 1\u20135 (2024)","journal-title":"Library Hi Tech. News"},{"key":"4133_CR25","unstructured":"Hao, Y., Chi, Z., Dong, L., Wei, F.: Optimizing prompts for text-to-image generation. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"4133_CR26","doi-asserted-by":"crossref","unstructured":"Mahdavi Goloujeh, A., Sullivan, A., Magerko, B.: Is it AI or is it me? Understanding users\u2019prompt journey with text-to-image generative AI tools. In: Proceedings of the CHI Conference on Human Factors in Computing Systems, pp. 1\u201313 (2024)","DOI":"10.1145\/3613904.3642861"},{"key":"4133_CR27","unstructured":"Sahoo, P., Singh, A. K., Saha, S., Jain, V., Mondal, S., Chadha, A.: A systematic survey of prompt engineering in large language models: techniques and applications, arXiv preprint arXiv:2402.07927 (2024)"},{"key":"4133_CR28","doi-asserted-by":"crossref","unstructured":"Gao, A.: Prompt engineering for large language models, Available at SSRN 4504303 (2023)","DOI":"10.2139\/ssrn.4504303"},{"key":"4133_CR29","doi-asserted-by":"crossref","unstructured":"Ahamed,M. F., Islam,M. R., Nahiduzzaman,M., Chowdhury,M. E., Alqahtani,A., Murugappan,M.: Automated colorectal polyps detection from endoscopic images using multiresunet framework with attention guided segmentation. Human-Centric Intell. Syst. pp. 1\u201317 (2024)","DOI":"10.1007\/s44230-024-00067-1"},{"key":"4133_CR30","unstructured":"Wylder, J.: An Illustrated Guide to AI Prompt Mastery: for MidJourney, DALL-E. Deep Dream Generator, and More. Baen Books, NightCafe (2022)"},{"issue":"2","key":"4133_CR31","first-page":"192","volume":"23","author":"LR Al-Khazraji","year":"2023","unstructured":"Al-Khazraji, L.R., Abbas, A.R., Jamil, A.S.: A systematic review of deep dream. Iraqi J. Comput. Commun. Control Syst. Eng. 23(2), 192\u2013209 (2023)","journal-title":"Iraqi J. Comput. Commun. Control Syst. Eng."},{"key":"4133_CR32","doi-asserted-by":"crossref","unstructured":"Adetayo, A. J., Aborisade, M. O., Sanni, B. A.: Microsoft copilot and anthropic claude AI in education and library service, Library Hi Tech News (2024)","DOI":"10.1108\/LHTN-01-2024-0002"},{"key":"4133_CR33","doi-asserted-by":"crossref","unstructured":"Fagadau, I. D., Mariani, L., Micucci, D., Riganelli, O.: Analyzing prompt influence on automated method generation: An empirical study with copilot. In Proceedings of the 32nd IEEE\/ACM International Conference on Program Comprehension, pp. 24\u201334 (2024)","DOI":"10.1145\/3643916.3644409"},{"key":"4133_CR34","doi-asserted-by":"crossref","unstructured":"S\u00e1godi, Z., Siket, I., Ferenc, R.: Methodology for code synthesis evaluation of llms presented by a case study of chatgpt and copilot. IEEE Access (2024)","DOI":"10.1109\/ACCESS.2024.3403858"},{"key":"4133_CR35","doi-asserted-by":"crossref","unstructured":"Radanliev, P.: Artificial intelligence: reflecting on the past and looking towards the next paradigm shift. J. Exp. Theoret. Artific. Intell. pp. 1\u201318 (2024)","DOI":"10.1080\/0952813X.2024.2323042"},{"key":"4133_CR36","unstructured":"Carolan, K., Fennelly, L., Smeaton, A. F.: A review of multi-modal large language and vision models, arXiv preprint arXiv:2404.01322 (2024)"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-04133-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-025-04133-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-04133-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T06:41:22Z","timestamp":1748587282000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-025-04133-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,12]]},"references-count":36,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["4133"],"URL":"https:\/\/doi.org\/10.1007\/s11760-025-04133-4","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"type":"print","value":"1863-1703"},{"type":"electronic","value":"1863-1711"}],"subject":[],"published":{"date-parts":[[2025,5,12]]},"assertion":[{"value":"7 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 March 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 March 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 May 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors. Also, this work is original and has not been published elsewhere, nor is it currently under consideration for publication elsewhere.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}},{"value":"All the authors involved have agreed to participate in this submitted article.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}}],"article-number":"569"}}