{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T04:06:56Z","timestamp":1745294816155,"version":"3.40.4"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031901669","type":"print"},{"value":"9783031901676","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\/978-3-031-90167-6_7","type":"book-chapter","created":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T02:15:14Z","timestamp":1745288114000},"page":"94-110","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Search-Based Negative Prompt Optimisation for\u00a0Text-to-Image Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8733-7148","authenticated-orcid":false,"given":"Guillermo","family":"Iglesias","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8872-4876","authenticated-orcid":false,"given":"Mar","family":"Zamorano","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9146-442X","authenticated-orcid":false,"given":"Federica","family":"Sarro","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,4,20]]},"reference":[{"key":"7_CR1","unstructured":"AI, S.: Stable diffusion v2 (2022). https:\/\/huggingface.co\/stabilityai\/stable-diffusion-2. Accessed 18 Mar 2024"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"An, J., Ding, W., Lin, C.: Chatgpt: tackle the growing carbon footprint of generative AI, vol. 615, p. 586 (2023)","DOI":"10.1038\/d41586-023-00843-2"},{"key":"7_CR3","doi-asserted-by":"publisher","unstructured":"Berger, H., et al.: Stableyolo: optimizing image generation for large language models. In: Search-Based Software Engineering: 15th International Symposium, SSBSE 2023, San Francisco, CA, USA, 8 December 2023, Proceedings, pp. 133\u2013139. Springer, Heidelberg (2023). https:\/\/doi.org\/10.1007\/978-3-031-48796-5_10","DOI":"10.1007\/978-3-031-48796-5_10"},{"key":"7_CR4","unstructured":"Bird, S., Klein, E., Loper, E.: Natural Language Processing with Python: Analyzing Text with the Natural Language Toolkit. O\u2019Reilly Media, Inc., Newton (2009)"},{"key":"7_CR5","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Cer, D., et\u00a0al.: Universal sentence encoder for english. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 169\u2013174 (2018)","DOI":"10.18653\/v1\/D18-2029"},{"key":"7_CR7","unstructured":"Chen, B., Zhang, Z., Langren\u00e9, N., Zhu, S.: Unleashing the potential of prompt engineering in large language models: a comprehensive review. arXiv:2310.14735 (2023)"},{"key":"7_CR8","unstructured":"Chen, M., et\u00a0al.: Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374 (2021)"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Cohen, I., et al.: Pearson correlation coefficient. In: Noise Reduction in Speech Processing, pp.\u00a01\u20134 (2009)","DOI":"10.1007\/978-3-642-00296-0_5"},{"key":"7_CR10","unstructured":"Dayma, B.: Craiyon (2024). https:\/\/www.craiyon.com. Accessed 06 June 2024"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Ding, Z., Li, P., Yang, Q., Li, S.: Enhance image-to-image generation with llava prompt and negative prompt. arXiv preprint arXiv:2406.01956 (2024)","DOI":"10.1109\/ISPDS62779.2024.10667513"},{"key":"7_CR12","unstructured":"Dong, Z., Wei, P., Lin, L.: Dreamartist: towards controllable one-shot text-to-image generation via positive-negative prompt-tuning. arXiv preprint arXiv:2211.11337 (2022)"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Feng, Y., et al.: Promptmagician: interactive prompt engineering for text-to-image creation. IEEE Trans. Visualizat. Comput. Graph. (2023)","DOI":"10.1109\/TVCG.2023.3327168"},{"key":"7_CR14","unstructured":"Gao, A.K.: Vec2vec: a compact neural network approach for transforming text embeddings with high fidelity. arXiv preprint arXiv:2306.12689 (2023)"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"Gao, T., Fisch, A., Chen, D.: Making pre-trained language models better few-shot learners. arXiv preprint arXiv:2012.15723 (2020)","DOI":"10.18653\/v1\/2021.acl-long.295"},{"key":"7_CR16","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1007\/978-3-031-64573-0_7","volume-title":"Search-Based Software Engineering","author":"J Gong","year":"2024","unstructured":"Gong, J., Li, S., d\u2019Aloisio, G., Ding, Z., Ye, Y., Langdon, W.B., Sarro, F.: Greenstableyolo: optimizing inference time and image quality of text-to-image generation. In: Jahangirova, G., Khomh, F. (eds.) Search-Based Software Engineering, pp. 70\u201376. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-64573-0_7"},{"key":"7_CR17","unstructured":"Hao, Y., Chi, Z., Dong, L., Wei, F.: Optimizing prompts for text-to-image generation. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Haviv, A., Berant, J., Globerson, A.: Bertese: learning to speak to bert. arXiv preprint arXiv:2103.05327 (2021)","DOI":"10.18653\/v1\/2021.eacl-main.316"},{"key":"7_CR19","unstructured":"Holz, D.: Midjouney (2024). https:\/\/www.midjourney.com\/home. Accessed 06 June 2024"},{"key":"7_CR20","unstructured":"Imagen: Imagen (2024). https:\/\/imagen-ai.com\/es\/. Accessed 06 June 2024"},{"key":"7_CR21","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1162\/tacl_a_00324","volume":"8","author":"Z Jiang","year":"2020","unstructured":"Jiang, Z., Xu, F.F., Araki, J., Neubig, G.: How can we know what language models know? Trans. Assoc. Comput. Linguist. 8, 423\u2013438 (2020)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Kang, M., et al.: Scaling up gans for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10124\u201310134 (2023)","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"7_CR23","unstructured":"Lepikhin, D., et al.: Gshard: scaling giant models with conditional computation and automatic sharding. arXiv preprint arXiv:2006.16668 (2020)"},{"key":"7_CR24","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Li, W., Wen, S., Shi, K., Yang, Y., Huang, T.: Neural architecture search with a lightweight transformer for text-to-image synthesis. IEEE Trans. Netw. Sci. Eng. 9(3), 1567\u20131576 (2022)","DOI":"10.1109\/TNSE.2022.3147787"},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Li, W., Zhang, P., Zhang, L., Huang, Q., He, X., Lyu, S., Gao, J.: Object-driven text-to-image synthesis via adversarial training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12174\u201312182 (2019)","DOI":"10.1109\/CVPR.2019.01245"},{"key":"7_CR27","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":"7_CR28","doi-asserted-by":"crossref","unstructured":"Mao, Q., Lee, H.Y., Tseng, H.Y., Ma, S., Yang, M.H.: Mode seeking generative adversarial networks for diverse image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1429\u20131437 (2019)","DOI":"10.1109\/CVPR.2019.00152"},{"issue":"6654","key":"7_CR29","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1126\/science.adh2586","volume":"381","author":"S Noy","year":"2023","unstructured":"Noy, S., Zhang, W.: Experimental evidence on the productivity effects of generative artificial intelligence. Science 381(6654), 187\u2013192 (2023)","journal-title":"Science"},{"key":"7_CR30","unstructured":"Oikarinen, T., Weng, T.W.: Clip-dissect: automatic description of neuron representations in deep vision networks. arXiv preprint arXiv:2204.10965 (2022)"},{"key":"7_CR31","unstructured":"Oppenlaender, J.: A taxonomy of prompt modifiers for text-to-image generation. Behav. Inf. Technol., 1\u201314 (2023)"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Oppenlaender, J., Linder, R., Silvennoinen, J.: Prompting ai art: an investigation into the creative skill of prompt engineering. arXiv:2303.13534 (2023)","DOI":"10.1080\/10447318.2024.2431761"},{"key":"7_CR33","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents, vol. 1, no. 2, p. 3. arXiv:2204.06125 (2022)"},{"key":"7_CR34","doi-asserted-by":"crossref","unstructured":"Reimers, N.: Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084 (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"7_CR35","doi-asserted-by":"crossref","unstructured":"Reynolds, L., McDonell, K.: Prompt programming for large language models: beyond the few-shot paradigm. In: Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems, pp.\u00a01\u20137 (2021)","DOI":"10.1145\/3411763.3451760"},{"key":"7_CR36","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 (CVPR), pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"7_CR37","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., Chan, W., Saxena, S., Li, L., Whang, J., 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":"7_CR38","unstructured":"Salesforce: Blip (2024). https:\/\/huggingface.co\/Salesforce\/blip-image-captioning-large. Accessed 18 Mar 2024"},{"key":"7_CR39","doi-asserted-by":"crossref","unstructured":"Sarro, F.: Search-based software engineering in the era of modern software systems. In: Proceedings of IEEE International Requirements Engineering Conference (2023)","DOI":"10.1109\/RE57278.2023.00010"},{"key":"7_CR40","doi-asserted-by":"crossref","unstructured":"Sarro, F.: Automated optimisation of modern software system properties. In: Proceedings of the ACM\/SPEC International Conference on Performance Engineering (2023)","DOI":"10.1145\/3578244.3583739"},{"key":"7_CR41","unstructured":"SBERT: all-mpnet-base-v2 (2024). https:\/\/huggingface.co\/sentence-transformers\/all-mpnet-base-v2. Accessed 18 Mar 2024"},{"key":"7_CR42","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2022.102237","volume":"73","author":"S Shahriar","year":"2022","unstructured":"Shahriar, S.: Gan computers generate arts? a survey on visual arts, music, and literary text generation using generative adversarial network. Displays 73, 102237 (2022)","journal-title":"Displays"},{"key":"7_CR43","doi-asserted-by":"crossref","unstructured":"Shin, R., et al.: Constrained language models yield few-shot semantic parsers. arXiv preprint arXiv:2104.08768 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.608"},{"issue":"1","key":"7_CR44","doi-asserted-by":"publisher","first-page":"80","DOI":"10.54097\/ak59r592","volume":"9","author":"H Song","year":"2024","unstructured":"Song, H., Song, Y.: Target research based on blip model. Acad. J. Sci. Technol. 9(1), 80\u201386 (2024)","journal-title":"Acad. J. Sci. Technol."},{"key":"7_CR45","first-page":"16857","volume":"33","author":"K Song","year":"2020","unstructured":"Song, K., Tan, X., Qin, T., Lu, J., Liu, T.Y.: Mpnet: masked and permuted pre-training for language understanding. Adv. Neural. Inf. Process. Syst. 33, 16857\u201316867 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"7_CR46","unstructured":"Wang, J., et al.: Git: a generative image-to-text transformer for vision and language. arXiv preprint arXiv:2205.14100 (2022)"},{"key":"7_CR47","doi-asserted-by":"publisher","DOI":"10.1016\/j.metrad.2023.100047","volume":"1","author":"J Wang","year":"2023","unstructured":"Wang, J., Liu, Z., Zhao, L., Wu, Z., Ma, C., et al.: Review of large vision models and visual prompt engineering. Meta-Radiol. 1, 100047 (2023)","journal-title":"Meta-Radiol."},{"key":"7_CR48","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":"7_CR49","doi-asserted-by":"crossref","unstructured":"Wang, Z.J., Montoya, E., Munechika, D., Yang, H., Hoover, B., Chau, D.H.: DiffusionDB: a large-scale prompt gallery dataset for text-to-image generative models. arXiv:2210.14896 (2022)","DOI":"10.18653\/v1\/2023.acl-long.51"},{"key":"7_CR50","doi-asserted-by":"publisher","unstructured":"Weerasinghe, E., Kotuwegedara, T., Amarasena, R., Jayasinghe, P., Manathunga, K.: Dynamic conversational chatbot for assessing primary students. In: International Conference on Artificial Intelligence in Education, pp. 444\u2013448. Springer, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-11647-6_89","DOI":"10.1007\/978-3-031-11647-6_89"},{"key":"7_CR51","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: Dialogpt: large-scale generative pre-training for conversational response generation. arXiv preprint arXiv:1911.00536 (2019)","DOI":"10.18653\/v1\/2020.acl-demos.30"},{"key":"7_CR52","unstructured":"Zhou, Y., et al.: Large language models are human-level prompt engineers. arXiv preprint arXiv:2211.01910 (2022)"},{"key":"7_CR53","doi-asserted-by":"crossref","unstructured":"Zhu, M., Pan, P., Chen, W., Yang, Y.: Dm-gan: dynamic memory generative adversarial networks for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5802\u20135810 (2019)","DOI":"10.1109\/CVPR.2019.00595"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence in Music, Sound, Art and Design"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-90167-6_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T02:15:40Z","timestamp":1745288140000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-90167-6_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031901669","9783031901676"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-90167-6_7","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":"20 April 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"EvoMUSART","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Intelligence in Music, Sound, Art and Design (Part of EvoStar)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Trieste","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 April 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 April 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"evomusart2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.evostar.org\/2025\/evomusart\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}