{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:31:52Z","timestamp":1777656712864,"version":"3.51.4"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730238","type":"print"},{"value":"9783031730245","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,24]],"date-time":"2024-11-24T00:00:00Z","timestamp":1732406400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,24]],"date-time":"2024-11-24T00:00:00Z","timestamp":1732406400000},"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\/978-3-031-73024-5_12","type":"book-chapter","created":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T16:39:54Z","timestamp":1732552794000},"page":"190-206","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Understanding the\u00a0Impact of\u00a0Negative Prompts: When and\u00a0How Do They Take Effect?"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2114-9340","authenticated-orcid":false,"given":"Yuanhao","family":"Ban","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0197-2361","authenticated-orcid":false,"given":"Ruochen","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5348-0632","authenticated-orcid":false,"given":"Tianyi","family":"Zhou","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3965-4215","authenticated-orcid":false,"given":"Minhao","family":"Cheng","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3915-5977","authenticated-orcid":false,"given":"Boqing","family":"Gong","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3520-9627","authenticated-orcid":false,"given":"Cho-Jui","family":"Hsieh","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,24]]},"reference":[{"key":"12_CR1","unstructured":"Achiam, J., et\u00a0al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Agrawal, H., et al.: Nocaps: novel object captioning at scale. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8948\u20138957 (2019)","DOI":"10.1109\/ICCV.2019.00904"},{"key":"12_CR3","unstructured":"Andrew: How to use negative prompts? (2023). https:\/\/stable-diffusion-art.com\/how-to-use-negative-prompts\/#Why_does_negative_prompt_become_more_important_in_v2"},{"key":"12_CR4","unstructured":"Armandpour, M., Zheng, H., Sadeghian, A., Sadeghian, A., Zhou, M.: Re-imagine the negative prompt algorithm: transform 2d diffusion into 3d, alleviate janus problem and beyond. arXiv preprint arXiv:2304.04968 (2023)"},{"key":"12_CR5","unstructured":"Balaji, Y., et\u00a0al.: ediffi: text-to-image diffusion models with an ensemble of expert denoisers. arXiv preprint arXiv:2211.01324 (2022)"},{"issue":"4","key":"12_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592116","volume":"42","author":"H Chefer","year":"2023","unstructured":"Chefer, H., Alaluf, Y., Vinker, Y., Wolf, L., Cohen-Or, D.: Attend-and-excite: attention-based semantic guidance for text-to-image diffusion models. ACM Trans. Graph. (TOG) 42(4), 1\u201310 (2023)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"9","key":"12_CR7","doi-asserted-by":"publisher","first-page":"1200","DOI":"10.1109\/TIP.2004.833105","volume":"13","author":"A Criminisi","year":"2004","unstructured":"Criminisi, A., P\u00e9rez, P., Toyama, K.: Region filling and object removal by exemplar-based image inpainting. IEEE Trans. Image Process. 13(9), 1200\u20131212 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"12_CR8","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat gans on image synthesis. Adv. Neural. Inf. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"12_CR9","unstructured":"Feng, W., et al.: Training-free structured diffusion guidance for compositional text-to-image synthesis. arXiv preprint arXiv:2212.05032 (2022)"},{"key":"12_CR10","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":"12_CR11","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"12_CR12","unstructured":"mukund kapoor: Negative prompts in stable diffusion: a beginner\u2019s guide (2023). https:\/\/www.greataiprompts.com\/imageprompt\/what-is-negative-prompt-in-stable-diffusion\/"},{"key":"12_CR13","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":"12_CR14","unstructured":"Lian, L., Li, B., Yala, A., Darrell, T.: Llm-grounded diffusion: enhancing prompt understanding of text-to-image diffusion models with large language models. arXiv preprint arXiv:2305.13655 (2023)"},{"key":"12_CR15","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":"12_CR16","doi-asserted-by":"crossref","unstructured":"Mahajan, S., Rahman, T., Yi, K.M., Sigal, L.: Prompting hard or hardly prompting: prompt inversion for text-to-image diffusion models. arXiv preprint arXiv:2312.12416 (2023)","DOI":"10.1109\/CVPR52733.2024.00650"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Ng, E.G., Pang, B., Sharma, P., Soricut, R.: Understanding guided image captioning performance across domains. arXiv preprint arXiv:2012.02339 (2020)","DOI":"10.18653\/v1\/2021.conll-1.14"},{"key":"12_CR18","unstructured":"Nichol, A., et al.: Glide: towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)"},{"key":"12_CR19","unstructured":"O\u2019Connor, R.: Stable diffusion 1 vs 2 - what you need to know (2023). https:\/\/www.assemblyai.com\/blog\/stable-diffusion-1-vs-2-what-you-need-to-know\/#negative-prompts"},{"key":"12_CR20","unstructured":"von Platen, P., et al.: Diffusers: state-of-the-art diffusion models (2022). https:\/\/github.com\/huggingface\/diffusers"},{"key":"12_CR21","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":"12_CR22","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":"12_CR23","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":"12_CR24","doi-asserted-by":"crossref","unstructured":"Tang, R., et al.: What the daam: interpreting stable diffusion using cross attention. arXiv preprint arXiv:2210.04885 (2022)","DOI":"10.18653\/v1\/2023.acl-long.310"},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Tumanyan, N., Geyer, M., Bagon, S., Dekel, T.: Plug-and-play diffusion features for text-driven image-to-image translation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1921\u20131930 (2023)","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"12_CR26","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Rohrbach, M., Donahue, J., Mooney, R., Darrell, T., Saenko, K.: Sequence to sequence-video to text. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4534\u20134542 (2015)","DOI":"10.1109\/ICCV.2015.515"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Wang, X., Wu, J., Chen, J., Li, L., Wang, Y.F., Wang, W.Y.: Vatex: a large-scale, high-quality multilingual dataset for video-and-language research. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4581\u20134591 (2019)","DOI":"10.1109\/ICCV.2019.00468"},{"key":"12_CR28","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 preprint arXiv:2210.14896 (2022)","DOI":"10.18653\/v1\/2023.acl-long.51"},{"key":"12_CR29","unstructured":"Woolf, M.: Stable diffusion 2.0 and the importance of negative prompts for good results (2023). https:\/\/minimaxir.com\/2022\/11\/stable-diffusion-negative-prompt\/"},{"key":"12_CR30","unstructured":"Yang, S., Zhang, L., Ma, L., Liu, Y., Fu, J., He, Y.: Magicremover: tuning-free text-guided image inpainting with diffusion models. arXiv preprint arXiv:2310.02848 (2023)"},{"key":"12_CR31","unstructured":"Yildirim, A.B., Baday, V., Erdem, E., Erdem, A., Dundar, A.: Inst-inpaint: instructing to remove objects with diffusion models. arXiv preprint arXiv:2304.03246 (2023)"},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"Yu, J., Lin, Z., Yang, J., Shen, X., Lu, X., Huang, T.S.: Generative image inpainting with contextual attention. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5505\u20135514 (2018)","DOI":"10.1109\/CVPR.2018.00577"},{"key":"12_CR33","doi-asserted-by":"crossref","unstructured":"Zhong, S., Huang, Z., Wen, W., Qin, J., Lin, L.: Sur-adapter: enhancing text-to-image pre-trained diffusion models with large language models. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 567\u2013578 (2023)","DOI":"10.1145\/3581783.3611863"},{"issue":"6","key":"12_CR34","doi-asserted-by":"publisher","first-page":"1452","DOI":"10.1109\/TPAMI.2017.2723009","volume":"40","author":"B Zhou","year":"2017","unstructured":"Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., Torralba, A.: Places: a 10 million image database for scene recognition. IEEE Trans. Pattern Anal. Mach. Intell. 40(6), 1452\u20131464 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"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\/978-3-031-73024-5_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T17:05:39Z","timestamp":1732554339000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73024-5_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,24]]},"ISBN":["9783031730238","9783031730245"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73024-5_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,24]]},"assertion":[{"value":"24 November 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"}}]}}