{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T16:36:33Z","timestamp":1785602193985,"version":"3.56.0"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T00:00:00Z","timestamp":1734912000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T00:00:00Z","timestamp":1734912000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022ZD0118700"],"award-info":[{"award-number":["2022ZD0118700"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1007\/s11263-024-02309-y","type":"journal-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T03:50:02Z","timestamp":1734925802000},"page":"3083-3104","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["AutoStory: Generating Diverse Storytelling Images with Minimal Human Efforts"],"prefix":"10.1007","volume":"133","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-4349-5532","authenticated-orcid":false,"given":"Wen","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Canyu","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhekai","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kecheng","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunhua","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,12,23]]},"reference":[{"key":"2309_CR1","unstructured":"Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F.\u00a0L., Almeida, D., Altenschmidt, J., Altman, S., & Anadkat, S., et\u00a0al. (2023). Gpt-4 technical report, arXiv preprint arXiv:2303.08774"},{"key":"2309_CR2","doi-asserted-by":"crossref","unstructured":"Ahn, D., Kim, D., Song, G., Kim, S.\u00a0H., Lee, H., Kang, D., & Choi, J. (2023). Story visualization by online text augmentation with context memory. In Proceedings of IEEE international conference on computer vision.","DOI":"10.1109\/ICCV51070.2023.00290"},{"key":"2309_CR3","unstructured":"Anil, R., Dai, A.\u00a0M., Firat, O., Johnson, M., Lepikhin, D., Passos, A., Shakeri, S., Taropa, E., Bailey, P., Chen, Z., et\u00a0al. (2023). Palm 2 technical report, arXiv preprint arXiv:2305.10403"},{"key":"2309_CR4","unstructured":"Blattmann, A., Dockhorn, T., Kulal S.,\u00a0Mendelevitch, D, Kilian, M., Lorenz, D., Levi, Y., English, Z., Voleti, V., Letts, A., et\u00a0al. (2023). Stable video diffusion: Scaling latent video diffusion models to large datasets, arXiv preprint arXiv:2311.15127"},{"key":"2309_CR5","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020). Language models are few-shot learners. In Advances in neural information processing systems."},{"key":"2309_CR6","doi-asserted-by":"crossref","unstructured":"Chefer, H., Alaluf, Y., Vinker, Y., Wolf, L., & Cohen-Or, D. (2023). Attend-and-excite: Attention-based semantic guidance for text-to-image diffusion models. In SIGGRAPH.","DOI":"10.1145\/3592116"},{"key":"2309_CR7","doi-asserted-by":"crossref","unstructured":"Chen, H., Han, R., Wu, T.-L., Nakayama, H., & Peng, N. (2022). Character-centric story visualization via visual planning and token alignment. In Proceedings on empirical methods in natural language processing (EMNLP).","DOI":"10.18653\/v1\/2022.emnlp-main.565"},{"key":"2309_CR8","unstructured":"Feng, W., Zhu, W., Fu, T.-J.,\u00a0Jampani, V., Akula, A., He, X., Basu, S., Wang, X.\u00a0E., & Wang, W.\u00a0Y. (2023). Layoutgpt: Compositional visual planning and generation with large language models. In Advances in neural information processing systems."},{"key":"2309_CR9","unstructured":"Gal, R.,\u00a0Alaluf, Y.,\u00a0Atzmon, Y., Patashnik, O., Bermano, A.\u00a0H., Chechik, G., & Cohen-Or, D. (2023). An image is worth one word: Personalizing text-to-image generation using textual inversion. In Proceedings of the international conference learning representations."},{"key":"2309_CR10","doi-asserted-by":"crossref","unstructured":"Gong, Y.,\u00a0Pang, Y.,\u00a0Cun, X.,\u00a0Xia, M.,\u00a0Chen, H.,\u00a0Wang, L.,\u00a0Zhang, Y.,\u00a0Wang, X.,\u00a0Shan, Y., &\u00a0Yang, Y. (2023). Talecrafter: Interactive story visualization with multiple characters. In SIGGRAPH.","DOI":"10.1145\/3610548.3618184"},{"key":"2309_CR11","doi-asserted-by":"crossref","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2020). Generative adversarial networks. Communications of the ACM, 139\u2013144.","DOI":"10.1145\/3422622"},{"key":"2309_CR12","unstructured":"Gu, Y.,.\u00a0Wang, X, Wu, J.\u00a0Z., Shi, Y., Chen, Y., Fan, Z., Xiao, W., Zhao, R., Chang, S., Wu, W., et\u00a0al. (2023). Mix-of-show: Decentralized low-rank adaptation for multi-concept customization of diffusion models. In Advances in neural information processing systems."},{"key":"2309_CR13","unstructured":"Hu, E.\u00a0J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., & Chen, W. (2022). LoRA: Low-rank adaptation of large language models. In Proceedings of the international conference on learning representations."},{"key":"2309_CR14","unstructured":"Jeong, H., Kwon, G., & Ye, J.\u00a0C. (2023). Zero-shot generation of coherent storybook from plain text story using diffusion models, arXiv preprint arXiv:2302.03900"},{"key":"2309_CR15","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.\u00a0C., Lo, W.-Y., et\u00a0al. (2023). Segment anything. In Proceedings of IEEE international conference on computer vision.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"2309_CR16","doi-asserted-by":"crossref","unstructured":"Kumari, N., Zhang, B., Zhang, R., Shechtman, E., & Zhu, J.-Y. (2023). Multi-concept customization of text-to-image diffusion. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"2309_CR17","doi-asserted-by":"crossref","unstructured":"Li, B. (2022). Word-level fine-grained story visualization. In Proceedings of the European conference on computer vision.","DOI":"10.1007\/978-3-031-20059-5_20"},{"key":"2309_CR18","doi-asserted-by":"crossref","unstructured":"Li, Y., Liu, H., Wu, Q., Mu, F., Yang, J., Gao, J., Li, C., & Lee, Y.\u00a0J. (2023). Gligen: Open-set grounded text-to-image generation. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"2309_CR19","doi-asserted-by":"crossref","unstructured":"Li, Y.,\u00a0Gan, Z.,\u00a0Shen, Y.,\u00a0Liu, J.,\u00a0Cheng, Y.,\u00a0Wu, Y.,\u00a0Carin, L.,\u00a0Carlson, D., & Gao, J. (2019). Storygan: A sequential conditional gan for story visualization. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2019.00649"},{"key":"2309_CR20","unstructured":"Lian, L., Li, B., Yala, A., & Darrell, T. (2023). Llm-grounded diffusion: Enhancing prompt understanding of text-to-image diffusion models with large language models. Transactions on Machine Learning Research."},{"key":"2309_CR21","doi-asserted-by":"crossref","unstructured":"Liang, H., Zhang, W., Li, W., Yu, J., & Xu, L. (2024). Intergen: Diffusion-based multi-human motion generation under complex interactions. International Journal of Computer Vision, 1\u201321.","DOI":"10.1007\/s11263-024-02042-6"},{"key":"2309_CR22","doi-asserted-by":"crossref","unstructured":"Liu, C., Wu, H., Zhong, Y., Zhang, X., & Xie, W. (2024a). Intelligent grimm-open-ended visual storytelling via latent diffusion models. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR52733.2024.00592"},{"key":"2309_CR23","unstructured":"Liu, M., Xu, C., Jin, H., Chen, L., Xu, Z., Su, H., et\u00a0al. (2023a). One-2-3-45: Any single image to 3d mesh in 45 seconds without per-shape optimization. In Proceedings of the advances in neural information processing systems."},{"key":"2309_CR24","doi-asserted-by":"crossref","unstructured":"Liu, R.,\u00a0Wu, R., Hoorick B.\u00a0V.,\u00a0Tokmakov, P., Zakharov, S., & Vondrick, C. (2023b). Zero-1-to-3: Zero-shot one image to 3d object. In Proceedings of the IEEE international conference on computer vision.","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"2309_CR25","doi-asserted-by":"crossref","unstructured":"Liu, S., Zeng, Z., Ren, T., Li, F., Zhang, H., Yang, J.,\u00a0Li, C., Yang, J., Su, H., Zhu, J., et\u00a0al. (2024b). Grounding dino: Marrying dino with grounded pre-training for open-set object detection. In Proceedings of the European conference on computer vision.","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"2309_CR26","unstructured":"Liu, Z., Feng, R., Zhu, K., Zhang, Y., Zheng, K., Liu, Y., Zhao, D.,\u00a0Zhou, J., & Cao, Y. (2023c). Cones: Concept neurons in diffusion models for customized generation. In Proceedings international conference on machine learning."},{"key":"2309_CR27","unstructured":"Liu, Z., Zhang, Y., Shen, Y., Zheng, K., Zhu, K., Feng, R., Liu, Y., Zhao, D., Zhou, J., & Cao, Y. (2023d). Cones 2: Customizable image synthesis with multiple subjects. In Advances in neural information processing systems."},{"key":"2309_CR28","doi-asserted-by":"crossref","unstructured":"Maharana, A., &\u00a0Bansal, M. (2021). Integrating visuospatial, linguistic and commonsense structure into story visualization. In Proceedings on empirical methods in natural language processing (EMNLP).","DOI":"10.18653\/v1\/2021.emnlp-main.543"},{"key":"2309_CR29","doi-asserted-by":"crossref","unstructured":"Maharana, A., Hannan, D., &\u00a0Bansal, M. (2021). Improving generation and evaluation of visual stories via semantic consistency. In North American chapter of the ACL","DOI":"10.18653\/v1\/2021.naacl-main.194"},{"key":"2309_CR30","doi-asserted-by":"crossref","unstructured":"Maharana, A.,\u00a0Hannan, D., &\u00a0Bansal M. (2022). Storydall-e: Adapting pretrained text-to-image transformers for story continuation. In Proceedings of the European conference on computer vision.","DOI":"10.1007\/978-3-031-19836-6_5"},{"key":"2309_CR31","doi-asserted-by":"crossref","unstructured":"Mou, C., Wang, X., Xie, L., Zhang, J., Qi, Z., Shan, Y., & Qie, X. (2024). 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.","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"2309_CR32","unstructured":"Pan, X., Qin, P., Li, Y., Xue, H., & Chen, W. (2022). Synthesizing coherent story with auto-regressive latent diffusion models. In IEEE Winter conference applied computer vision."},{"key":"2309_CR33","doi-asserted-by":"crossref","unstructured":"Phung, Q., Ge, S., & Huang, J.-B. (2024). Grounded text-to-image synthesis with attention refocusing. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR52733.2024.00758"},{"key":"2309_CR34","doi-asserted-by":"crossref","unstructured":"Rahman, T., Lee, H.-Y., Ren, J., Tulyakov, S.,\u00a0Mahajan, S., & Sigal, L. (2023). Make-a-story: Visual memory conditioned consistent story generation. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR52729.2023.00246"},{"key":"2309_CR35","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., & Chen, M. (2022). Hierarchical text-conditional image generation with clip latents, arXiv preprint arXiv:2204.06125"},{"key":"2309_CR36","unstructured":"Ramesh, A., Pavlov, M., Goh, G., Gray, S., Voss, C., Radford, A., Chen, M., & Sutskever, I. (2021). Zero-shot text-to-image generation. In Proceedings international conference on machine learning."},{"key":"2309_CR37","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2309_CR38","doi-asserted-by":"crossref","unstructured":"Ruiz, N.,\u00a0Li, Y.,\u00a0Jampani, V., Pritch, Y., Rubinstein, M., & Aberman, K. (2023). Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation. In Proceedings of the IEEE conference on computer vision and pattern Recognition.","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"2309_CR39","doi-asserted-by":"crossref","unstructured":"Saharia, C., Chan, W., Saxena, S., Li, L., Whang, J., Denton, E.\u00a0L., Ghasemipour, K., Gontijo\u00a0Lopes, R., Karagol\u00a0Ayan, B., & Salimans, T. et\u00a0al. (2022). Photorealistic text-to-image diffusion models with deep language understanding. InAdvances in neural information processing systems.","DOI":"10.1145\/3528233.3530757"},{"key":"2309_CR40","unstructured":"Schuhmann, C., Beaumont, R., Vencu, R., Gordon, C., Wightman, R., Cherti, M., Coombes, T., Katta, A., Mullis, C., Wortsman, M., et\u00a0al. (2022). Laion-5b: An open large-scale dataset for training next generation image-text models. In Advances in neural information processing systems."},{"key":"2309_CR41","doi-asserted-by":"crossref","unstructured":"Song, Y.-Z., Rui\u00a0Tam, Z., Chen, H.-J., Lu, H.-H., & Shuai, H.-H. (2020). Character-preserving coherent story visualization. In Proceedings of the European conference on computer vision.","DOI":"10.1007\/978-3-030-58520-4_2"},{"key":"2309_CR42","doi-asserted-by":"crossref","unstructured":"Su, Z., Liu, W., Yu, Z., Hu, D., Liao, Q., Tian, Q., Pietik\u00e4inen, M., & Liu, L. (2021). Pixel difference networks for efficient edge detection. In Proceedings of IEEE international conference on computer vision.","DOI":"10.1109\/ICCV48922.2021.00507"},{"key":"2309_CR43","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.\u00a0N.,\u00a0Kaiser, \u0141., & Polosukhin, I. (2017). Attention is all you need. In Advances in neural information processing systems."},{"key":"2309_CR44","doi-asserted-by":"crossref","unstructured":"Wang, J., Sun, K., Cheng, T., Jiang, B., Deng, C., Zhao, Y., Liu, D., Mu, Y., Tan, M., Wang, X., et al. (2020). Deep high-resolution representation learning for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence .","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"2309_CR45","unstructured":"Wang, W., Xie, k., Liu, Z., Chen, H., Cao, Y., Wang, X., & Shen, C. (2023). Zero-shot video editing using off-the-shelf image diffusion models, arXiv preprint arXiv:2303.17599"},{"key":"2309_CR46","doi-asserted-by":"crossref","unstructured":"Wu, J.\u00a0Z., Ge, Y., Wang, X.,\u00a0Lei, W., Gu, Y.,\u00a0Hsu, W., Shan, Y., Qie, X., & Shou, M.\u00a0Z. (2023). Tune-a-video: One-shot tuning of image diffusion models for text-to-video generation. In Proceedings of IEEE international conference on computer vision.","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"2309_CR47","doi-asserted-by":"crossref","unstructured":"Xiao, G., Yin, T., Freeman, W.\u00a0T., Durand, F., & Han, S. (2024). Fastcomposer: Tuning-free multi-subject image generation with localized attention. International Journal of Computer Vision, 1\u201320.","DOI":"10.1007\/s11263-024-02227-z"},{"key":"2309_CR48","doi-asserted-by":"crossref","unstructured":"Xie, J., Li, Y., Huang, Y., Liu, H., Zhang, W., Zheng, Y., & Shou, M.\u00a0Z. (2023). Boxdiff: Text-to-image synthesis with training-free box-constrained diffusion. In Proceedings of IEEE international conference on computer vision.","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"2309_CR49","unstructured":"Xu, X., Li, M., Tao, C., Shen, T., Cheng, R., Li, J., Xu, C.,\u00a0Tao, D., & Zhou, T. (2024). A survey on knowledge distillation of large language models, arXiv preprint arXiv:2402.13116"},{"key":"2309_CR50","doi-asserted-by":"crossref","unstructured":"Yang, B., Gu, S.,\u00a0Zhang, B., Zhang, T., Chen, X., Sun, X., Chen, D., & Wen, F. (2023). Paint by example: Exemplar-based image editing with diffusion models. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"2309_CR51","doi-asserted-by":"crossref","unstructured":"Zhang, L., & Agrawala, M. (2023). Adding conditional control to text-to-image diffusion models. In Proceedings of IEEE international conference on computer vision.","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"2309_CR52","doi-asserted-by":"crossref","unstructured":"Zhao, B., Yin, W., Meng, L., & Sigal, L. (2020). Layout2image: Image generation from layout. International Journal of Computer Vision, 2418\u20132435.","DOI":"10.1007\/s11263-020-01300-7"},{"key":"2309_CR53","unstructured":"Zhu, X., Li, J., Liu, Y., Ma, C., & Wang, W. (2023). A survey on model compression for large language models, arXiv preprint arXiv:2308.07633"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02309-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02309-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02309-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,10]],"date-time":"2025-05-10T06:53:00Z","timestamp":1746859980000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02309-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,23]]},"references-count":53,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["2309"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02309-y","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,23]]},"assertion":[{"value":"31 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 November 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 December 2024","order":3,"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"}}]}}