{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T14:48:48Z","timestamp":1762094928625,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Natural Science Foundation of China","award":["91948303-1, 61803375, 12002380, 62106278, 62101575, 61906210"],"award-info":[{"award-number":["91948303-1, 61803375, 12002380, 62106278, 62101575, 61906210"]}]},{"name":"Postgraduate Scientific Research Innovation Project of Hunan Province","award":["QL20210018"],"award-info":[{"award-number":["QL20210018"]}]},{"name":"National Key R&D Program of China","award":["2021ZD0140301"],"award-info":[{"award-number":["2021ZD0140301"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612588","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:26:54Z","timestamp":1698391614000},"page":"5143-5152","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Null-text Guidance in Diffusion Models is Secretly a Cartoon-style Creator"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0049-1802","authenticated-orcid":false,"given":"Jing","family":"Zhao","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2220-3880","authenticated-orcid":false,"given":"Heliang","family":"Zheng","sequence":"additional","affiliation":[{"name":"JD Explore Academy, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9002-1029","authenticated-orcid":false,"given":"Chaoyue","family":"Wang","sequence":"additional","affiliation":[{"name":"JD Explore Academy, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4238-8985","authenticated-orcid":false,"given":"Long","family":"Lan","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5778-9055","authenticated-orcid":false,"given":"Wanrong","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6997-0406","authenticated-orcid":false,"given":"Wenjing","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Fine-Tuning StyleGAN2 For Cartoon Face Generation. CoRR","author":"Back Jihye","year":"2021","unstructured":"Jihye Back. 2021. Fine-Tuning StyleGAN2 For Cartoon Face Generation. CoRR, Vol. abs\/2106.12445 (2021)."},{"key":"e_1_3_2_1_2_1","volume-title":"SAR-to-EO Image Translation with Multi-Conditional Adversarial Networks. CoRR","author":"Cabrera Armando","year":"2022","unstructured":"Armando Cabrera, Miriam Cha, Prafull Sharma, and Michael Newey. 2022. SAR-to-EO Image Translation with Multi-Conditional Adversarial Networks. CoRR, Vol. abs\/2207.13184 (2022)."},{"key":"e_1_3_2_1_3_1","volume-title":"ISICA 2019","author":"Chen Jie","year":"2019","unstructured":"Jie Chen, Gang Liu, and Xin Chen. 2019. AnimeGAN: A Novel Lightweight GAN for Photo Animation. In Artificial Intelligence Algorithms and Applications - 11th International Symposium, ISICA 2019, Guangzhou, China, November 16-17, 2019, Revised Selected Papers (Communications in Computer and Information Science, Vol. 1205), Kangshun Li, Wei Li, Hui Wang, and Yong Liu (Eds.). Springer, 242--256."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2021.3074073"},{"key":"e_1_3_2_1_5_1","volume-title":"CartoonGAN: Generative Adversarial Networks for Photo Cartoonization. In 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018","author":"Chen Yang","year":"2018","unstructured":"Yang Chen, Yu-Kun Lai, and Yong-Jin Liu. 2018. CartoonGAN: Generative Adversarial Networks for Photo Cartoonization. In 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018. Computer Vision Foundation \/ IEEE Computer Society, 9465--9474."},{"key":"e_1_3_2_1_6_1","volume-title":"Diffusion Models Beat GANs on Image Synthesis. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021","author":"Dhariwal Prafulla","year":"2021","unstructured":"Prafulla Dhariwal and Alexander Quinn Nichol. 2021. Diffusion Models Beat GANs on Image Synthesis. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual, Marc'Aurelio Ranzato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, and Jennifer Wortman Vaughan (Eds.). 8780--8794."},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings, Part XV (Lecture Notes in Computer Science","volume":"106","author":"Gafni Oran","year":"2022","unstructured":"Oran Gafni, Adam Polyak, Oron Ashual, Shelly Sheynin, Devi Parikh, and Yaniv Taigman. 2022. Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors. In Computer Vision - ECCV 2022 - 17th European Conference, Tel Aviv, Israel, October 23--27, 2022, Proceedings, Part XV (Lecture Notes in Computer Science, Vol. 13675), Shai Avidan, Gabriel J. Brostow, Moustapha Ciss\u00e9, Giovanni Maria Farinella, and Tal Hassner (Eds.). Springer, 89--106."},{"key":"e_1_3_2_1_8_1","volume-title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion. CoRR","author":"Gal Rinon","year":"2022","unstructured":"Rinon Gal, Yuval Alaluf, Yuval Atzmon, Or Patashnik, Amit H. Bermano, Gal Chechik, and Daniel Cohen-Or. 2022. An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion. CoRR, Vol. abs\/2208.01618 (2022)."},{"key":"e_1_3_2_1_9_1","volume-title":"Generative Adversarial Nets. In Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014","author":"Goodfellow Ian J.","year":"2014","unstructured":"Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron C. Courville, and Yoshua Bengio. 2014. Generative Adversarial Nets. In Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, December 8-13 2014, Montreal, Quebec, Canada, Zoubin Ghahramani, Max Welling, Corinna Cortes, Neil D. Lawrence, and Kilian Q. Weinberger (Eds.). 2672--2680."},{"key":"e_1_3_2_1_10_1","volume-title":"Prompt-to-Prompt Image Editing with Cross Attention Control. CoRR","author":"Hertz Amir","year":"2022","unstructured":"Amir Hertz, Ron Mokady, Jay Tenenbaum, Kfir Aberman, Yael Pritch, and Daniel Cohen-Or. 2022. Prompt-to-Prompt Image Editing with Cross Attention Control. CoRR, Vol. abs\/2208.01626 (2022)."},{"key":"e_1_3_2_1_11_1","volume-title":"Imagen Video: High Definition Video Generation with Diffusion Models. CoRR","author":"Ho Jonathan","year":"2022","unstructured":"Jonathan Ho, William Chan, Chitwan Saharia, Jay Whang, Ruiqi Gao, Alexey A. Gritsenko, Diederik P. Kingma, Ben Poole, Mohammad Norouzi, David J. Fleet, and Tim Salimans. 2022. Imagen Video: High Definition Video Generation with Diffusion Models. CoRR, Vol. abs\/2210.02303 (2022)."},{"key":"e_1_3_2_1_12_1","volume-title":"Denoising Diffusion Probabilistic Models. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising Diffusion Probabilistic Models. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, Hugo Larochelle, Marc'Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.)."},{"key":"e_1_3_2_1_13_1","volume-title":"Classifier-Free Diffusion Guidance. CoRR","author":"Ho Jonathan","year":"2022","unstructured":"Jonathan Ho and Tim Salimans. 2022. Classifier-Free Diffusion Guidance. CoRR, Vol. abs\/2207.12598 (2022)."},{"key":"e_1_3_2_1_14_1","volume-title":"Amsterdam, The Netherlands","volume":"711","author":"Johnson Justin","year":"2016","unstructured":"Justin Johnson, Alexandre Alahi, and Li Fei-Fei. 2016. Perceptual Losses for Real-Time Style Transfer and Super-Resolution. In Computer Vision - ECCV 2016 - 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part II (Lecture Notes in Computer Science, Vol. 9906), Bastian Leibe, Jiri Matas, Nicu Sebe, and Max Welling (Eds.). Springer, 694--711."},{"key":"e_1_3_2_1_15_1","volume-title":"Imagic: Text-Based Real Image Editing with Diffusion Models. CoRR","author":"Kawar Bahjat","year":"2022","unstructured":"Bahjat Kawar, Shiran Zada, Oran Lang, Omer Tov, Huiwen Chang, Tali Dekel, Inbar Mosseri, and Michal Irani. 2022. Imagic: Text-Based Real Image Editing with Diffusion Models. CoRR , Vol. abs\/2210.09276 (2022)."},{"key":"e_1_3_2_1_16_1","volume-title":"3ddesigner: Towards photorealistic 3d object generation and editing with text-guided diffusion models. arXiv preprint arXiv:2211.14108","author":"Li Gang","year":"2022","unstructured":"Gang Li, Heliang Zheng, Chaoyue Wang, Chang Li, Changwen Zheng, and Dacheng Tao. 2022. 3ddesigner: Towards photorealistic 3d object generation and editing with text-guided diffusion models. arXiv preprint arXiv:2211.14108 (2022)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3056196"},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021","volume":"8171","author":"Nichol Alexander Quinn","year":"2021","unstructured":"Alexander Quinn Nichol and Prafulla Dhariwal. 2021. Improved Denoising Diffusion Probabilistic Models. In Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 8162--8171."},{"key":"e_1_3_2_1_20_1","volume-title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models. In International Conference on Machine Learning, ICML 2022","volume":"16804","author":"Nichol Alexander Quinn","year":"2022","unstructured":"Alexander Quinn Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob McGrew, Ilya Sutskever, and Mark Chen. 2022. GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models. In International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA (Proceedings of Machine Learning Research, Vol. 162), Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesv\u00e1 ri, Gang Niu, and Sivan Sabato (Eds.). PMLR, 16784--16804."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2962579"},{"key":"e_1_3_2_1_23_1","volume-title":"High-Resolution Image Synthesis with Latent Diffusion Models. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022","author":"Rombach Robin","year":"2022","unstructured":"Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Bj\u00f6 rn Ommer. 2022. High-Resolution Image Synthesis with Latent Diffusion Models. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022. IEEE, 10674--10685."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_2_1_25_1","volume-title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation. CoRR","author":"Ruiz Nataniel","year":"2022","unstructured":"Nataniel Ruiz, Yuanzhen Li, Varun Jampani, Yael Pritch, Michael Rubinstein, and Kfir Aberman. 2022. DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation. CoRR, Vol. abs\/2208.12242 (2022)."},{"key":"e_1_3_2_1_26_1","volume-title":"Burcu Karagol Ayan, S. Sara Mahdavi, Rapha Gontijo Lopes, Tim Salimans, Jonathan Ho, David J. Fleet, and Mohammad Norouzi.","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily Denton, Seyed Kamyar Seyed Ghasemipour, Burcu Karagol Ayan, S. Sara Mahdavi, Rapha Gontijo Lopes, Tim Salimans, Jonathan Ho, David J. Fleet, and Mohammad Norouzi. 2022. Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding. CoRR, Vol. abs\/2205.11487 (2022)."},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings, Part VIII (Lecture Notes in Computer Science","volume":"731","author":"Sanakoyeu Artsiom","year":"2018","unstructured":"Artsiom Sanakoyeu, Dmytro Kotovenko, Sabine Lang, and Bj\u00f6 rn Ommer. 2018. A Style-Aware Content Loss for Real-Time HD Style Transfer. In Computer Vision - ECCV 2018 - 15th European Conference, Munich, Germany, September 8--14, 2018, Proceedings, Part VIII (Lecture Notes in Computer Science, Vol. 11212), Vittorio Ferrari, Martial Hebert, Cristian Sminchisescu, and Yair Weiss (Eds.). Springer, 715--731."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2206.00386"},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France, 6-11 July 2015 (JMLR Workshop and Conference Proceedings","volume":"2265","author":"Sohl-Dickstein Jascha","year":"2015","unstructured":"Jascha Sohl-Dickstein, Eric A. Weiss, Niru Maheswaranathan, and Surya Ganguli. 2015. Deep Unsupervised Learning using Nonequilibrium Thermodynamics. In Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France, 6-11 July 2015 (JMLR Workshop and Conference Proceedings, Vol. 37), Francis R. Bach and David M. Blei (Eds.). JMLR.org, 2256--2265."},{"key":"e_1_3_2_1_30_1","volume-title":"Denoising Diffusion Implicit Models. In 9th International Conference on Learning Representations, ICLR 2021","author":"Song Jiaming","year":"2021","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2021a. Denoising Diffusion Implicit Models. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net."},{"key":"e_1_3_2_1_31_1","volume-title":"Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019","author":"Song Yang","year":"2019","unstructured":"Yang Song and Stefano Ermon. 2019. Generative Modeling by Estimating Gradients of the Data Distribution. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada, Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d'Alch\u00e9-Buc, Emily B. Fox, and Roman Garnett (Eds.). 11895--11907."},{"key":"e_1_3_2_1_32_1","volume-title":"9th International Conference on Learning Representations, ICLR 2021","author":"Song Yang","year":"2021","unstructured":"Yang Song, Jascha Sohl-Dickstein, Diederik P. Kingma, Abhishek Kumar, Stefano Ermon, and Ben Poole. 2021b. Score-Based Generative Modeling through Stochastic Differential Equations. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net."},{"key":"e_1_3_2_1_33_1","volume-title":"Bermano","author":"Tevet Guy","year":"2022","unstructured":"Guy Tevet, Sigal Raab, Brian Gordon, Yonatan Shafir, Daniel Cohen-Or, and Amit H. Bermano. 2022. Human Motion Diffusion Model. CoRR, Vol. abs\/2209.14916 (2022)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00811"},{"key":"e_1_3_2_1_35_1","volume-title":"The Tenth International Conference on Learning Representations, ICLR 2022","author":"Watson Daniel","year":"2022","unstructured":"Daniel Watson, William Chan, Jonathan Ho, and Mohammad Norouzi. 2022. Learning Fast Samplers for Diffusion Models by Differentiating Through Sample Quality. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net."},{"key":"e_1_3_2_1_36_1","volume-title":"Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016","author":"Wu Jiajun","year":"2016","unstructured":"Jiajun Wu, Chengkai Zhang, Tianfan Xue, Bill Freeman, and Josh Tenenbaum. 2016. Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling. In Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, December 5-10, 2016, Barcelona, Spain, Daniel D. Lee, Masashi Sugiyama, Ulrike von Luxburg, Isabelle Guyon, and Roman Garnett (Eds.). 82--90."},{"key":"e_1_3_2_1_37_1","volume-title":"Adding Conditional Control to Text-to-Image Diffusion Models. CoRR","author":"Zhang Lvmin","year":"2023","unstructured":"Lvmin Zhang and Maneesh Agrawala. 2023. Adding Conditional Control to Text-to-Image Diffusion Models. CoRR, Vol. abs\/2302.05543 (2023)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/1391801"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Jing Zhao Heliang Zheng Chaoyue Wang Long Lan and Wenjing Yang. 2023. MagicFusion: Boosting Text-to-Image Generation Performance by Fusing Diffusion Models. arxiv: 2303.13126 [cs.CV]","DOI":"10.1109\/ICCV51070.2023.02065"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"e_1_3_2_1_41_1","volume-title":"Few-Shot Knowledge Transfer for Fine-Grained Cartoon Face Generation. In 2021 IEEE International Conference on Multimedia and Expo, ICME 2021","author":"Zhuang Nan","year":"2021","unstructured":"Nan Zhuang and Cheng Yang. 2021. Few-Shot Knowledge Transfer for Fine-Grained Cartoon Face Generation. In 2021 IEEE International Conference on Multimedia and Expo, ICME 2021, Shenzhen, China, July 5-9, 2021. IEEE, 1--6."}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Ottawa ON Canada","acronym":"MM '23"},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612588","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612588","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:01:12Z","timestamp":1755820872000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612588"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":41,"alternative-id":["10.1145\/3581783.3612588","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612588","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}