{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T16:22:04Z","timestamp":1775665324845,"version":"3.50.1"},"publisher-location":"Cham","reference-count":66,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730320","type":"print"},{"value":"9783031730337","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"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\/978-3-031-73033-7_13","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:03:55Z","timestamp":1730333035000},"page":"225-242","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":30,"title":["MobileDiffusion: Instant Text-to-Image Generation on\u00a0Mobile Devices"],"prefix":"10.1007","author":[{"given":"Yang","family":"Zhao","sequence":"first","affiliation":[]},{"given":"Yanwu","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Zhisheng","family":"Xiao","sequence":"additional","affiliation":[]},{"given":"Haolin","family":"Jia","sequence":"additional","affiliation":[]},{"given":"Tingbo","family":"Hou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"key":"13_CR1","unstructured":"Balaji, Y., et\u00a0al.: ediffi: text-to-image diffusion models with an ensemble of expert denoisers. arXiv preprint arXiv:2211.01324 (2022)"},{"key":"13_CR2","unstructured":"Bao, F., Li, C., Zhu, J., Zhang, B.: Analytic-DPM: an analytic estimate of the optimal reverse variance in diffusion probabilistic models. arXiv preprint arXiv:2201.06503 (2022)"},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Bao, F., et al.: All are worth words: A VIT backbone for diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"13_CR4","doi-asserted-by":"crossref","unstructured":"Blattmann, A., et al.: Align your latents: high-resolution video synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22563\u201322575 (2023)","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"13_CR5","unstructured":"Chen, J., et\u00a0al.: Pixart-$$\\alpha $$: fast training of diffusion transformer for photorealistic text-to-image synthesis. arXiv preprint arXiv:2310.00426 (2023)"},{"key":"13_CR6","unstructured":"Chen, X., et al.: Pali: a jointly-scaled multilingual language-image model. In: International Conference on Learning Representations (2023)"},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"Cherti, M., et al.: Reproducible scaling laws for contrastive language-image learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132829 (2023)","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"13_CR8","unstructured":"Choi, J., et al.: Squeezing large-scale diffusion models for mobile. arXiv preprint arXiv:2307.01193 (2023)"},{"key":"13_CR9","unstructured":"Dai, X., et al.: EMU: enhancing image generation models using photogenic needles in a haystack. arXiv preprint arXiv:2309.15807 (2023)"},{"key":"13_CR10","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: Advances in Neural Information Processing Systems (2021)"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Ding, N., et\u00a0al.: Delta tuning: a comprehensive study of parameter efficient methods for pre-trained language models. arXiv preprint arXiv:2203.06904 (2022)","DOI":"10.21203\/rs.3.rs-1553541\/v1"},{"key":"13_CR12","first-page":"30150","volume":"35","author":"T Dockhorn","year":"2022","unstructured":"Dockhorn, T., Vahdat, A., Kreis, K.: Genie: higher-order denoising diffusion solvers. Adv. Neural. Inf. Process. Syst. 35, 30150\u201330166 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"13_CR13","unstructured":"Gal, R., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"13_CR14","unstructured":"Guo, Y., et al.: AnimateDiff: animate your personalized text-to-image diffusion models without specific tuning. arXiv preprint arXiv:2307.04725 (2023)"},{"key":"13_CR15","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":"13_CR16","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"13_CR17","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"13_CR18","unstructured":"Hoogeboom, E., Heek, J., Salimans, T.: simple diffusion: end-to-end diffusion for high resolution images. arXiv preprint arXiv:2301.11093 (2023)"},{"key":"13_CR19","unstructured":"Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"13_CR20","unstructured":"Hu, E.J., et\u00a0al.: Lora: low-rank adaptation of large language models. In: International Conference on Learning Representations (2021)"},{"key":"13_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"646","DOI":"10.1007\/978-3-319-46493-0_39","volume-title":"Computer Vision \u2013 ECCV 2016","author":"G Huang","year":"2016","unstructured":"Huang, G., Sun, Yu., Liu, Z., Sedra, D., Weinberger, K.Q.: Deep networks with stochastic depth. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 646\u2013661. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_39"},{"key":"13_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":"13_CR23","first-page":"26565","volume":"35","author":"T Karras","year":"2022","unstructured":"Karras, T., Aittala, M., Aila, T., Laine, S.: Elucidating the design space of diffusion-based generative models. Adv. Neural. Inf. Process. Syst. 35, 26565\u201326577 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"13_CR24","unstructured":"Kim, B.K., Song, H.K., Castells, T., Choi, S.: BK-SDM: architecturally compressed stable diffusion for efficient text-to-image generation. In: Workshop on Efficient Systems for Foundation Models @ ICML2023 (2023). https:\/\/openreview.net\/forum?id=bOVydU0XKC"},{"key":"13_CR25","unstructured":"Kim, B.K., Song, H.K., Castells, T., Choi, S.: On architectural compression of text-to-image diffusion models. arXiv preprint arXiv:2305.15798 (2023)"},{"key":"13_CR26","doi-asserted-by":"crossref","unstructured":"Li, A.C., Prabhudesai, M., Duggal, S., Brown, E., Pathak, D.: Your diffusion model is secretly a zero-shot classifier. arXiv preprint arXiv:2303.16203 (2023)","DOI":"10.1109\/ICCV51070.2023.00210"},{"key":"13_CR27","unstructured":"Li, Y., et al.: SnapFusion: text-to-image diffusion model on mobile devices within two seconds. arXiv preprint arXiv:2306.00980 (2023)"},{"key":"13_CR28","unstructured":"Lin, S., Wang, A., Yang, X.: SDXL-lightning: progressive adversarial diffusion distillation. arXiv preprint arXiv:2402.13929 (2024)"},{"key":"13_CR29","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, Part V. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"13_CR30","unstructured":"Liu, X., Zhang, X., Ma, J., Peng, J., Liu, Q.: Instaflow: one step is enough for high-quality diffusion-based text-to-image generation. arXiv preprint arXiv:2309.06380 (2023)"},{"key":"13_CR31","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: Proceedings of the IEEE\/CVF Conference on Computer vision and Pattern Recognition, pp. 11976\u201311986 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"13_CR32","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2018)"},{"key":"13_CR33","first-page":"5775","volume":"35","author":"C Lu","year":"2022","unstructured":"Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., Zhu, J.: DPM-solver: a fast ode solver for diffusion probabilistic model sampling in around 10 steps. Adv. Neural. Inf. Process. Syst. 35, 5775\u20135787 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"13_CR34","unstructured":"Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., Zhu, J.: DPM-solver++: fast solver for guided sampling of diffusion probabilistic models. arXiv preprint arXiv:2211.01095 (2022)"},{"key":"13_CR35","unstructured":"Luo, S., Tan, Y., Huang, L., Li, J., Zhao, H.: Latent consistency models: synthesizing high-resolution images with few-step inference. arXiv preprint arXiv:2310.04378 (2023)"},{"key":"13_CR36","unstructured":"Luo, S., et al.: LCM-Lora: a universal stable-diffusion acceleration module. arXiv preprint arXiv:2311.05556 (2023)"},{"key":"13_CR37","unstructured":"Meng, C., et al.: SDEdit: guided image synthesis and editing with stochastic differential equations. In: International Conference on Learning Representations (2021)"},{"key":"13_CR38","doi-asserted-by":"crossref","unstructured":"Meng, C., et al.: On distillation of guided diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14297\u201314306 (2023)","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"13_CR39","doi-asserted-by":"crossref","unstructured":"Mou, C., et al.: T2i-adapter: learning adapters to dig out more controllable ability for text-to-image diffusion models. arXiv preprint arXiv:2302.08453 (2023)","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"13_CR40","unstructured":"Nichol, A.Q., et al.: Glide: towards photorealistic image generation and editing with text-guided diffusion models. In: International Conference on Machine Learning, pp. 16784\u201316804. PMLR (2022)"},{"key":"13_CR41","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4195\u20134205 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"13_CR42","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"13_CR43","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"13_CR44","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125, 1(2), 3 (2022)"},{"key":"13_CR45","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":"13_CR46","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: Dreambooth: fine tuning text-to-image diffusion models for subject-driven generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22500\u201322510 (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"13_CR47","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":"13_CR48","unstructured":"Salimans, T., Ho, J.: Progressive distillation for fast sampling of diffusion models. In: International Conference on Learning Representations (2022)"},{"key":"13_CR49","doi-asserted-by":"crossref","unstructured":"Sauer, A., Lorenz, D., Blattmann, A., Rombach, R.: Adversarial diffusion distillation. arXiv preprint arXiv:2311.17042 (2023)","DOI":"10.1007\/978-3-031-73016-0_6"},{"key":"13_CR50","unstructured":"Shazeer, N.: GLU variants improve transformer. arXiv preprint arXiv:2002.05202 (2020)"},{"key":"13_CR51","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: International Conference on Learning Representations (2020)"},{"key":"13_CR52","unstructured":"Song, Y., Dhariwal, P., Chen, M., Sutskever, I.: Consistency models (2023)"},{"key":"13_CR53","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. In: International Conference on Learning Representations (2020)"},{"key":"13_CR54","doi-asserted-by":"crossref","unstructured":"Sun, Z., Yu, H., Song, X., Liu, R., Yang, Y., Zhou, D.: MobileBert: a compact task-agnostic Bert for resource-limited devices. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 2158\u20132170 (2020)","DOI":"10.18653\/v1\/2020.acl-main.195"},{"key":"13_CR55","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":"13_CR56","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhang, L.L., Wang, Y., Yang, M.: Towards efficient vision transformer inference: a first study of transformers on mobile devices. In: Proceedings of the 23rd Annual International Workshop on Mobile Computing Systems and Applications, pp.\u00a01\u20137 (2022)","DOI":"10.1145\/3508396.3512869"},{"key":"13_CR57","unstructured":"Wortsman, M., Lee, J., Gilmer, J., Kornblith, S.: Replacing softmax with relu in vision transformers. arXiv preprint arXiv:2309.08586 (2023)"},{"key":"13_CR58","unstructured":"Wu, X., et al.: Human preference score v2: a solid benchmark for evaluating human preferences of text-to-image synthesis. arXiv preprint arXiv:2306.09341 (2023)"},{"key":"13_CR59","unstructured":"Xiao, J., et al.: CCM: adding conditional controls to text-to-image consistency models. arXiv preprint arXiv:2312.06971 (2023)"},{"key":"13_CR60","unstructured":"Xiao, Z., Kreis, K., Vahdat, A.: Tackling the generative learning trilemma with denoising diffusion GANs. In: International Conference on Learning Representations (2022)"},{"key":"13_CR61","doi-asserted-by":"crossref","unstructured":"Xu, J., Liu, S., Vahdat, A., Byeon, W., Wang, X., De\u00a0Mello, S.: Open-vocabulary panoptic segmentation with text-to-image diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2955\u20132966 (2023)","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"13_CR62","doi-asserted-by":"crossref","unstructured":"Xu, Y., Zhao, Y., Xiao, Z., Hou, T.: UFOGen: you forward once large scale text-to-image generation via diffusion GANs. arXiv preprint arXiv:2311.09257 (2023)","DOI":"10.1109\/CVPR52733.2024.00783"},{"key":"13_CR63","unstructured":"Yin, T., et al.: One-step diffusion with distribution matching distillation. arXiv preprint arXiv:2311.18828 (2023)"},{"key":"13_CR64","unstructured":"Yu, J., Yang, L., Xu, N., Yang, J., Huang, T.: Slimmable neural networks. In: International Conference on Learning Representations (2018)"},{"key":"13_CR65","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"13_CR66","doi-asserted-by":"crossref","unstructured":"Zhou, Y., et al.: Towards language-free training for text-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 17907\u201317917 (2022)","DOI":"10.1109\/CVPR52688.2022.01738"}],"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\/978-3-031-73033-7_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:35:45Z","timestamp":1730334945000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73033-7_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031730320","9783031730337"],"references-count":66,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73033-7_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 October 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"}}]}}