{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:43:32Z","timestamp":1777657412487,"version":"3.51.4"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729829","type":"print"},{"value":"9783031729836","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"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\/978-3-031-72983-6_9","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:34:20Z","timestamp":1730108060000},"page":"145-161","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["HiDiffusion: Unlocking Higher-Resolution Creativity and\u00a0Efficiency in\u00a0Pretrained Diffusion Models"],"prefix":"10.1007","author":[{"given":"Shen","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaowei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenyu","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yao","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiajun","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"key":"9_CR1","unstructured":"Bar-Tal, O., Yariv, L., Lipman, Y., Dekel, T.: Multidiffusion: fusing diffusion paths for controlled image generation. In: ICML (2023)"},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"Bolya, D., Hoffman, J.: Token merging for fast stable diffusion. In: CVPRW, pp. 4598\u20134602 (2023)","DOI":"10.1109\/CVPRW59228.2023.00484"},{"key":"9_CR3","doi-asserted-by":"publisher","unstructured":"Chai, L., Gharbi, M., Shechtman, E., Isola, P., Zhang, R.: Any-resolution training for\u00a0high-resolution image synthesis. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022, Part XVI, pp. 170\u2013188. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19787-1_10","DOI":"10.1007\/978-3-031-19787-1_10"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Y.H., et al.: Speed is all you need: on-device acceleration of large diffusion models via GPU-aware optimizations. In: CVPR, pp. 4650\u20134654 (2023)","DOI":"10.1109\/CVPRW59228.2023.00490"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Choi, J., Lee, J., Shin, C., Kim, S., Kim, H., Yoon, S.: Perception prioritized training of diffusion models. In: CVPR, pp. 11472\u201311481 (2022)","DOI":"10.1109\/CVPR52688.2022.01118"},{"key":"9_CR6","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. 34, 8780\u20138794 (2021)"},{"key":"9_CR7","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"9_CR8","doi-asserted-by":"crossref","unstructured":"Du, R., Chang, D., Hospedales, T., Song, Y.Z., Ma, Z.: Demofusion: democratising high-resolution image generation with no $$\\$. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00589"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: CVPR, pp. 12873\u201312883 (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"9_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"9_CR11","unstructured":"He, Y., et al.: Scalecrafter: tuning-free higher-resolution visual generation with diffusion models. In: ICLR (2024)"},{"key":"9_CR12","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: NeurIPS (2017)"},{"key":"9_CR13","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS, pp. 6840\u20136851 (2020)"},{"key":"9_CR14","unstructured":"Hoogeboom, E., Heek, J., Salimans, T.: simple diffusion: end-to-end diffusion for high resolution images. arXiv preprint arXiv:2301.11093 (2023)"},{"key":"9_CR15","unstructured":"Jim\u00e9nez, \u00c1.B.: Mixture of diffusers for scene composition and high resolution image generation. arXiv preprint arXiv:2302.02412 (2023)"},{"key":"9_CR16","unstructured":"Jin, Z., Shen, X., Li, B., Xue, X.: Training-free diffusion model adaptation for variable-sized text-to-image synthesis. arXiv preprint arXiv:2306.08645 (2023)"},{"key":"9_CR17","unstructured":"Lee, Y., Kim, K., Kim, H., Sung, M.: Syncdiffusion: coherent montage via synchronized joint diffusions. In: NeurIPS (2023)"},{"key":"9_CR18","unstructured":"Lefaudeux, B., et al.: xformers: a modular and hackable transformer modelling library (2022). https:\/\/github.com\/facebookresearch\/xformers"},{"key":"9_CR19","doi-asserted-by":"crossref","unstructured":"Li, L., et al.: Autodiffusion: Training-free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration, pp. 7105\u20137114 (2023)","DOI":"10.1109\/ICCV51070.2023.00654"},{"key":"9_CR20","unstructured":"Li, Y., et al.: Snapfusion: text-to-image diffusion model on mobile devices within two seconds. In: NeurIPS (2024)"},{"key":"9_CR21","doi-asserted-by":"publisher","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","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"9_CR23","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. In: NeurIPS, pp. 5775\u20135787 (2022)"},{"key":"9_CR24","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":"9_CR25","doi-asserted-by":"publisher","unstructured":"Ma, H., Zhang, L., Zhu, X., Feng, J.: Accelerating score-based generative models with\u00a0preconditioned diffusion sampling. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022, Part XXIII, pp. 1\u201316. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20050-2_1","DOI":"10.1007\/978-3-031-20050-2_1"},{"key":"9_CR26","doi-asserted-by":"crossref","unstructured":"Ma, X., Fang, G., Wang, X.: Deepcache: accelerating diffusion models for free. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01492"},{"key":"9_CR27","doi-asserted-by":"crossref","unstructured":"Meng, C., et al.: On distillation of guided diffusion models. In: CVPR, pp. 14297\u201314306 (2023)","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"9_CR28","doi-asserted-by":"crossref","unstructured":"Pan, X., Ye, T., Xia, Z., Song, S., Huang, G.: Slide-transformer: hierarchical vision transformer with local self-attention. In: CVPR, pp. 2082\u20132091 (2023)","DOI":"10.1109\/CVPR52729.2023.00207"},{"key":"9_CR29","doi-asserted-by":"crossref","unstructured":"Pan, Z., Gherardi, R., Xie, X., Huang, S.: Effective real image editing with accelerated iterative diffusion inversion. In: ICCV, pp. 15912\u201315921 (2023)","DOI":"10.1109\/ICCV51070.2023.01458"},{"key":"9_CR30","unstructured":"Podell, D., et al.: Sdxl: improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"9_CR31","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763. PMLR (2021)"},{"key":"9_CR32","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"9_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"9_CR34","doi-asserted-by":"crossref","unstructured":"Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. IJCV 115, 211\u2013252 (2015)","DOI":"10.1007\/s11263-015-0816-y"},{"key":"9_CR35","unstructured":"Salimans, T., Ho, J.: Progressive distillation for fast sampling of diffusion models. arXiv preprint arXiv:2202.00512 (2022)"},{"key":"9_CR36","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":"9_CR37","unstructured":"Schuhmann, C., et\u00a0al.: Laion-5b: an open large-scale dataset for training next generation image-text models. In: NeurIPS, pp. 25278\u201325294 (2022)"},{"key":"9_CR38","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: ICLR (2021)"},{"key":"9_CR39","unstructured":"Song, Y., Ermon, S.: Generative modeling by estimating gradients of the data distribution. In: NeurIPS, pp. 11895\u201311907 (2019)"},{"key":"9_CR40","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. In: ICLR (2021)"},{"key":"9_CR41","unstructured":"Teng, J., et al.: Relay diffusion: unifying diffusion process across resolutions for image synthesis. arXiv preprint arXiv:2309.03350 (2023)"},{"key":"9_CR42","doi-asserted-by":"crossref","unstructured":"Xie, E., et al.: Difffit: unlocking transferability of large diffusion models via simple parameter-efficient fine-tuning. arXiv preprint arXiv:2304.06648 (2023)","DOI":"10.1109\/ICCV51070.2023.00390"},{"key":"9_CR43","doi-asserted-by":"crossref","unstructured":"Yang, X., Zhou, D., Feng, J., Wang, X.: Diffusion probabilistic model made slim. In: CVPR, pp. 22552\u201322562 (2023)","DOI":"10.1109\/CVPR52729.2023.02160"},{"key":"9_CR44","doi-asserted-by":"crossref","unstructured":"Zheng, Q., et al.: Any-size-diffusion: toward efficient text-driven synthesis for any-size HD images. arXiv preprint arXiv:2308.16582 (2023)","DOI":"10.1609\/aaai.v38i7.28589"}],"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\/978-3-031-72983-6_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T10:33:48Z","timestamp":1732962828000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72983-6_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,29]]},"ISBN":["9783031729829","9783031729836"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72983-6_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,29]]},"assertion":[{"value":"29 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"}}]}}