{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T23:07:18Z","timestamp":1743030438307,"version":"3.40.3"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031729942"},{"type":"electronic","value":"9783031729959"}],"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\/978-3-031-72995-9_10","type":"book-chapter","created":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T19:17:14Z","timestamp":1732389434000},"page":"159-176","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PanGu-Draw: Advancing Resource-Efficient Text-to-Image Synthesis with\u00a0Time-Decoupled Training and\u00a0Reusable Coop-Diffusion"],"prefix":"10.1007","author":[{"given":"Guansong","family":"Lu","sequence":"first","affiliation":[]},{"given":"Yuanfan","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Jianhua","family":"Han","sequence":"additional","affiliation":[]},{"given":"Minzhe","family":"Niu","sequence":"additional","affiliation":[]},{"given":"Yihan","family":"Zeng","sequence":"additional","affiliation":[]},{"given":"Songcen","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Zeyi","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Zhao","family":"Zhong","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Hang","family":"Xu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,24]]},"reference":[{"key":"10_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":"10_CR2","unstructured":"Betker, J., et\u00a0al.: Improving image generation with better captions. Computer Science (2023). https:\/\/cdn.openai.com\/papers\/dall-e-3.pdf"},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"Chen, C., et al.: bert2BERT: towards reusable pretrained language models. arXiv preprint arXiv:2110.07143 (2021)","DOI":"10.18653\/v1\/2022.acl-long.151"},{"key":"10_CR4","unstructured":"Chen, J., et al.: Pixart-$$\\alpha $$: fast training of diffusion transformer for photorealistic text-to-image synthesis (2023)"},{"key":"10_CR5","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":"10_CR6","doi-asserted-by":"crossref","unstructured":"Ding, N., Tang, Y., Han, K., Xu, C., Wang, Y.: Network expansion for practical training acceleration. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20269\u201320279 (2023)","DOI":"10.1109\/CVPR52729.2023.01941"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Feng, Z., et\u00a0al.: ERNIE-ViLG 2.0: improving text-to-image diffusion model with knowledge-enhanced mixture-of-denoising-experts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10135\u201310145 (2023)","DOI":"10.1109\/CVPR52729.2023.00977"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Fu, C., et\u00a0al.: TripLe: revisiting pretrained model reuse and progressive learning for efficient vision transformer scaling and searching. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01573"},{"key":"10_CR9","first-page":"26418","volume":"35","author":"J Gu","year":"2022","unstructured":"Gu, J., et al.: Wukong: a 100 million large-scale Chinese cross-modal pre-training benchmark. Adv. Neural. Inf. Process. Syst. 35, 26418\u201326431 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"10_CR10","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. Adv. Neural Info. Process. Syst. 30 (2017)"},{"key":"10_CR11","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":"10_CR12","first-page":"47","volume":"23","author":"J Ho","year":"2022","unstructured":"Ho, J., Saharia, C., Chan, W., Fleet, D.J., Norouzi, M., Salimans, T.: Cascaded diffusion models for high fidelity image generation. J. Mach. Learn. Res. 23, 47\u20131 (2022)","journal-title":"J. Mach. Learn. Res."},{"key":"10_CR13","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"10_CR14","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)"},{"issue":"9","key":"10_CR15","doi-asserted-by":"publisher","first-page":"2347","DOI":"10.1109\/TMM.2019.2896494","volume":"21","author":"X Li","year":"2019","unstructured":"Li, X., et al.: COCO-CN for cross-lingual image tagging, captioning, and retrieval. IEEE Trans. Multimedia 21(9), 2347\u20132360 (2019)","journal-title":"IEEE Trans. Multimedia"},{"key":"10_CR16","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 13. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"10_CR17","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)"},{"key":"10_CR18","doi-asserted-by":"publisher","unstructured":"Liu, N., Li, S., Du, Y., Torralba, A., Tenenbaum, J.B.: Compositional visual generation with composable diffusion models. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision, ECCV 2022. LNCS, vol. 13677, pp. 423\u2013439. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19790-1_26","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"10_CR19","unstructured":"Nichol, A, et al.: GLIDE: towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)"},{"key":"10_CR20","unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: ICML, pp. 8162\u20138171. PMLR (2021)"},{"key":"10_CR21","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Qin, Y., et al.: ELLE: efficient lifelong pre-training for emerging data. arXiv preprint arXiv:2203.06311 (2022)","DOI":"10.18653\/v1\/2022.findings-acl.220"},{"key":"10_CR23","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with CLIP latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"10_CR24","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: International Conference on Machine Learning, pp. 8821\u20138831. PMLR (2021)"},{"key":"10_CR25","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), June 2022, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"10_CR26","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":"10_CR27","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, Part III 18. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"10_CR28","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":"10_CR29","first-page":"2234","volume":"29","author":"T Salimans","year":"2016","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. Adv. Neural. Inf. Process. Syst. 29, 2234\u20132242 (2016)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"10_CR30","unstructured":"Shonenkov, A., Konstantinov, M., Bakshandaeva, D., Schuhmann, C., Ivanova, K., Klokova, N.: DeepFloyd IF: a powerful text-to-image model that can smartly integrate text into images (2023). https:\/\/www.deepfloyd.ai\/deepfloyd-if. Accessed 16 Nov 2023"},{"key":"10_CR31","doi-asserted-by":"crossref","unstructured":"Xu, X., Wang, Z., Zhang, E., Wang, K., Shi, H.: Versatile diffusion: text, images and variations all in one diffusion model. arXiv preprint arXiv:2211.08332 (2022)","DOI":"10.1109\/ICCV51070.2023.00713"},{"key":"10_CR32","unstructured":"Xue, Z., et al.: RAPHAEL: text-to-image generation via large mixture of diffusion paths. arXiv preprint arXiv:2305.18295 (2023)"},{"key":"10_CR33","unstructured":"Yang, A., et al.: Chinese CLIP: contrastive vision-language pretraining in Chinese. arXiv preprint arXiv:2211.01335 (2022)"},{"key":"10_CR34","doi-asserted-by":"crossref","unstructured":"Yao, L., et al.: DetCLIPv2: scalable open-vocabulary object detection pre-training via word-region alignment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23497\u201323506 (2023)","DOI":"10.1109\/CVPR52729.2023.02250"},{"key":"10_CR35","unstructured":"Yao, L., et al.: FILIP: fine-grained interactive language-image pre-training. arXiv preprint arXiv:2111.07783 (2021)"},{"key":"10_CR36","doi-asserted-by":"crossref","unstructured":"Ye, F., Liu, G., Wu, X., Wu, L.: AltDiffusion: a multilingual text-to-image diffusion model (2023)","DOI":"10.1609\/aaai.v38i7.28487"},{"key":"10_CR37","unstructured":"Zhang, J., et al.: Fengshenbang 1.0: being the foundation of Chinese cognitive intelligence. CoRR abs\/2209.02970 (2022)"},{"key":"10_CR38","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"}],"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\/978-3-031-72995-9_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T20:03:26Z","timestamp":1732392206000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72995-9_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,24]]},"ISBN":["9783031729942","9783031729959"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72995-9_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"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"}}]}}