{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T11:51:11Z","timestamp":1777722671622,"version":"3.51.4"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726293","type":"print"},{"value":"9783031726309","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"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\/978-3-031-72630-9_17","type":"book-chapter","created":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T05:19:27Z","timestamp":1733289567000},"page":"285-302","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with\u00a0Metric-Decoupled Mixed Precision Quantization"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2071-7514","authenticated-orcid":false,"given":"Tianchen","family":"Zhao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2209-8312","authenticated-orcid":false,"given":"Xuefei","family":"Ning","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7279-8359","authenticated-orcid":false,"given":"Tongcheng","family":"Fang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0062-3294","authenticated-orcid":false,"given":"Enshu","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1280-4781","authenticated-orcid":false,"given":"Guyue","family":"Huang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8421-2662","authenticated-orcid":false,"given":"Zinan","family":"Lin","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3858-7972","authenticated-orcid":false,"given":"Shengen","family":"Yan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0849-3252","authenticated-orcid":false,"given":"Guohao","family":"Dai","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6108-5157","authenticated-orcid":false,"given":"Yu","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,5]]},"reference":[{"key":"17_CR1","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: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 4651\u20134655 (2023). https:\/\/api.semanticscholar.org\/CorpusID:258298971","DOI":"10.1109\/CVPRW59228.2023.00490"},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Dong, Z., Yao, Z., Gholami, A., Mahoney, M.W., Keutzer, K.: HAWQ: Hessian aware quantization of neural networks with mixed-precision. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 293\u2013302 (2019). https:\/\/api.semanticscholar.org\/CorpusID:148571720","DOI":"10.1109\/ICCV.2019.00038"},{"key":"17_CR3","unstructured":"He, Y., Liu, J., Wu, W., Zhou, H., Zhuang, B.: EfficientDM: efficient quantization-aware fine-tuning of low-bit diffusion models. ArXiv abs\/2310.03270 (2023). https:\/\/api.semanticscholar.org\/CorpusID:263672060"},{"key":"17_CR4","unstructured":"He, Y., Liu, L., Liu, J., Wu, W., Zhou, H., Zhuang, B.: PTQD: accurate post-training quantization for diffusion models. ArXiv abs\/2305.10657 (2023). https:\/\/api.semanticscholar.org\/CorpusID:258762678"},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Bras, R.L., Choi, Y.: ClipScore: a reference-free evaluation metric for image captioning. arXiv preprint arXiv:2104.08718 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"17_CR6","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 30 (2017)"},{"key":"17_CR7","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":"17_CR8","unstructured":"Huang, Y., Gong, R., Liu, J., Chen, T., Liu, X.: TFMQ-DM: temporal feature maintenance quantization for diffusion models. ArXiv abs\/2311.16503 (2023). https:\/\/api.semanticscholar.org\/CorpusID:265466808"},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"Jacob, B., et al.: Quantization and training of neural networks for efficient integer-arithmetic-only inference. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2704\u20132713 (2017). https:\/\/api.semanticscholar.org\/CorpusID:39867659","DOI":"10.1109\/CVPR.2018.00286"},{"key":"17_CR10","unstructured":"Li, S., et al.: LLM-MQ: mixed-precision quantization for efficient LLM deployment. In: NeurIPS 2023 Efficient Natural Language and Speech Processing Workshop (2023)"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Li, X., et al.: Q-diffusion: quantizing diffusion models. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01608"},{"key":"17_CR12","unstructured":"Li, Y., Xu, S., Cao, X., Sun, X., Zhang, B.: Q-DM: an efficient low-bit quantized diffusion model. In: Neural Information Processing Systems (2023). https:\/\/api.semanticscholar.org\/CorpusID:268096292"},{"key":"17_CR13","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. https:\/\/api.semanticscholar.org\/CorpusID:14113767","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"17_CR14","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. arXiv preprint arXiv:2206.00927 (2022)"},{"key":"17_CR15","unstructured":"Luo, S., et al.: LCM-LoRA: a universal stable-diffusion acceleration module. ArXiv abs\/2311.05556 (2023). https:\/\/api.semanticscholar.org\/CorpusID:265067414"},{"key":"17_CR16","unstructured":"Stable Fast Maintainers: Stable-fast. https:\/\/github.com\/chengzeyi\/stable-fast"},{"key":"17_CR17","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":"17_CR18","unstructured":"Nagel, M., Amjad, R.A., van Baalen, M., Louizos, C., Blankevoort, T.: Up or down? Adaptive rounding for post-training quantization. ArXiv abs\/2004.10568 (2020). https:\/\/api.semanticscholar.org\/CorpusID:216056295"},{"key":"17_CR19","unstructured":"Nagel, M., Fournarakis, M., Amjad, R.A., Bondarenko, Y., van Baalen, M., Blankevoort, T.: A white paper on neural network quantization. ArXiv abs\/2106.08295 (2021). https:\/\/api.semanticscholar.org\/CorpusID:235435934"},{"key":"17_CR20","unstructured":"NVIDIA: Nsight Systems. https:\/\/docs.nvidia.com\/nsight-systems\/index.html"},{"key":"17_CR21","unstructured":"Nvidia: Nvidia cutlass release v3.4 (2024). https:\/\/github.com\/NVIDIA\/cutlass"},{"key":"17_CR22","unstructured":"Pandey, N.P., Nagel, M., van Baalen, M., Huang, Y.R., Patel, C., Blankevoort, T.: A practical mixed precision algorithm for post-training quantization. ArXiv abs\/2302.05397 (2023). https:\/\/api.semanticscholar.org\/CorpusID:256808627"},{"key":"17_CR23","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. ArXiv abs\/2307.01952 (2023). https:\/\/api.semanticscholar.org\/CorpusID:259341735"},{"key":"17_CR24","unstructured":"PyTorch: PyTorch Memory Management (2023). https:\/\/pytorch.org\/docs\/stable\/notes\/cuda.html#memory-management"},{"key":"17_CR25","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":"17_CR26","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: ICML, pp. 8821\u20138831. PMLR (2021)"},{"key":"17_CR27","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":"17_CR28","unstructured":"Ryu, H., Lim, S., Shim, H.: Memory-efficient personalization using quantized diffusion model. ArXiv abs\/2401.04339 (2024). https:\/\/api.semanticscholar.org\/CorpusID:266899926"},{"key":"17_CR29","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs 29 (2016)"},{"key":"17_CR30","unstructured":"Salimans, T., Ho, J.: Progressive distillation for fast sampling of diffusion models. arXiv preprint arXiv:2202.00512 (2022)"},{"key":"17_CR31","unstructured":"Sauer, A., Lorenz, D., Blattmann, A., Rombach, R.: Adversarial diffusion distillation. ArXiv abs\/2311.17042 (2023). https:\/\/api.semanticscholar.org\/CorpusID:265466173"},{"key":"17_CR32","unstructured":"So, J., Lee, J., Ahn, D., Kim, H., Park, E.: Temporal dynamic quantization for diffusion models. ArXiv abs\/2306.02316 (2023). https:\/\/api.semanticscholar.org\/CorpusID:259075274"},{"key":"17_CR33","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: International Conference on Machine Learning, pp. 2256\u20132265. PMLR (2015)"},{"key":"17_CR34","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"17_CR35","unstructured":"Song, Y., Dhariwal, P., Chen, M., Sutskever, I.: Consistency models. In: International Conference on Machine Learning (2023). https:\/\/api.semanticscholar.org\/CorpusID:257280191"},{"key":"17_CR36","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456 (2020)"},{"key":"17_CR37","unstructured":"Tang, S., et al.: Post-training quantization with progressive calibration and activation relaxing for text-to-image diffusion models. ArXiv abs\/2311.06322 (2023). https:\/\/api.semanticscholar.org\/CorpusID:265149927"},{"key":"17_CR38","unstructured":"Google OR-Tools Development Team: OR-tools. https:\/\/github.com\/google\/or-tools (Year Accessed)"},{"key":"17_CR39","unstructured":"Wang, H., Shang, Y., Yuan, Z., Wu, J., Yan, Y.: Quest: low-bit diffusion model quantization via efficient selective finetuning. ArXiv abs\/2402.03666 (2024). https:\/\/api.semanticscholar.org\/CorpusID:267500241"},{"key":"17_CR40","doi-asserted-by":"crossref","unstructured":"Wang, K., Liu, Z., Lin, Y., Lin, J., Han, S.: HAQ: hardware-aware automated quantization with mixed precision. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8604\u20138612 (2018). https:\/\/api.semanticscholar.org\/CorpusID:102350477","DOI":"10.1109\/CVPR.2019.00881"},{"key":"17_CR41","unstructured":"Wikipedia: Pareto front (2024). https:\/\/en.wikipedia.org\/wiki\/Pareto_front. Accessed 3 Mar 2024"},{"key":"17_CR42","unstructured":"Wikipedia contributors: Structural similarity index measure. https:\/\/en.wikipedia.org\/wiki\/Structural_similarity_index_measure. Accessed 28 Feb 2024"},{"key":"17_CR43","doi-asserted-by":"crossref","unstructured":"Wu, X., Sun, K., Zhu, F., Zhao, R., Li, H.: Better aligning text-to-image models with human preference. arXiv preprint arXiv:2303.14420 (2023)","DOI":"10.1109\/ICCV51070.2023.00200"},{"key":"17_CR44","unstructured":"Xiao, G., Tian, Y., Chen, B., Han, S., Lewis, M.: Efficient streaming language models with attention sinks. ArXiv abs\/2309.17453 (2023). https:\/\/api.semanticscholar.org\/CorpusID:263310483"},{"key":"17_CR45","unstructured":"Xu, J., et al.: ImageReward: learning and evaluating human preferences for text-to-image generation. arXiv preprint arXiv:2304.05977 (2023)"},{"key":"17_CR46","unstructured":"Yang, Y., Dai, X., Wang, J., Zhang, P., Zhang, H.: Efficient quantization strategies for latent diffusion models. ArXiv abs\/2312.05431 (2023). https:\/\/api.semanticscholar.org\/CorpusID:266163100"},{"key":"17_CR47","unstructured":"Zhao, W., Bai, L., Rao, Y., Zhou, J., Lu, J.: UniPC: a unified predictor-corrector framework for fast sampling of diffusion models. arXiv preprint arXiv:2302.04867 (2023)"},{"key":"17_CR48","unstructured":"Zhao, Y., Xu, Y., Xiao, Z., Hou, T.: MobileDiffusion: subsecond text-to-image generation on mobile devices. ArXiv abs\/2311.16567 (2023). https:\/\/api.semanticscholar.org\/CorpusID:265466277"}],"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\/978-3-031-72630-9_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T06:38:19Z","timestamp":1768199899000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72630-9_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,5]]},"ISBN":["9783031726293","9783031726309"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72630-9_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,5]]},"assertion":[{"value":"5 December 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"}}]}}