{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T14:45:29Z","timestamp":1781621129631,"version":"3.54.5"},"reference-count":78,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01502","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"16185-16195","source":"Crossref","is-referenced-by-count":2,"title":["SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation"],"prefix":"10.1109","author":[{"given":"Junsong","family":"Chen","sequence":"first","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuchen","family":"Xue","sequence":"additional","affiliation":[{"name":"Independent Researcher"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuyang","family":"Zhao","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jincheng","family":"Yu","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sayak","family":"Paul","sequence":"additional","affiliation":[{"name":"Huggingface"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Cai","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Song","family":"Han","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Enze","family":"Xie","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","author":"Albergo","year":"2022","journal-title":"Building normalizing flows with stochastic interpolants"},{"key":"ref2","author":"Balaji","year":"2022","journal-title":"ediff-i: Text-to-image diffusion models with an ensemble of expert denoisers"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00687"},{"key":"ref4","author":"Chen","year":"2024","journal-title":"Deep compression autoencoder for efficient high-resolution diffusion models"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"ref6","article-title":"Pixart- \\alpha: Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"International Conference on Learning Representations","author":"Chen"},{"key":"ref7","author":"Chen","year":"2024","journal-title":"Pixart- \\delta : Fast and controllable image generation with latent consistency models"},{"key":"ref8","author":"Dubey","year":"2024","journal-title":"The llama 3 herd of models"},{"key":"ref9","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser","year":"2024"},{"key":"ref10","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2270"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref13","author":"Heek","year":"2024","journal-title":"Multistep consistency models"},{"key":"ref14","author":"Ho","year":"2022","journal-title":"Classifier-free diffusion guidance"},{"key":"ref15","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref16","author":"Hu","year":"2024","journal-title":"Snapgen: Taming high-resolution text-to-image models for mobile devices with efficient architectures and training"},{"key":"ref17","first-page":"428","article-title":"Distilling diffusion models into conditional gans","volume-title":"European Conference on Computer Vision","author":"Kang","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1926"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02282"},{"key":"ref20","author":"Kim","year":"2023","journal-title":"Consistency trajectory models: Learning probability flow ode trajectory of diffusion"},{"key":"ref21","article-title":"Pagoda: Progressive growing of a onestep generator from a low-resolution diffusion teacher","volume":"37","author":"Kim","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","author":"Kohler","year":"2024","journal-title":"Imagine flash: Accelerating emu diffusion models with backward distillation"},{"key":"ref23","article-title":"Black Forest Labs","year":"2024","journal-title":"Flux"},{"key":"ref24","article-title":"Playground v2","author":"Li","year":"2024","journal-title":"5: Three insights towards enhancing aesthetic quality in text-to-image generation"},{"key":"ref25","author":"Li","year":"2024","journal-title":"Svdquant: Absorbing outliers by lowrank components for 4-bit diffusion models"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0907"},{"key":"ref27","author":"Li","year":"2024","journal-title":"Hunyuan-dit: A powerful multiresolution diffusion transformer with fine-grained chinese understanding"},{"key":"ref28","author":"Lim","year":"2017","journal-title":"Geometric gan. arXiv preprint arXiv:1705.02894"},{"key":"ref29","author":"Lipman","year":"2022","journal-title":"Flow matching for generative modeling"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-23161-2_300919"},{"key":"ref31","author":"Liu","year":"2022","journal-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow"},{"key":"ref32","author":"Liu","year":"2024","journal-title":"Dilatequant: Accurate and efficient diffusion quantization via weight dilation"},{"key":"ref33","author":"Lu","year":"2023","journal-title":"Research on reversible generative models and their efficient algorithms"},{"key":"ref34","author":"Lu","year":"2024","journal-title":"Simplifying, stabilizing and scaling continuous-time consistency models"},{"key":"ref35","author":"Luhman","year":"2021","journal-title":"Knowledge distillation in iterative generative models for improved sampling speed"},{"key":"ref36","author":"Luo","year":"2023","journal-title":"Latent consistency models: Synthesizing highresolution images with few-step inference"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3344"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3664"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"ref40","article-title":"OpenAI","year":"2023","journal-title":"Dalle-3"},{"key":"ref41","author":"Oquab","year":"2023","journal-title":"Dinov2: Learning robust visual features without supervision"},{"key":"ref42","author":"Peebles","year":"2022","journal-title":"Scalable diffusion models with transformers"},{"key":"ref43","author":"Peluchetti","year":"2022","journal-title":"Non-denoising forward-time diffusions"},{"key":"ref44","author":"Pernias","year":"2023","journal-title":"Wuerstchen: An efficient architecture for large-scale text-to-image diffusion models"},{"key":"ref45","volume-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"ref46","author":"Poole","year":"2022","journal-title":"Dreamfusion: Text-to-3d using 2d diffusion"},{"key":"ref47","volume-title":"Ultrapixel: Advancing ultra-high-resolution image synthesis to new peaks","author":"Ren","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref49","author":"Salimans","year":"2022","journal-title":"Progressive distillation for fast sampling of diffusion models"},{"key":"ref50","first-page":"36046","article-title":"Multistep distillation of diffusion models via moment matching","volume":"37","author":"Salimans","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687625"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73016-0_6"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1142\/9789814354110_0008"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/960128.806879"},{"key":"ref55","author":"Sui","year":"2024","journal-title":"Bitsfusion: 1.99 bits weight quantization of diffusion model"},{"key":"ref56","author":"Tang","year":"2024","journal-title":"Hart: Efficient visual generation with hybrid autoregressive transformer"},{"key":"ref57","volume-title":"Dim: Diffusion mamba for efficient high-resolution image synthesis","author":"Teng","year":"2024"},{"key":"ref58","author":"Tian","year":"2024","journal-title":"U-dits: Downsample tokens in u-shaped diffusion transformers"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00142"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2668"},{"key":"ref61","author":"Wang","year":"2022","journal-title":"Diffusion-gan: Training gans with diffusion"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0368"},{"key":"ref63","volume-title":"Sana: Efficient high-resolution image synthesis with linear diffusion transformers","author":"Xie","year":"2024"},{"key":"ref64","article-title":"Sana 1","author":"Xie","year":"2025","journal-title":"5: Efficient scaling of training-time and inference-time compute in linear diffusion transformer"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.164"},{"key":"ref66","author":"Xie","year":"2024","journal-title":"Em distillation for one-step diffusion models"},{"key":"ref67","article-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","author":"Xu","year":"2024","journal-title":"Advances in Neural Information Processing Systems, 36"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00787"},{"key":"ref69","volume-title":"Improved distribution matching distillation for fast image synthesis","author":"Yin","year":"2024"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00632"},{"key":"ref71","article-title":"Root mean square layer normalization","author":"Zhang","year":"2019","journal-title":"Advances in Neural Information Processing Systems, 32"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_13"},{"key":"ref75","article-title":"Score identity distillation: Exponentially fast distillation of pretrained diffusion models for one-step generation","volume-title":"Forty-first International Conference on Machine Learning","author":"Zhou","year":"2024"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00718"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4172"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445728.pdf?arnumber=11445728","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:20:02Z","timestamp":1777530002000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445728\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":78,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01502","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}