{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T17:03:58Z","timestamp":1789319038350,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032375919","type":"print"},{"value":"9783032375926","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37592-6_31","type":"book-chapter","created":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T16:43:06Z","timestamp":1789317786000},"page":"536-554","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["HRDiT: Training-Free High-Resolution Image Generation with\u00a0Off-the-Shelf Diffusion Transformer Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3961-890X","authenticated-orcid":false,"given":"Yu","family":"Xue","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5054-3394","authenticated-orcid":false,"given":"Haoxuan","family":"Qu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2166-3353","authenticated-orcid":false,"given":"Zhuoling","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3455-1527","authenticated-orcid":false,"given":"Hongbin","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4686-2768","authenticated-orcid":false,"given":"Jianxiong","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4958-9237","authenticated-orcid":false,"given":"Simon","family":"See","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1920-0371","authenticated-orcid":false,"given":"Hossein","family":"Rahmani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4365-4165","authenticated-orcid":false,"given":"Jun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,14]]},"reference":[{"key":"31_CR1","unstructured":"Bai, Y., Li, H., Huang, Q.: Positional encoding field. arXiv preprint arXiv:2510.20385 (2025)"},{"key":"31_CR2","unstructured":"Bar-Tal, O., Yariv, L., Lipman, Y., Dekel, T.: MultiDiffusion: fusing diffusion paths for controlled image generation. In: International Conference on Machine Learning, pp. 1737\u20131752. PMLR (2023)"},{"key":"31_CR3","doi-asserted-by":"crossref","unstructured":"Bu, J., et al.: HiFlow: training-free high-resolution image generation with flow-aligned guidance. arXiv preprint arXiv:2504.06232 (2025)","DOI":"10.52202\/085713-4831"},{"key":"31_CR4","unstructured":"Cao, B., Ye, J., Wei, Y., Shan, H.: AP-LDM: attentive and progressive latent diffusion model for training-free high-resolution image generation. arXiv preprint arXiv:2410.06055 (2024)"},{"key":"31_CR5","unstructured":"Chen, Y., et al.: Fast video generation with sliding tile attention. In: Forty-second International Conference on Machine Learning (2025). https:\/\/openreview.net\/forum?id=U74MOXPEJd"},{"key":"31_CR6","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6159\u20136168 (2024)","DOI":"10.1109\/CVPR52733.2024.00589"},{"key":"31_CR7","unstructured":"Du, R., et al.: I-max: maximize the resolution potential of pre-trained rectified flow transformers with projected flow. arXiv preprint arXiv:2410.07536 (2024)"},{"key":"31_CR8","unstructured":"Esser, P., et al.: Scaling rectified flow transformers for high-resolution image synthesis. In: Forty-First International Conference on Machine Learning (2024)"},{"key":"31_CR9","doi-asserted-by":"crossref","unstructured":"Guo, L., et\u00a0al.: Make a cheap scaling: a self-cascade diffusion model for higher-resolution adaptation. In: European Conference on Computer Vision, pp. 39\u201355. Springer (2024)","DOI":"10.1007\/978-3-031-72764-1_3"},{"key":"31_CR10","unstructured":"Gurobi\u00a0Optimization, L.: Gurobi Optimizer Reference Manual (2025). https:\/\/www.gurobi.com. Accessed 29 June 2026"},{"key":"31_CR11","unstructured":"Han, C., et al.: LM-infinite: zero-shot extreme length generalization for large language models. arXiv preprint arXiv:2308.16137 (2023)"},{"issue":"1","key":"31_CR12","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1016\/j.ijresmar.2024.09.002","volume":"42","author":"J Hartmann","year":"2025","unstructured":"Hartmann, J., Exner, Y., Domdey, S.: The power of generative marketing: can generative ai create superhuman visual marketing content? Int. J. Res. Mark. 42(1), 13\u201331 (2025)","journal-title":"Int. J. Res. Mark."},{"key":"31_CR13","unstructured":"He, Y., et al.: ScaleCrafter: tuning-free higher-resolution visual generation with diffusion models. In: The Twelfth International Conference on Learning Representations (2023)"},{"key":"31_CR14","unstructured":"Hoogeboom, E., Heek, J., Salimans, T.: Simple diffusion: end-to-end diffusion for high resolution images. In: International Conference on Machine Learning, pp. 13213\u201313232. PMLR (2023)"},{"key":"31_CR15","doi-asserted-by":"crossref","unstructured":"Huang, L., et al.: FouriScale: a frequency perspective on training-free high-resolution image synthesis. In: European Conference on Computer Vision, pp. 196\u2013212. Springer (2024)","DOI":"10.1007\/978-3-031-73254-6_12"},{"key":"31_CR16","unstructured":"Issachar, N., Yariv, G., Benaim, S., Adi, Y., Lischinski, D., Fattal, R.: DyPE: dynamic position extrapolation for ultra high resolution diffusion. arXiv preprint arXiv:2510.20766 (2025)"},{"key":"31_CR17","unstructured":"Jin, H., et al: LLM maybe longLM: Selfextend LLM context window without tuning. In: Forty-first International Conference on Machine Learning (2024). https:\/\/openreview.net\/forum?id=nkOMLBIiI7"},{"key":"31_CR18","doi-asserted-by":"crossref","unstructured":"Kim, Y., Hwang, G., Zhang, J., Park, E.: DiffuseHigh: training-free progressive high-resolution image synthesis through structure guidance. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, pp. 4338\u20134346 (2025)","DOI":"10.1609\/aaai.v39i4.32456"},{"key":"31_CR19","doi-asserted-by":"crossref","unstructured":"Koh, S., Cha, S., Oh, H., Lee, K., Kim, D.J.: ScaleDiff: higher-resolution image synthesis via efficient and model-agnostic diffusion. arXiv preprint arXiv:2510.25818 (2025)","DOI":"10.52202\/085713-3196"},{"key":"31_CR20","unstructured":"Labs, B.F.: Flux (2024). https:\/\/github.com\/black-forest-labs\/flux. Accessed 29 June 2026"},{"key":"31_CR21","unstructured":"Lai, H.P., Nguyen, P., Tran, A.: PixelRush: ultra-fast, training-free high-resolution image generation via one-step diffusion. arXiv preprint arXiv:2602.12769 (2026)"},{"key":"31_CR22","doi-asserted-by":"publisher","first-page":"58610","DOI":"10.52202\/079017-1868","volume":"37","author":"Y Lee","year":"2024","unstructured":"Lee, Y., Yoon, T., Sung, M.: GrounDiT: grounding diffusion transformers via noisy patch transplantation. Adv. Neural. Inf. Process. Syst. 37, 58610\u201358636 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"31_CR23","unstructured":"Leroy, V., Revaud, J., Lucas, T., Weinzaepfel, P.: Win-win: training high-resolution vision transformers from two windows. In: The Twelfth International Conference on Learning Representations (2024). https:\/\/openreview.net\/forum?id=N23A4ybMJr"},{"key":"31_CR24","doi-asserted-by":"crossref","unstructured":"Li, Z., Rahmani, H., Ke, Q., Liu, J.: LongDiff: training-free long video generation in one go. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 17789\u201317798 (2025)","DOI":"10.1109\/CVPR52734.2025.01657"},{"key":"31_CR25","doi-asserted-by":"crossref","unstructured":"Lin, Z., Lin, M., Zhao, M., Ji, R.: AccDiffusion: an accurate method for higher-resolution image generation. In: European Conference on Computer Vision. pp. 38\u201353. Springer (2024)","DOI":"10.1007\/978-3-031-72658-3_3"},{"key":"31_CR26","unstructured":"Liu, C., et al.: Boosting resolution generalization of diffusion transformers with randomized positional encodings. arXiv preprint arXiv:2503.18719 (2025)"},{"key":"31_CR27","doi-asserted-by":"crossref","unstructured":"Liu, S., Tan, Z., Wang, X.: CLEAR: conv-like linearization revs pre-trained diffusion transformers up. arXiv preprint arXiv:2412.16112 (2024)","DOI":"10.52202\/085713-5173"},{"key":"31_CR28","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":"31_CR29","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"31_CR30","doi-asserted-by":"publisher","unstructured":"Qin, J.: How does text-to-image ai affect indie game designers and artists? J. Innov. Dev. 5, 107\u2013111 (2023). https:\/\/doi.org\/10.54097\/f7of9f8k","DOI":"10.54097\/f7of9f8k"},{"key":"31_CR31","unstructured":"Qiu, H., Yu, N., Huang, Z., Debevec, P., Liu, Z.: CineScale: free lunch in high-resolution cinematic visual generation. arXiv preprint arXiv:2508.15774 (2025)"},{"key":"31_CR32","doi-asserted-by":"crossref","unstructured":"Qiu, H., et al.: Freescale: unleashing the resolution of diffusion models via tuning-free scale fusion. arXiv preprint arXiv:2412.09626 (2024)","DOI":"10.1109\/ICCV51701.2025.01569"},{"key":"31_CR33","doi-asserted-by":"publisher","first-page":"111131","DOI":"10.52202\/079017-3529","volume":"37","author":"J Ren","year":"2024","unstructured":"Ren, J., et al.: UltraPixel: advancing ultra high-resolution image synthesis to new peaks. Adv. Neural. Inf. Process. Syst. 37, 111131\u2013111171 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"31_CR34","doi-asserted-by":"publisher","first-page":"25278","DOI":"10.52202\/068431-1833","volume":"35","author":"C Schuhmann","year":"2022","unstructured":"Schuhmann, C., et al.: Laion-5b: an open large-scale dataset for training next generation image-text models. Adv. Neural. Inf. Process. Syst. 35, 25278\u201325294 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"31_CR35","unstructured":"Shen, T., Yu, J., Zhou, D., Li, D., Barsoum, E.: E-MMDiT: revisiting multimodal diffusion transformer design for fast image synthesis under limited resources. arXiv preprint arXiv:2510.27135 (2025)"},{"key":"31_CR36","doi-asserted-by":"crossref","unstructured":"Tang, Y., et al.: Patch slimming for efficient vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12165\u201312174 (2022)","DOI":"10.1109\/CVPR52688.2022.01185"},{"key":"31_CR37","doi-asserted-by":"crossref","unstructured":"Vontobel, T., Sadat, S., Salehi, F., Weber, R.: Hiwave: training-free high-resolution image generation via wavelet-based diffusion sampling. In: Proceedings of the SIGGRAPH Asia 2025 Conference Papers, pp. 1\u201311 (2025)","DOI":"10.1145\/3757377.3763979"},{"key":"31_CR38","doi-asserted-by":"crossref","unstructured":"Wu, H., Shen, S., Hu, Q., Zhang, X., Zhang, Y., Wang, Y.: MegaFusion: extend diffusion models towards higher-resolution image generation without further tuning. In: 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 3944\u20133953. IEEE (2025)","DOI":"10.1109\/WACV61041.2025.00388"},{"key":"31_CR39","unstructured":"Wu, W., Wang, Y., Xiao, G., Peng, H., Fu, Y.: Retrieval head mechanistically explains long-context factuality. In: The Thirteenth International Conference on Learning Representations (2025). https:\/\/openreview.net\/forum?id=EytBpUGB1Z"},{"key":"31_CR40","doi-asserted-by":"crossref","unstructured":"Yang, H., et al.: Fam diffusion: Frequency and attention modulation for high-resolution image generation with stable diffusion. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 2459\u20132468 (2025)","DOI":"10.1109\/CVPR52734.2025.00235"},{"key":"31_CR41","unstructured":"Yang, Z., et al.: RectifiedHR: enable efficient high-resolution image generation via energy rectification. arXiv e-prints, pp. arXiv\u20132503 (2025)"},{"key":"31_CR42","unstructured":"Ye, Z., et al.: FlashInfer: efficient and customizable attention engine for LLM inference serving. In: Eighth Conference on Machine Learning and Systems (2025). https:\/\/openreview.net\/forum?id=RXPofAsL8F"},{"key":"31_CR43","doi-asserted-by":"publisher","first-page":"1196","DOI":"10.52202\/079017-0037","volume":"37","author":"Z Yuan","year":"2024","unstructured":"Yuan, Z., et al.: DiTFastAttn: attention compression for diffusion transformer models. Adv. Neural. Inf. Process. Syst. 37, 1196\u20131219 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"31_CR44","unstructured":"Zhang, G., et\u00a0al.: MoA: mixture of sparse attention for automatic large language model compression. arXiv preprint arXiv:2406.14909 (2024)"},{"key":"31_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: DiTFastAttnV2: head-wise attention compression for multi-modality diffusion transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16399\u201316409 (2025)","DOI":"10.1109\/ICCV51701.2025.01522"},{"key":"31_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, J., Huang, Q., Liu, J., Guo, X., Huang, D.: Diffusion-4k: ultra-high-resolution image synthesis with latent diffusion models. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 23464\u201323473 (2025)","DOI":"10.1109\/CVPR52734.2025.02185"},{"key":"31_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, S., Chen, Z., Zhao, Z., Chen, Y., Tang, Y., Liang, J.: HiDiffusion: unlocking higher-resolution creativity and efficiency in pretrained diffusion models. In: European Conference on Computer Vision, pp. 145\u2013161. Springer (2024)","DOI":"10.1007\/978-3-031-72983-6_9"},{"key":"31_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, S., et\u00a0al.: LeDiT: your length-extrapolatable diffusion transformer without positional encoding. arXiv preprint arXiv:2503.04344 (2025)","DOI":"10.52202\/085713-0766"},{"key":"31_CR49","unstructured":"Zhang, Z., Li, R., Zhang, L.: FreCaS: efficient higher-resolution image generation via frequency-aware cascaded sampling. In: The Thirteenth International Conference on Learning Representations (2025). https:\/\/openreview.net\/forum?id=TsBDfe8Ra5"},{"key":"31_CR50","unstructured":"Zhao, M., et al.: UltraImage: rethinking resolution extrapolation in image diffusion transformers. arXiv preprint arXiv:2512.04504 (2025)"},{"key":"31_CR51","doi-asserted-by":"publisher","first-page":"9010","DOI":"10.52202\/068431-0655","volume":"35","author":"C Zheng","year":"2022","unstructured":"Zheng, C., et al.: SAViT: structure-aware vision transformer pruning via collaborative optimization. Adv. Neural. Inf. Process. Syst. 35, 9010\u20139023 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37592-6_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T16:43:14Z","timestamp":1789317794000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37592-6_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032375919","9783032375926"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37592-6_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"14 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}