{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T23:22:25Z","timestamp":1790724145407,"version":"4.1.0"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032371737","type":"print"},{"value":"9783032371744","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\/978-3-032-37174-4_13","type":"book-chapter","created":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T07:08:00Z","timestamp":1789715280000},"page":"214-232","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["DreamLite: A Lightweight On-Device Unified Model for\u00a0Image Generation and\u00a0Editing"],"prefix":"10.1007","author":[{"given":"Kailai","family":"Feng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxiang","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Songwei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenqian","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wangmeng","family":"Zuo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,19]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Alekseenko, G., et al.: VIBE: visual instruction based editor. arXiv preprint arXiv:2601.02242 (2026)","DOI":"10.2139\/ssrn.6033994"},{"key":"13_CR2","unstructured":"Bai, J., et al.: Meissonic: revitalizing masked generative transformers for efficient high-resolution text-to-image synthesis. In: The Thirteenth International Conference on Learning Representations (2024)"},{"key":"13_CR3","unstructured":"Bai, S., et\u00a0al.: Qwen3-VL technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"13_CR4","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: InstructPix2Pix: learning to follow image editing instructions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18392\u201318402 (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"13_CR5","unstructured":"Cai, H., et al.: Z-image: an efficient image generation foundation model with single-stream diffusion transformer. arXiv preprint arXiv:2511.22699 (2025)"},{"key":"13_CR6","unstructured":"Cao, S., et\u00a0al.: HunyuanImage 3.0 technical report. arXiv preprint arXiv:2509.23951 (2025)"},{"key":"13_CR7","doi-asserted-by":"publisher","unstructured":"Chen, J., et al.: Pixart-$$\\sigma $$: weak-to-strong training of diffusion transformer for 4k text-to-image generation. In: European Conference on Computer Vision, pp. 74\u201391. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-73411-3_5","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"13_CR8","unstructured":"Chow, W., et\u00a0al.: EditMGT: unleashing potentials of masked generative transformers in image editing. arXiv preprint arXiv:2512.11715 (2025)"},{"key":"13_CR9","unstructured":"Deng, C., et al.: Emerging properties in unified multimodal pretraining. arXiv preprint arXiv:2505.14683 (2025)"},{"key":"13_CR10","unstructured":"Esser, P., et al.: Scaling rectified flow transformers for high-resolution image synthesis. In: Forty-First International Conference on Machine Learning (2024)"},{"key":"13_CR11","unstructured":"Gao, Y., et\u00a0al.: Seedream 3.0 technical report. arXiv preprint arXiv:2504.11346 (2025)"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Geng, Z., et\u00a0al.: InstructDiffusion: a generalist modeling interface for vision tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12709\u201312720 (2024)","DOI":"10.1109\/CVPR52733.2024.01208"},{"key":"13_CR13","doi-asserted-by":"publisher","first-page":"52132","DOI":"10.52202\/075280-2270","volume":"36","author":"D Ghosh","year":"2023","unstructured":"Ghosh, D., Hajishirzi, H., Schmidt, L.: GenEval: an object-focused framework for evaluating text-to-image alignment. Adv. Neural. Inf. Process. Syst. 36, 52132\u201352152 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"13_CR14","unstructured":"Gong, L., et\u00a0al.: Seedream 2.0: a native chinese-english bilingual image generation foundation model. arXiv preprint arXiv:2503.07703 (2025)"},{"key":"13_CR15","unstructured":"Google: Gemini 2.5 flash. https:\/\/aistudio.google.com\/models\/gemini-2-5-flash-image (2025)"},{"key":"13_CR16","unstructured":"Hu, D., et\u00a0al.: SnapGen: taming high-resolution text-to-image models for mobile devices with efficient architectures and training. arXiv preprint arXiv:2412.09619 (2024)"},{"key":"13_CR17","unstructured":"Hu, D., et\u00a0al.: SnapGen++: unleashing diffusion transformers for efficient high-fidelity image generation on edge devices. arXiv preprint arXiv:2601.08303 (2026)"},{"key":"13_CR18","unstructured":"Hu, X., Wang, R., Fang, Y., Fu, B., Cheng, P., Yu, G.: ELLA: equip diffusion models with LLM for enhanced semantic alignment. arXiv preprint arXiv:2403.05135 (2024)"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Huang, Y., et\u00a0al.: SmartEdit: exploring complex instruction-based image editing with multimodal large language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8362\u20138371 (2024)","DOI":"10.1109\/CVPR52733.2024.00799"},{"key":"13_CR20","doi-asserted-by":"publisher","first-page":"36652","DOI":"10.52202\/075280-1594","volume":"36","author":"Y Kirstain","year":"2023","unstructured":"Kirstain, Y., Polyak, A., Singer, U., Matiana, S., Penna, J., Levy, O.: Pick-a-pic: an open dataset of user preferences for text-to-image generation. Adv. Neural. Inf. Process. Syst. 36, 36652\u201336663 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"13_CR21","unstructured":"Labs, B.F.: Flux (2024). https:\/\/github.com\/black-forest-labs\/flux"},{"key":"13_CR22","unstructured":"Labs, B.F.: Flux2 (2025). https:\/\/github.com\/black-forest-labs\/flux2"},{"key":"13_CR23","unstructured":"Labs, B.F., et\u00a0al.: FLUX. 1 kontext: flow matching for in-context image generation and editing in latent space. arXiv preprint arXiv:2506.15742 (2025)"},{"key":"13_CR24","doi-asserted-by":"publisher","first-page":"20662","DOI":"10.52202\/075280-0907","volume":"36","author":"Y Li","year":"2023","unstructured":"Li, Y., et al.: SnapFusion: text-to-image diffusion model on mobile devices within two seconds. Adv. Neural. Inf. Process. Syst. 36, 20662\u201320678 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"13_CR25","unstructured":"Lin, B., et al.: Uniworld-V1: high-resolution semantic encoders for unified visual understanding and generation. arXiv preprint arXiv:2506.03147(2025)"},{"key":"13_CR26","unstructured":"Lipman, Y., Chen, R.T., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. arXiv preprint arXiv:2210.02747 (2022)"},{"key":"13_CR27","doi-asserted-by":"crossref","unstructured":"Liu, J., et al.: Flow-GRPO: training flow matching models via online RL. arXiv preprint arXiv:2505.05470 (2025)","DOI":"10.52202\/085713-1362"},{"key":"13_CR28","unstructured":"Liu, S., et al.: Step1X-Edit: a practical framework for general image editing. arXiv preprint arXiv:2504.17761 (2025)"},{"key":"13_CR29","unstructured":"Liu, X., Gong, C., Liu, Q.: Flow straight and fast: learning to generate and transfer data with rectified flow. arXiv preprint arXiv:2209.03003 (2022)"},{"key":"13_CR30","unstructured":"Luo, S., Tan, Y., Huang, L., Li, J., Zhao, H.: Latent consistency models: synthesizing high-resolution images with few-step inference. arXiv preprint arXiv:2310.04378 (2023)"},{"key":"13_CR31","doi-asserted-by":"crossref","unstructured":"Ma, Y., Wu, X., Sun, K., Li, H.: HPSV3: towards wide-spectrum human preference score. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15086\u201315095 (2025)","DOI":"10.1109\/ICCV51701.2025.01400"},{"key":"13_CR32","unstructured":"Madebyollin: TAESD (2024). https:\/\/github.com\/madebyollin\/taesd"},{"key":"13_CR33","unstructured":"OpenAI: GPT-image (2025). https:\/\/openai.com\/index\/gpt-4o-system-card\/"},{"key":"13_CR34","unstructured":"Prabhudesai, M., Goyal, A., Pathak, D., Fragkiadaki, K.: Aligning text-to-image diffusion models with reward backpropagation (2023)"},{"key":"13_CR35","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":"13_CR36","doi-asserted-by":"publisher","unstructured":"Sauer, A., Lorenz, D., Blattmann, A., Rombach, R.: Adversarial diffusion distillation. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) European Conference on Computer Vision, pp. 87\u2013103. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-73016-0_6","DOI":"10.1007\/978-3-031-73016-0_6"},{"key":"13_CR37","unstructured":"Seedream, T., et\u00a0al.: Seedream 4.0: toward next-generation multimodal image generation. arXiv preprint arXiv:2509.20427 (2025)"},{"key":"13_CR38","unstructured":"Shaker, A., et al.: Mobile-o: unified multimodal understanding and generation on mobile device. arXiv preprint arXiv:2602.20161 (2026)"},{"key":"13_CR39","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":"13_CR40","unstructured":"Team, M.L., et\u00a0al.: LongCat-image technical report. arXiv preprint arXiv:2512.07584 (2025)"},{"key":"13_CR41","doi-asserted-by":"crossref","unstructured":"Wallace, B., et al.: Diffusion model alignment using direct preference optimization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8228\u20138238 (2024)","DOI":"10.1109\/CVPR52733.2024.00786"},{"key":"13_CR42","unstructured":"Wang, D., et\u00a0al.: DeepGen 1.0: a lightweight unified multimodal model for advancing image generation and editing. arXiv preprint arXiv:2602.12205 (2026)"},{"key":"13_CR43","unstructured":"Wu, C., et\u00a0al.: Qwen-image technical report. arXiv preprint arXiv:2508.02324 (2025)"},{"key":"13_CR44","unstructured":"Wu, C., et\u00a0al.: Omnigen2: exploration to advanced multimodal generation. arXiv preprint arXiv:2506.18871 (2025)"},{"key":"13_CR45","unstructured":"Wu, K., Jiang, S., Ku, M., Nie, P., Liu, M., Chen, W.: EditReward: a human-aligned reward model for instruction-guided image editing. arXiv preprint arXiv:2509.26346 (2025)"},{"key":"13_CR46","unstructured":"Wu, X., et al.: Human preference score v2: a solid benchmark for evaluating human preferences of text-to-image synthesis. arXiv preprint arXiv:2306.09341 (2023)"},{"key":"13_CR47","unstructured":"Xie, E., et\u00a0al.: SANA: efficient high-resolution image synthesis with linear diffusion transformers. arXiv preprint arXiv:2410.10629 (2024)"},{"key":"13_CR48","doi-asserted-by":"publisher","first-page":"15903","DOI":"10.52202\/075280-0700","volume":"36","author":"J Xu","year":"2023","unstructured":"Xu, J., et al.: ImageReward: learning and evaluating human preferences for text-to-image generation. Adv. Neural. Inf. Process. Syst. 36, 15903\u201315935 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"13_CR49","unstructured":"Xue, Z., et\u00a0al.: DanceGRPO: unleashing GRPO on visual generation. arXiv preprint arXiv:2505.07818 (2025)"},{"key":"13_CR50","doi-asserted-by":"crossref","unstructured":"Ye, Y., et al.: ImgEdit: a unified image editing dataset and benchmark. arXiv preprint arXiv:2505.20275 (2025)","DOI":"10.52202\/085713-4387"},{"key":"13_CR51","doi-asserted-by":"publisher","first-page":"47455","DOI":"10.52202\/079017-1505","volume":"37","author":"T Yin","year":"2024","unstructured":"Yin, T., et al.: Improved distribution matching distillation for fast image synthesis. Adv. Neural. Inf. Process. Syst. 37, 47455\u201347487 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"13_CR52","doi-asserted-by":"crossref","unstructured":"Yin, T., et al.: One-step diffusion with distribution matching distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6613\u20136623 (2024)","DOI":"10.1109\/CVPR52733.2024.00632"},{"key":"13_CR53","doi-asserted-by":"publisher","unstructured":"Zhao, Y., Xu, Y., Xiao, Z., Jia, H., Hou, T.: MobileDiffusion: instant text-to-image generation on mobile devices. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) European Conference on Computer Vision, pp. 225\u2013242. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-73033-7_13","DOI":"10.1007\/978-3-031-73033-7_13"}],"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\/978-3-032-37174-4_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T07:08:19Z","timestamp":1789715299000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37174-4_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032371737","9783032371744"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37174-4_13","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":"19 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"}}]}}