{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:18:50Z","timestamp":1777889930728,"version":"3.51.4"},"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\/iccv51701.2025.01534","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"16524-16534","source":"Crossref","is-referenced-by-count":0,"title":["Generating Multi-Image Synthetic Data for Text-to-Image Customization"],"prefix":"10.1109","author":[{"given":"Nupur","family":"Kumari","sequence":"first","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xi","family":"Yin","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun-Yan","family":"Zhu","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ishan","family":"Misra","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Samaneh","family":"Azadi","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"LAION AI. Laion-aesthetics predictor","year":"2022"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3618322"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref5","article-title":"Re-imagen: Retrieval-augmented text-to-image generator","volume-title":"International Conference on Learning Representations (ICLR)","author":"Chen","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1318"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1554"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73383-3_6"},{"key":"ref11","article-title":"Diffusion models beat gans on image synthesis","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Dhariwal","year":"2021"},{"key":"ref12","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"International Conference on Machine Learning (ICML)","author":"Esser","year":"2024"},{"key":"ref14","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"International Conference on Learning Representations (ICLR)","author":"Gal","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00694"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_23"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00673"},{"key":"ref18","article-title":"Prompt-to-prompt image editing with cross attention control","volume-title":"International Conference on Learning Representations (ICLR)","author":"Hertz","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00457"},{"key":"ref20","article-title":"Denoising diffusion probabilistic models","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Ho","year":"2020"},{"key":"ref21","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations (ICLR)","author":"Edward","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01866"},{"key":"ref23","article-title":"Creativesynth: Creative blending and synthesis of visual arts based on multimodal diffusion","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1926"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02282"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref29","article-title":"Black Forest Labs","volume-title":"Flux","year":"2024"},{"key":"ref30","volume-title":"Black Forest Labs. Flux-depth","year":"2024"},{"key":"ref31","article-title":"Blip-diffusion: Pre-trained subject representation for controllable text-toimage generation and editing","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Li","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00532"},{"key":"ref33","article-title":"Maximilian Nickel, and Matt Le. Flow matching for generative modeling","author":"Lipman","year":"2022","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"ref35","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","volume-title":"International Conference on Learning Representations (ICLR)","author":"Liu","year":"2023"},{"key":"ref36","article-title":"Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Lu","year":"2022"},{"key":"ref37","article-title":"Scalable 3d captioning with pretrained models","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Luo","year":"2024"},{"key":"ref38","article-title":"Subjectdiffusion: Open domain personalized text-to-image generation without test-time fine-tuning","author":"Ma","year":"2024","journal-title":"ACM SIGGRAPH"},{"key":"ref39","article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","volume-title":"International Conference on Learning Representations (ICLR)","author":"Meng","year":"2022"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref41","article-title":"Improved denoising diffusion probabilistic models","volume-title":"International Conference on Machine Learning (ICML)","author":"Quinn Nichol","year":"2021"},{"key":"ref42","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"Transactions on Machine Learning Research (TMLR)"},{"key":"ref43","article-title":"Kosmos-g: Generating images in context with multimodal large language models","volume-title":"International Conference on Learning Representations (ICLR)","author":"Pan","year":"2024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591513"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3757377.3763867"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref47","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning (ICML)","author":"Radford","year":"2021"},{"key":"ref48","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"Grounded sam: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3659578"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref54","article-title":"Progressive distillation for fast sampling of diffusion models","volume-title":"International Conference on Learning Representations (ICLR)","author":"Salimans","year":"2022"},{"key":"ref55","article-title":"Stylegan-t: Unlocking the power of gans for fast large-scale text-to-image synthesis","volume-title":"International Conference on Machine Learning (ICML)","author":"Sauer","year":"2023"},{"key":"ref56","article-title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021","journal-title":"arXiv preprint"},{"key":"ref57","article-title":"Zero123++: a single image to consistent multi-view diffusion base model","author":"Shi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref58","article-title":"Mvdream: Multi-view diffusion for 3d generation","volume-title":"International Conference on Learning Representations (ICLR)","author":"Shi","year":"2024"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73661-2_7"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01365"},{"key":"ref62","article-title":"Ominicontrol: Minimal and universal control for diffusion transformer","author":"Tan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591506"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3658157"},{"key":"ref65","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref66","article-title":"p+: Extended textual conditioning in text-to-image generation","author":"Voynov","year":"2023","journal-title":"arXiv preprint"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref68","volume-title":"Dreambooth on stable diffusion","author":"Xiao","year":"2022"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02227-z"},{"key":"ref70","volume-title":"XLabs-AI. Flux ip-adapter","year":"2024"},{"key":"ref71","article-title":"Motion-conditioned image animation for video editing","author":"Yan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref72","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref73","article-title":"Scaling autoregressive models for content-rich text-to-image generation","volume-title":"International Conference on Machine Learning (ICML)","author":"Yu","year":"2022"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00648"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/3618342"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref78","article-title":"Storydiffusion: Consistent self-attention for long-range image and video generation","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Zhou","year":"2024"}],"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\/11445396.pdf?arnumber=11445396","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:23:51Z","timestamp":1777613031000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445396\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":78,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01534","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}