{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:19:37Z","timestamp":1778080777167,"version":"3.51.4"},"reference-count":63,"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\/iccv51701.2025.01482","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"15971-15981","source":"Crossref","is-referenced-by-count":1,"title":["Magic Insert: Style-Aware Drag-And-Drop"],"prefix":"10.1109","author":[{"given":"Nataniel","family":"Ruiz","sequence":"first","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanzhen","family":"Li","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Neal","family":"Wadhwa","sequence":"additional","affiliation":[{"name":"Google"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yael","family":"Pritch","sequence":"additional","affiliation":[{"name":"Google"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Rubinstein","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David E.","family":"Jacobs","sequence":"additional","affiliation":[{"name":"Google"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shlomi","family":"Fruchter","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618173"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25099"},{"key":"ref5","article-title":"Muse: Text-to-image generation via masked generative transformers","author":"Chang","year":"2023","journal-title":"arXiv preprint"},{"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":"10.1007\/978-3-031-72684-2_11"},{"key":"ref9","article-title":"An image is worth one word: Personalizing text-toimage generation using textual inversion","author":"Gal","year":"2022","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3592133"},{"key":"ref11","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref12","article-title":"Swapanything: Enabling arbitrary object swapping in personalized visual editing","author":"Gu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00457"},{"key":"ref14","author":"Ho","year":"2020","journal-title":"Denoising diffusion probabilistic models."},{"key":"ref15","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Image fine-grained inpainting","author":"Hui","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073659"},{"key":"ref18","article-title":"Context-aware synthesis and placement of object instances","volume":"abs\/1812.02350","author":"Lee","year":"2018","journal-title":"ArXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_6"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_43"},{"key":"ref21","article-title":"Dreamcom: Finetuning text-guided inpainting model for image composition","author":"Lu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00218"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref24","article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","author":"Meng","year":"2021","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","author":"Meng","year":"2021","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28231"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-67070-2_43"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref29","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00223"},{"key":"ref31","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00027"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref34","article-title":"Rb-modulation: Training-free personalization of diffusion models using stochastic optimal control","author":"Rout","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00624"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00661"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00416"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_24"},{"key":"ref42","author":"Sohl-Dickstein","year":"2015","journal-title":"Deep unsupervised learning using nonequilibrium thermodynamics."},{"key":"ref43","article-title":"Styledrop: Text-to-image generation in any style. In 37th Conference on Neural Information Processing Systems (NeurIPS)","volume-title":"Neural Information Processing Systems Foundation","author":"Sohn"},{"key":"ref44","article-title":"Measuring style similarity in diffusion models","author":"Somepalli","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","author":"Song","year":"2022","journal-title":"Denoising diffusion implicit models."},{"key":"ref46","article-title":"Objectstitch: Generative object compositing","author":"Song","year":"2022","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00769"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3658237"},{"key":"ref50","article-title":"$p+$: Extended textual conditioning in text-toimage generation","author":"Voynov","year":"2023","journal-title":"arXiv preprint"},{"key":"ref51","article-title":"Instantstyle: Free lunch towards stylepreserving in text-to-image generation","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"Instantid: Zero-shot identity-preserving generation in seconds","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01761"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680848"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_7"},{"key":"ref56","article-title":"Nuwa-infinity: Autoregressive over autoregressive generation for infinite visual synthesis","author":"Wu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref57","article-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","volume":"36","author":"Xu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"ref59","author":"Ye","year":"2023","journal-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models."},{"key":"ref60","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00158"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-019-0136-1"}],"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\/11444771.pdf?arnumber=11444771","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:30:23Z","timestamp":1777613423000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444771\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01482","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}