{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T16:16:47Z","timestamp":1784391407435,"version":"3.55.0"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100012401","name":"Beijing Science and Technology Planning Project","doi-asserted-by":"publisher","award":["Z231100005923033"],"award-info":[{"award-number":["Z231100005923033"]}],"id":[{"id":"10.13039\/501100012401","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L221013"],"award-info":[{"award-number":["L221013"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Science and Technology Council, Taiwan","award":["113-2221-E-006-161-MY3"],"award-info":[{"award-number":["113-2221-E-006-161-MY3"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Visual. Comput. Graphics"],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tvcg.2025.3570771","type":"journal-article","created":{"date-parts":[[2025,5,16]],"date-time":"2025-05-16T13:44:04Z","timestamp":1747403044000},"page":"8425-8438","source":"Crossref","is-referenced-by-count":9,"title":["CreativeSynth: Cross-Art-Attention for Artistic Image Synthesis With Multimodal Diffusion"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1627-6584","authenticated-orcid":false,"given":"Nisha","family":"Huang","sequence":"first","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6502-145X","authenticated-orcid":false,"given":"Weiming","family":"Dong","sequence":"additional","affiliation":[{"name":"MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6433-2678","authenticated-orcid":false,"given":"Yuxin","family":"Zhang","sequence":"additional","affiliation":[{"name":"MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3975-2483","authenticated-orcid":false,"given":"Fan","family":"Tang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7703-9315","authenticated-orcid":false,"given":"Ronghui","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8243-9513","authenticated-orcid":false,"given":"Chongyang","family":"Ma","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0403-1923","authenticated-orcid":false,"given":"Xiu","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6699-2944","authenticated-orcid":false,"given":"Tong-Yee","family":"Lee","sequence":"additional","affiliation":[{"name":"National Cheng Kung University, Tainan, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8343-9665","authenticated-orcid":false,"given":"Changsheng","family":"Xu","sequence":"additional","affiliation":[{"name":"MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591506"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3592133"},{"key":"ref4","first-page":"2023","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gal"},{"key":"ref5","first-page":"26291","article-title":"Dynamic prompt learning: Addressing cross-attention leakage for text-based image editing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Yang","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref7","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022"},{"key":"ref8","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2017.2660488"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.3032734"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2019.2908166"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3357568"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0371-3"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref15","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Podell","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2019.2921336"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073683"},{"key":"ref18","first-page":"386","article-title":"Universal style transfer via feature transforms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00603"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16208"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-024-0413-5"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00662"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3342645"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00092"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530736"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01104"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00978"},{"key":"ref28","first-page":"66860","article-title":"StyleDrop: Text-to-image synthesis of any style","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sohn","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref30","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh","year":"2021"},{"key":"ref31","first-page":"14866","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Razavi","year":"2019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00457"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548282"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3618342"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref39","first-page":"2021","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song"},{"key":"ref40","article-title":"IP-Adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref43","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref44","article-title":"Image mixer","author":"Pinkney","year":"2024"},{"key":"ref45","first-page":"2024","article-title":"Kosmos-G: Generating images in context with multimodal large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Pan"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00713"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref48","article-title":"Aesthetic predictor","author":"Beaumont","year":"2024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2831899"},{"key":"ref50","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"}],"container-title":["IEEE Transactions on Visualization and Computer Graphics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/2945\/11151252\/11006017.pdf?arnumber=11006017","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T22:52:07Z","timestamp":1757371927000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11006017\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":50,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tvcg.2025.3570771","relation":{},"ISSN":["1077-2626","1941-0506","2160-9306"],"issn-type":[{"value":"1077-2626","type":"print"},{"value":"1941-0506","type":"electronic"},{"value":"2160-9306","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}