{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:22:09Z","timestamp":1778048529513,"version":"3.51.4"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00793","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"8220-8230","source":"Crossref","is-referenced-by-count":0,"title":["VitaGlyph: Vitalizing Artistic Typography with Flexible Dual-branch Diffusion Models"],"prefix":"10.1109","author":[{"given":"Kailai","family":"Feng","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yabo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haodong","family":"Yu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhilong","family":"Ji","sequence":"additional","affiliation":[{"name":"Tomorrow Advancing Life"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinfeng","family":"Bai","sequence":"additional","affiliation":[{"name":"Tomorrow Advancing Life"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongzhi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wangmeng","family":"Zuo","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Achiam","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00217"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1561\/116.20240037"},{"key":"ref4","author":"Balaji","year":"2022","journal-title":"ediff-i: Text-to-image diffusion models with an ensemble of expert denoisers"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_23"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15804\/tner.23.72.2.15"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687898"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611929"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-industry.23"},{"key":"ref11","volume-title":"Metadesigner: Advancing artistic typography through ai-driven, user-centric, and multilingual wordart synthesis","author":"He","year":"2024"},{"key":"ref12","first-page":"30","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref13","author":"Hu","year":"2021","journal-title":"Lora: Low-rank adaptation of large language models"},{"key":"ref14","volume-title":"Composer: Creative and controllable image synthesis with composable conditions","author":"Huang","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-92808-6_18"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3592123"},{"key":"ref17","author":"Jiang","year":"2024","journal-title":"Mc 2: Multi-concept guidance for customized multi-concept generation"},{"key":"ref18","volume-title":"Deepfloyd if","year":"2023"},{"key":"ref19","author":"Lian","year":"2023","journal-title":"Llm-grounded diffusion: Enhancing prompt understanding of text-to-image diffusion models with large language models"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611930"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_1"},{"key":"ref23","first-page":"57500","article-title":"Cones 2: Customizable image synthesis with multiple subjects","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Liu"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51701.2025.01372"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3209870"},{"key":"ref26","volume-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","author":"Meng","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00860"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73636-0_18"},{"key":"ref30","year":"2024","journal-title":"Chatgpt"},{"key":"ref31","volume-title":"Gpt-4o","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-70536-6_4"},{"key":"ref33","author":"Poole","year":"2022","journal-title":"Dreamfusion: Text-to-3d using 2d diffusion"},{"key":"ref34","author":"Pu","year":"2024","journal-title":"Dynamic texture transfer using patchmatch and transformers"},{"key":"ref35","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref36","first-page":"36","article-title":"Linguistic binding in diffusion models: Enhancing attribute correspondence through attention map alignment","author":"Rassin","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref38","author":"Song","year":"2020","journal-title":"Denoising diffusion implicit models"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00041"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1002\/tesq.274"},{"key":"ref41","author":"Wan","year":"2025","journal-title":"Wan: Open and advanced large-scale video generative models"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618208"},{"key":"ref43","author":"Wu","year":"2025","journal-title":"Qwen-image technical report"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642185"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3286392"},{"key":"ref46","article-title":"Mastering text-to-image diffusion: Recaptioning, planning, and generating with multi-modal llms","volume-title":"Forty-first International Conference on Machine Learning","author":"Yang"},{"key":"ref47","first-page":"36","article-title":"Glyphcontrol: Glyph conditional control for visual text generation","author":"Yang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref49","author":"Zhang","year":"2024","journal-title":"Realcompo: Dynamic equilibrium between realism and compositionality improves text-to-image diffusion models"},{"key":"ref50","author":"Zhang","year":"2023","journal-title":"Controlvideo: Training-free controllable text-to-video generation"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_13"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492593.pdf?arnumber=11492593","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:09:26Z","timestamp":1778047766000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492593\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00793","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}