{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:22:32Z","timestamp":1778048552047,"version":"3.51.4"},"reference-count":55,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00742","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"7689-7698","source":"Crossref","is-referenced-by-count":0,"title":["Leveraging Semantic Attribute Binding for Free-Lunch Color Control in Diffusion Models"],"prefix":"10.1109","author":[{"given":"H\u00e9ctor","family":"Laria","sequence":"first","affiliation":[{"name":"Computer Vision Center,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexandra","family":"Gomez-Villa","sequence":"additional","affiliation":[{"name":"Computer Vision Center,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiang","family":"Qin","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad Atif","family":"Butt","sequence":"additional","affiliation":[{"name":"Computer Vision Center,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bogdan","family":"Raducanu","sequence":"additional","affiliation":[{"name":"Computer Vision Center,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Javier","family":"Vazquez-Corral","sequence":"additional","affiliation":[{"name":"Computer Vision Center,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joost","family":"van de Weijer","sequence":"additional","affiliation":[{"name":"Computer Vision Center,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Wang","sequence":"additional","affiliation":[{"name":"Computer Vision Center,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Basic color terms: Their universality and evolution","author":"Berlin","year":"1991"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_26"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICICML60161.2023.10424833"},{"key":"ref4","article-title":"Subject-driven text-to-image generation via apprenticeship learning","volume-title":"NeurIPS","author":"Chen"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00391"},{"key":"ref6","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"ICML","author":"Esser"},{"key":"ref7","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"ICLR","author":"Gal"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00694"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02361-2"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02280"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01737"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/iccvw69036.2025.00206"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00221"},{"key":"ref14","article-title":"Prompt-to-prompt image editing with cross attention control","volume-title":"ICLR","author":"Hertz"},{"key":"ref15","author":"Ilharco","year":"2021","journal-title":"Open clip"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2005.12.007"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref19","volume-title":"Flux","year":"2024"},{"key":"ref20","article-title":"Blip-diffusion: Pre-trained subject representation for controllable text-to-image generation and editing","volume-title":"NeurIPS","author":"Li"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-72667-5_8","article-title":"ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback","volume-title":"ECCV","author":"Li"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.26599\/cvm.2025.9450462"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-025-1562-4"},{"key":"ref25","article-title":"DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps","volume-title":"NeurIPS","author":"Lu"},{"key":"ref26","article-title":"SDEdit: Guided image synthesis and editing with stochastic differential equations","volume-title":"ICLR","author":"Meng"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2227726"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1117\/1.2181547"},{"key":"ref31","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"ICLR","author":"Podell"},{"key":"ref32","article-title":"Free-lunch color-texture disentanglement for stylized image generation","volume-title":"NeurIPS","author":"Qin"},{"key":"ref33","article-title":"Learning transferable visual models from natural language super-vision","volume-title":"ICML","author":"Radford"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91838-4_4"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref38","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"NeurIPS","author":"Saharia"},{"key":"ref39","volume-title":"Deepfloyd-if","author":"Shonenkov","year":"2023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1108\/00251740610673332"},{"key":"ref41","article-title":"Styledrop: Text-to-image generation in any style","volume-title":"NeurIPS","author":"Sohn"},{"key":"ref42","article-title":"Denoising Diffusion Implicit Models","volume-title":"ICLR","author":"Song"},{"key":"ref43","doi-asserted-by":"crossref","DOI":"10.1109\/ICME57554.2024.10687547","article-title":"Iterinv: Iterative inversion for pixel-level t2i models","volume-title":"Neurips 2023 workshop on Diffusion Models","author":"Tang"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.4324\/9781315128948-7"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2009.2019809"},{"key":"ref46","article-title":"Instantstyle: Free lunch towards style-preserving in text-to-image generation","author":"Wang","year":"2024"},{"key":"ref47","article-title":"Instantstyleplus: Style transfer with content-preserving in text-to-image generation","author":"Wang","year":"2024"},{"key":"ref48","article-title":"Dynamic prompt learning: Addressing cross-attention leakage for text-based image editing","volume-title":"NeurIPS","author":"Wang"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00432"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28364"},{"key":"ref51","article-title":"Csgo: Content-style composition in text-to-image generation","author":"Xing","year":"2024"},{"key":"ref52","article-title":"Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref54","article-title":"Forgedit: Text guided image editing via learning and forgetting","author":"Zhang","year":"2023"},{"key":"ref55","article-title":"Uni-controlnet: All-in-one control to text-to-image diffusion models","volume-title":"NeurIPS","author":"Zhao"}],"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\/11492254.pdf?arnumber=11492254","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:06:47Z","timestamp":1778047607000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492254\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00742","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}