{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T14:04:06Z","timestamp":1779977046287,"version":"3.53.1"},"reference-count":63,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"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":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.neunet.2026.109129","type":"journal-article","created":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T23:27:16Z","timestamp":1779319636000},"page":"109129","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["AnyDesign: Versatile area fashion editing via mask-free diffusion"],"prefix":"10.1016","volume":"203","author":[{"given":"Yunfang","family":"Niu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1282-7310","authenticated-orcid":false,"given":"Dong","family":"Yi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9346-3597","authenticated-orcid":false,"given":"Lingxiang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9918-7937","authenticated-orcid":false,"given":"Jie","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinqiao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109129_bib0001","series-title":"ICCV","first-page":"23336","article-title":"Multimodal garment designer: Human-centric latent diffusion models for fashion image editing","author":"Baldrati","year":"2023"},{"key":"10.1016\/j.neunet.2026.109129_bib0002","series-title":"CVPR","first-page":"22669","article-title":"All are worth words: A vit backbone for diffusion models","author":"Bao","year":"2023"},{"key":"10.1016\/j.neunet.2026.109129_bib0003","series-title":"CVPR","first-page":"5968","article-title":"Person image synthesis via denoising diffusion model","author":"Bhunia","year":"2023"},{"key":"10.1016\/j.neunet.2026.109129_bib0004","series-title":"CVPR","first-page":"18392","article-title":"InstructPix2Pix: Learning to follow image editing instructions","author":"Brooks","year":"2023"},{"key":"10.1016\/j.neunet.2026.109129_bib0005","series-title":"CVPR","first-page":"7291","article-title":"Realtime multi-person 2D pose estimation using part affinity fields","author":"Cao","year":"2017"},{"key":"10.1016\/j.neunet.2026.109129_bib0006","series-title":"ICIP","first-page":"245","article-title":"OpenfashionCLIP: Vision-and-language contrastive learning with open-source fashion data","author":"Cartella","year":"2023"},{"key":"10.1016\/j.neunet.2026.109129_bib0007","doi-asserted-by":"crossref","unstructured":"Chen, J., Yu, J., Ge, C., Yao, L., Xie, E., Wang, Z., Kwok, J., Luo, P., Lu, H., Li, Z. (2024). PixArt-\u03b1: Fast training of diffusion transformer for photorealistic text-to-image synthesis. In ICLR.","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"10.1016\/j.neunet.2026.109129_bib0008","series-title":"CVPR","first-page":"14131","article-title":"Viton-HD: High-resolution virtual try-on via misalignment-aware normalization","author":"Choi","year":"2021"},{"key":"10.1016\/j.neunet.2026.109129_bib0009","series-title":"ECCV","first-page":"206","article-title":"Improving diffusion models for authentic virtual try-on in the wild","author":"Choi","year":"2024"},{"key":"10.1016\/j.neunet.2026.109129_bib0010","series-title":"ICLR","article-title":"DiffEdit: Diffusion-based semantic image editing with mask guidance","author":"Couairon","year":"2023"},{"key":"10.1016\/j.neunet.2026.109129_bib0011","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"NeurIPS"},{"key":"10.1016\/j.neunet.2026.109129_bib0012","series-title":"CVPR","first-page":"12873","article-title":"Taming transformers for high-resolution image synthesis","author":"Esser","year":"2021"},{"key":"10.1016\/j.neunet.2026.109129_bib0013","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106353","article-title":"A novel garment transfer method supervised by distilled knowledge of virtual try-on model","volume":"176","author":"Fang","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109129_bib0014","series-title":"ECCV","first-page":"1","article-title":"Stylegan-human: A data-centric odyssey of human generation","author":"Fu","year":"2022"},{"key":"10.1016\/j.neunet.2026.109129_bib0015","series-title":"ACM MM","first-page":"7599","article-title":"Taming the power of diffusion models for high-quality virtual try-on with appearance flow","author":"Gou","year":"2023"},{"key":"10.1016\/j.neunet.2026.109129_bib0016","series-title":"CVPR","first-page":"7297","article-title":"DensePose: Dense human pose estimation in the wild","author":"G\u00fcler","year":"2018"},{"key":"10.1016\/j.neunet.2026.109129_bib0017","series-title":"Int. Conf. Comput. Vis. Works.","article-title":"The imaterialist fashion attribute dataset","author":"Guo","year":"2019"},{"key":"10.1016\/j.neunet.2026.109129_bib0018","series-title":"ICCV","first-page":"1463","article-title":"Automatic spatially-aware fashion concept discovery","author":"Han","year":"2017"},{"key":"10.1016\/j.neunet.2026.109129_bib0019","series-title":"CVPR","first-page":"7543","article-title":"Viton: An image-based virtual try-on network","author":"Han","year":"2018"},{"key":"10.1016\/j.neunet.2026.109129_bib0020","series-title":"Conference on empirical methods in natural language processing (EMNLP)","first-page":"7514","article-title":"ClipScore: A reference-free evaluation metric for image captioning","author":"Hessel","year":"2021"},{"key":"10.1016\/j.neunet.2026.109129_bib0021","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"NeurIPS"},{"key":"10.1016\/j.neunet.2026.109129_bib0022","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"10.1016\/j.neunet.2026.109129_bib0023","unstructured":"Ho, J., & Salimans, T. (2022). Classifier-free diffusion guidance. arXiv preprint arXiv: 2207.12598."},{"key":"10.1016\/j.neunet.2026.109129_bib0024","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106777","article-title":"PFB-Diff: Progressive feature blending diffusion for text-driven image editing","volume":"181","author":"Huang","year":"2025","journal-title":"Neural Networks"},{"issue":"3","key":"10.1016\/j.neunet.2026.109129_bib0025","first-page":"665","article-title":"An overview of electronic commerce (E-commerce)","volume":"27","author":"Jain","year":"2021","journal-title":"Journal of Contemporary Issues in Business and Government (CIBG)"},{"issue":"9","key":"10.1016\/j.neunet.2026.109129_bib0026","doi-asserted-by":"crossref","first-page":"4538","DOI":"10.1109\/TNNLS.2021.3057892","article-title":"Deep learning for fashion style generation","volume":"33","author":"Jiang","year":"2021","journal-title":"IEEE Transactions on Neural Networks and Learning Systems (TNNLS)"},{"issue":"4","key":"10.1016\/j.neunet.2026.109129_bib0027","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3528223.3530104","article-title":"Text2human: Text-driven controllable human image generation","volume":"41","author":"Jiang","year":"2022","journal-title":"ACM TOG"},{"key":"10.1016\/j.neunet.2026.109129_bib0028","series-title":"CVPR","first-page":"8176","article-title":"Stableviton: Learning semantic correspondence with latent diffusion model for virtual try-on","author":"Kim","year":"2024"},{"key":"10.1016\/j.neunet.2026.109129_bib0029","series-title":"Proceedings of IEEE\/CVF winter conference on applications of computer vision (WACV)","first-page":"848","article-title":"Leveraging off-the-shelf diffusion model for multi-attribute fashion image manipulation","author":"Kong","year":"2023"},{"key":"10.1016\/j.neunet.2026.109129_bib0030","series-title":"ICCV","first-page":"19721","article-title":"Flowedit: Inversion-free text-based editing using pre-trained flow models","author":"Kulikov","year":"2025"},{"key":"10.1016\/j.neunet.2026.109129_bib0031","series-title":"Proceedings of international conference on machine learning (ICML)","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"10.1016\/j.neunet.2026.109129_bib0032","series-title":"ICCV","first-page":"1096","article-title":"DeepFashion: Powering robust clothes recognition and retrieval with rich annotations","author":"Liu","year":"2016"},{"key":"10.1016\/j.neunet.2026.109129_bib0033","series-title":"ICLR","article-title":"SDEdit: Guided image synthesis and editing with stochastic differential equations","author":"Meng","year":"2022"},{"key":"10.1016\/j.neunet.2026.109129_bib0034","series-title":"CVPR","first-page":"2231","article-title":"Dress code: High-resolution multi-category virtual try-on","author":"Morelli","year":"2022"},{"key":"10.1016\/j.neunet.2026.109129_bib0035","series-title":"Proceedings of international conference on machine learning (ICML)","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2022"},{"key":"10.1016\/j.neunet.2026.109129_bib0036","series-title":"ICCV","first-page":"2085","article-title":"Styleclip: Text-driven manipulation of stylegan imagery","author":"Patashnik","year":"2021"},{"key":"10.1016\/j.neunet.2026.109129_bib0037","series-title":"ICCV","first-page":"4195","article-title":"Scalable diffusion models with transformers","author":"Peebles","year":"2023"},{"key":"10.1016\/j.neunet.2026.109129_bib0038","article-title":"Fice: Text-conditioned fashion-image editing with guided gan inversion","volume":"158","author":"Pernu\u0161","year":"2025","journal-title":"PR"},{"key":"10.1016\/j.neunet.2026.109129_bib0039","series-title":"ICLR","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2024"},{"key":"10.1016\/j.neunet.2026.109129_bib0040","series-title":"CVPR","first-page":"10684","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2022"},{"key":"10.1016\/j.neunet.2026.109129_bib0041","unstructured":"Rostamzadeh, N., Hosseini, S., Boquet, T., Stokowiec, W., Zhang, Y., Jauvin, C., & Pal, C. (2018). Fashion-gen: The generative fashion dataset and challenge. arXiv preprint arXiv: 1806.08317."},{"key":"10.1016\/j.neunet.2026.109129_bib0042","unstructured":"RunwayML (2022). Stable diffusion inpainting. https:\/\/huggingface.co\/runwayml\/stable-diffusion-inpainting."},{"key":"10.1016\/j.neunet.2026.109129_bib0043","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"NeurIPS"},{"key":"10.1016\/j.neunet.2026.109129_bib0044","series-title":"Proceedings of international conference on machine learning (ICML)","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"Sohl-Dickstein","year":"2015"},{"key":"10.1016\/j.neunet.2026.109129_bib0045","series-title":"The fundamentals of fashion design","author":"Sorger","year":"2017"},{"key":"10.1016\/j.neunet.2026.109129_bib0046","series-title":"ACM MM","first-page":"8433","article-title":"SGDiff: A style guided diffusion model for fashion synthesis","author":"Sun","year":"2023"},{"key":"10.1016\/j.neunet.2026.109129_bib0047","series-title":"ICLR","first-page":"1","article-title":"Demystifying MMD GANs","author":"Sutherland","year":"2018"},{"key":"10.1016\/j.neunet.2026.109129_bib0048","series-title":"Proc. AAAI Conf. Artif. Intell.","first-page":"9971","article-title":"De-Net: Dynamic text-guided image editing adversarial networks","volume":"37","author":"Tao","year":"2023"},{"key":"10.1016\/j.neunet.2026.109129_bib0049","series-title":"CVPR","first-page":"16515","article-title":"Df-GAN: A simple and effective baseline for text-to-image synthesis","author":"Tao","year":"2022"},{"key":"10.1016\/j.neunet.2026.109129_bib0050","unstructured":"Wan, Z., Hu, D., Cheng, W., Chen, T., Wang, Z., Liu, F., Liu, T., Gong, M. et al. (2025). MF-viton: High-fidelity mask-free virtual try-on with minimal input. arXiv preprint arXiv: 2503.08650."},{"key":"10.1016\/j.neunet.2026.109129_bib0051","series-title":"Proc. AAAI Conf. Artif. Intell.","first-page":"10198","article-title":"Texfit: Text-driven fashion image editing with diffusion models","volume":"38","author":"Wang","year":"2024"},{"issue":"4","key":"10.1016\/j.neunet.2026.109129_bib0052","first-page":"600","article-title":"Image quality assessment: From error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE TIP"},{"key":"10.1016\/j.neunet.2026.109129_bib0053","series-title":"CVPR","first-page":"11307","article-title":"Fashion IQ: A new dataset towards retrieving images by natural language feedback","author":"Wu","year":"2021"},{"key":"10.1016\/j.neunet.2026.109129_bib0054","series-title":"ICME","first-page":"2105","article-title":"UFS-Net: Unsupervised network for fashion style editing and generation","author":"Wu","year":"2023"},{"key":"10.1016\/j.neunet.2026.109129_bib0055","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1016\/j.neunet.2023.08.038","article-title":"Word self-update contrastive adversarial networks for text-to-image synthesis","volume":"167","author":"Xiao","year":"2023","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109129_bib0056","series-title":"CVPR","first-page":"23550","article-title":"GP-Vton: Towards general purpose virtual try-on via collaborative local-flow global-parsing learning","author":"Xie","year":"2023"},{"key":"10.1016\/j.neunet.2026.109129_bib0057","first-page":"77632","article-title":"SA-Solver: Stochastic Adams solver for fast sampling of diffusion models","volume":"36","author":"Xue","year":"2023","journal-title":"NeurIPS"},{"key":"10.1016\/j.neunet.2026.109129_bib0058","series-title":"ICCV","first-page":"833","article-title":"Cross-modal contrastive learning for text-to-image generation","author":"Zhang","year":"2021"},{"key":"10.1016\/j.neunet.2026.109129_bib0059","series-title":"ICCV","first-page":"5907","article-title":"StackGAN: Text to photo-realistic image synthesis with stacked generative adversarial networks","author":"Zhang","year":"2017"},{"key":"10.1016\/j.neunet.2026.109129_bib0060","series-title":"ICCV","first-page":"3836","article-title":"Adding conditional control to text-to-image diffusion models","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neunet.2026.109129_bib0061","series-title":"ICCV","first-page":"586","article-title":"The unreasonable effectiveness of deep features as a perceptual metric","author":"Zhang","year":"2018"},{"key":"10.1016\/j.neunet.2026.109129_bib0062","series-title":"CVPR","first-page":"26399","article-title":"Boow-VTON: Boosting in-the-wild virtual try-on via mask-free pseudo data training","author":"Zhang","year":"2025"},{"issue":"16","key":"10.1016\/j.neunet.2026.109129_bib0063","doi-asserted-by":"crossref","DOI":"10.1142\/S0218001421530086","article-title":"FocusGAN: Preserving background in text-guided image editing","volume":"35","author":"Zhao","year":"2021","journal-title":"International Journal of Pattern Recognition and Artificial Intelligence (IJPRAI)"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026005903?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026005903?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T13:20:46Z","timestamp":1779974446000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026005903"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":63,"alternative-id":["S0893608026005903"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109129","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"AnyDesign: Versatile area fashion editing via mask-free diffusion","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109129","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"109129"}}