Personalized Adaptive Generation of Peking Opera Facial Makeup Using Generative Artificial Intelligence

Personalized Adaptive Generation of Peking Opera Facial Makeup Using Generative Artificial Intelligence | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article Personalized Adaptive Generation of Peking Opera Facial Makeup Using Generative Artificial Intelligence Ge Hongru, Zhang Weilaing, Sun Xingxing, Fan Ziqi, Xian Qingchi This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6067496/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 23 Nov, 2025 Read the published version in Scientific Reports → Version 1 posted 14 You are reading this latest preprint version Abstract The intelligent generation of Peking Opera facial makeup serves as a representative case of stylized image generation, offering valuable insights into the integration of artificial intelligence with traditional cultural expressions. This study focuses on the intelligent generation of Peking Opera facial makeup images by addressing these key challenges. First, two random number generators are designed to independently generate colors for bright and dark regions; Second, multiple attention mechanism enhanced U-Net models of the Stable Diffusion model are employed, which refine the generation process by capturing fine details and improving authenticity. Third, a labeled dataset of Peking Opera facial makeup is used to train a text-guided image generation model. Finally, LoRA fine-tuning network is implemented to optimize the model’s performance, accelerating the generation process while maintaining image quality. In subsequent experiments, the proposed model was compared with SOTA models. The proposed model achieved scores of 16.34, 9.44, 0.4912, and 0.2917 on the FID, KID, SSIM, and MS-SSIM metrics, surpassing other SOTA models. The improved Stable Diffusion model presented in this study effectively enhances both the quality and speed of Peking Opera facial makeup generation. Physical sciences/Mathematics and computing/Computer science Physical sciences/Mathematics and computing/Software image generation Peking Opera facial makeup LoRA Stable Diffusion U-Net text-to-image Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 23 Nov, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 21 Jul, 2025 Reviews received at journal 15 Jul, 2025 Reviewers agreed at journal 06 Jul, 2025 Reviewers agreed at journal 04 Jul, 2025 Reviewers agreed at journal 24 Jun, 2025 Reviewers agreed at journal 27 May, 2025 Reviews received at journal 26 May, 2025 Reviewers agreed at journal 26 May, 2025 Reviewers agreed at journal 24 Apr, 2025 Reviewers invited by journal 21 Apr, 2025 Editor invited by journal 15 Apr, 2025 Editor assigned by journal 20 Mar, 2025 Submission checks completed at journal 18 Mar, 2025 First submitted to journal 18 Mar, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-6067496","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":445994502,"identity":"878263c9-ce10-4211-923c-7fb0dfc83866","order_by":0,"name":"Ge Hongru","email":"","orcid":"","institution":"Kangwon National University","correspondingAuthor":false,"prefix":"","firstName":"Ge","middleName":"","lastName":"Hongru","suffix":""},{"id":445994503,"identity":"316ca791-0569-4355-ad66-609ab87dbd40","order_by":1,"name":"Zhang Weilaing","email":"","orcid":"","institution":"Changchun Sci-Tech University","correspondingAuthor":false,"prefix":"","firstName":"Zhang","middleName":"","lastName":"Weilaing","suffix":""},{"id":445994504,"identity":"1adb2ce8-e944-4c1a-8cf9-0a8de2c8fadc","order_by":2,"name":"Sun Xingxing","email":"","orcid":"","institution":"Kangwon National University","correspondingAuthor":false,"prefix":"","firstName":"Sun","middleName":"","lastName":"Xingxing","suffix":""},{"id":445994506,"identity":"1740df55-5760-4ffd-858b-bdf9cad14f30","order_by":3,"name":"Fan Ziqi","email":"","orcid":"","institution":"Sichuan Provincial Architectural Design and Research Institute Co","correspondingAuthor":false,"prefix":"","firstName":"Fan","middleName":"","lastName":"Ziqi","suffix":""},{"id":445994509,"identity":"a28a97cb-148d-4e33-87df-7226d9e93f7c","order_by":4,"name":"Xian Qingchi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5ElEQVRIiWNgGAWjYDACZiBmbJDgYWNmPmDwwcDGjmgtcvzsbAmFMwrSkomzibGBwViyn8fgM8+HQ0A2AcB3nPfwi587LBI3HGYw3GxjcICZgf3w0Q34tEge5kuz7D0jAdKSbJxjcIePgSct7QY+LQaHecyMGdvAWo4BtTxjZpDgMSNWC2P7bwuDw6DQI6jF+DFQi7FkMzODMQMxWiSBtjD2tgEDmZmNwbDHIC2ZjZBf+M6fMf7ws62Oh43//AeDH39s7PjZDx/Dq4XhAAObBIoAG17lEC3MHwgqGgWjYBSMgpENAFJqSR7IB96rAAAAAElFTkSuQmCC","orcid":"","institution":"Kangwon National University","correspondingAuthor":true,"prefix":"","firstName":"Xian","middleName":"","lastName":"Qingchi","suffix":""}],"badges":[],"createdAt":"2025-02-20 01:08:26","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6067496/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6067496/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-28460-1","type":"published","date":"2025-11-23T15:57:47+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":96650413,"identity":"813bb57d-b1aa-4f0e-8884-dcbbf8bc8984","added_by":"auto","created_at":"2025-11-24 16:12:04","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1293154,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6067496/v1_covered_348b2c4b-c631-49fc-91f6-a3a0efe007fb.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Personalized Adaptive Generation of Peking Opera Facial Makeup Using Generative Artificial Intelligence","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"image generation, Peking Opera facial makeup, LoRA, Stable Diffusion, U-Net, text-to-image","lastPublishedDoi":"10.21203/rs.3.rs-6067496/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6067496/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe intelligent generation of Peking Opera facial makeup serves as a representative case of stylized image generation, offering valuable insights into the integration of artificial intelligence with traditional cultural expressions. This study focuses on the intelligent generation of Peking Opera facial makeup images by addressing these key challenges. First, two random number generators are designed to independently generate colors for bright and dark regions; Second, multiple attention mechanism enhanced U-Net models of the Stable Diffusion model are employed, which refine the generation process by capturing fine details and improving authenticity. Third, a labeled dataset of Peking Opera facial makeup is used to train a text-guided image generation model. Finally, LoRA fine-tuning network is implemented to optimize the model\u0026rsquo;s performance, accelerating the generation process while maintaining image quality. In subsequent experiments, the proposed model was compared with SOTA models. The proposed model achieved scores of 16.34, 9.44, 0.4912, and 0.2917 on the FID, KID, SSIM, and MS-SSIM metrics, surpassing other SOTA models. The improved Stable Diffusion model presented in this study effectively enhances both the quality and speed of Peking Opera facial makeup generation.\u003c/p\u003e","manuscriptTitle":"Personalized Adaptive Generation of Peking Opera Facial Makeup Using Generative Artificial Intelligence","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-23 08:34:40","doi":"10.21203/rs.3.rs-6067496/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-07-21T10:35:58+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-07-15T12:50:23+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"87606908874644129910757651032505268686","date":"2025-07-06T08:55:51+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"61747970109952125464514394632947770934","date":"2025-07-04T15:23:25+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"59273073680059099987055317561839796722","date":"2025-06-25T00:42:43+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"188114747151888508098937742269078105383","date":"2025-05-27T07:29:45+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-27T03:46:46+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"176271648725733919194291727571278143619","date":"2025-05-27T03:28:55+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"186424575163354575524957664884158902550","date":"2025-04-24T04:53:44+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-04-22T01:27:00+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-04-15T21:13:03+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-03-20T10:01:45+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-03-18T11:39:19+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-03-18T11:38:12+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"36c05930-0127-48cd-a9c9-7056ac2dbc68","owner":[],"postedDate":"April 23rd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":47472077,"name":"Physical sciences/Mathematics and computing/Computer science"},{"id":47472078,"name":"Physical sciences/Mathematics and computing/Software"}],"tags":[],"updatedAt":"2025-11-24T16:07:59+00:00","versionOfRecord":{"articleIdentity":"rs-6067496","link":"https://doi.org/10.1038/s41598-025-28460-1","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-11-23 15:57:47","publishedOnDateReadable":"November 23rd, 2025"},"versionCreatedAt":"2025-04-23 08:34:40","video":"","vorDoi":"10.1038/s41598-025-28460-1","vorDoiUrl":"https://doi.org/10.1038/s41598-025-28460-1","workflowStages":[]},"version":"v1","identity":"rs-6067496","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6067496","identity":"rs-6067496","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}