[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85830-en":3,"doc-seo-85830-105":29,"detail-sidebar-cat-0-en-105":83},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},85830,8796095461610,"Oliver","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","EmoStyle Affective Conditioning of Style-Specialist Experts for Emotional Image Generation","Emotion-aware artistic image generation must align the output with the input prompt, adhere to a requested artistic style, and express a target emotion. The core challenge is the control gap: fine-grained visual and affective attributes are annotated in training but missing at test time. EmoStyle addresses this by converting prompts into a structured generation state, encoding LLM-predicted affective cues into an affective condition vector, and injecting it into denoising via AdaLN-style modulation. Style-dependent rendering is handled with style-bucket LoRA experts, followed by VLM-guided candidate selection. In AffectiveArt Challenge 2026 Track 1, the submission achieved first place.","EmoStyle: Affective Conditioning of Style-Specialist Experts for  \nEmotional Image Generation  \nDexiang Hong  \n[hongdexiang@mail.ustc.edu.cn](hongdexiang@mail.ustc.edu.cn)  \nUniversity of Science and Technology of China HeFei, China  \nYijie Guo  \n[guoyijie@ustc.edu](guoyijie@ustc.edu)  \nUniversity of Science and Technology of China HeFei, China  \nWeidong Chen✉  \n[chenweidong@ustc.edu.cn](chenweidong@ustc.edu.cn)  \nUniversity of Science and Technology of China HeFei, China  \nXinyan Liu  \n[xinyliu@hit.edu.cn](xinyliu@hit.edu.cn)  \nHarbin Institute of Technology,  \nWeiHai  \nWeiHai, China  \nZixuan Zou  \n[zouzixuan@hit.edu.cn](zouzixuan@hit.edu.cn)  \nHarbin Institute of Technology,  \nWeiHai  \nWeiHai, China  \nZhendong Mao  \n[zdmao@ustc.edu.cn](zdmao@ustc.edu.cn)  \nUniversity of Science and Technology of China HeFei, China  \narXiv :2607 . 10165v1 [ cs .CV] 11 Jul 2026  \nYongdong Zhang  \n[zhyd73@ustc.edu.cn](zhyd73@ustc.edu.cn)  \nUniversity of Science and Technology of China HeFei, China  \nAbstract  \nEmotion-aware artistic image generation requires an image to match the input prompt, follow the specified artistic style, and convey the target emotion. In this challenge, the main difficulty is that the visual and affective attributes available in the training data are not explicitly provided at test time. Without these attributes, the generator has to decide not only what to depict, but also how the target emotion should be expressed through color, lighting, brushwork, composition, line, and layout. This creates a control gap between the available test prompt and the fine-grained conditions needed for emotion-aware artistic generation. To bridge this gap, we propose EmoStyle, a Z-Image-based framework that converts the input prompt into a structured generation state. An LLM reasoner first predicts affective cues (valence-arousal, dominant emotion, and therapeutic-effect labels) and an aspect-ratio decision. Instead of using these predictions only as additional prompt text, we encode the affective fields into an affective condition vector and inject it into the denoising blocks through AdaLN-style modulation. This allows the inferred control variables to directly guide the generation of intermediate features. Since emotional expression is also style-dependent, we further train a dedicated LoRA adapter for each artistic style bucket and select the corresponding expert during inference, enabling the same affective cues to be rendered  \nPermission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission [and/or a fee. Request permissions from permissions@acm.org](and/or a fee. Request permissions from permissions@acm.org).  \nMM’26, Rio de Janeiro, Brazil  \n© 2026 Copyright held by the owner/author(s) . Publication rights licensed to ACM. ACM ISBN 979-8-4007-XXXX-X/2026/10  \n[https://doi.org/10.1145/XXXXXXX.XXXXXXX](https://doi.org/10.1145/XXXXXXX.XXXXXXX)  \nwith bucket-specific priors for color, texture, brushwork, and composition. Finally, a lightweight VLM-guided candidate selection step ranks the generated images based on prompt alignment, style consistency, emotional expression, and visual quality. In Track 1 of the AffectiveArt Challenge 2026, our USTC_PI_LAB_TEAM submission achieved first place.  \nCCS Concepts  \n• Computing methodologies → Computer vision.  \nKeywords  \nmultimedia, affective computing, emotion image generation, diffusion models  \nACM Reference Format:  \nDexiang Hong, Yijie Guo, Weidong Chen, Xinyan Liu, Zixuan Zou, Zhendong Mao, and Yongdong Zhang. 2026. EmoStyle: Affec","cbCaiqdTf2315gLk","https://ap.wps.com/l/cbCaiqdTf2315gLk","pdf",7501269,1,9,"English","en",105,"# Introduction\n## EmoStyle Framework Overview\n## Affective Conditioning and Control Gap","[{\"question\":\"How does EmoStyle ensure style-dependent emotional expression?\",\"answer\":\"It trains dedicated LoRA adapters for each artistic style bucket and selects the corresponding expert during inference, so the same affective cues are rendered with style-specific priors. A VLM-guided ranking step then selects candidates based on alignment, style consistency, emotional expression, and visual quality.\"}]",1784206548,23,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":78,"head_meta":80,"extra_data":82,"updated_unix":27},"emostyle-affective-conditioning-of-style-specialist-experts-for-emotional-image-generation","",{"@graph":35,"@context":77},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/emostyle-affective-conditioning-of-style-specialist-experts-for-emotional-image-generation/85830/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71],{"name":72,"@type":73,"acceptedAnswer":74},"How does EmoStyle ensure style-dependent emotional expression?","Question",{"text":75,"@type":76},"It trains dedicated LoRA adapters for each artistic style bucket and selects the corresponding expert during inference, so the same affective cues are rendered with style-specific priors. A VLM-guided ranking step then selects candidates based on alignment, style consistency, emotional expression, and visual quality.","Answer","https://schema.org",{"og:url":51,"og:type":79,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":81,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":84},[85,89,93,97,102,107,112,115,119,122,126],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":86,"show_sort_weight":87,"slug":88},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":90,"show_sort_weight":91,"slug":92},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Exam",70,"exam",{"id":98,"doc_module":4,"doc_module_name":45,"category_name":99,"show_sort_weight":100,"slug":101},5,"Comic",60,"comic",{"id":103,"doc_module":4,"doc_module_name":45,"category_name":104,"show_sort_weight":105,"slug":106},6,"Technology",50,"technology",{"id":108,"doc_module":4,"doc_module_name":45,"category_name":109,"show_sort_weight":110,"slug":111},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":113,"slug":114},30,"research-report",{"id":21,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":45,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":98,"slug":129},19,"General","general"]