EmoStyle: Affective Conditioning of Style-Specialist Experts for Emotional Image Generation

• URL: http://arxiv.org/abs/2607.10165v1
• Date: Sat, 11 Jul 2026 07:12:07 GMT
• Title: EmoStyle: Affective Conditioning of Style-Specialist Experts for Emotional Image Generation
• Abstract summary: EmoStyle is a Z-Image-based framework that converts the input prompt into a structured generation state.<n>We train a dedicated LoRA adapter for each artistic style bucket and select the corresponding expert during inference.<n>A lightweight VLM-guided candidate selection step ranks the generated images based on prompt alignment, style consistency, emotional expression, and visual quality.
• Score: 50.22045436428303
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Emotion-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 with 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.

Related papers

• ReART: Reference-Guided Retrieval and Refinement for Emotion-Aware Art Generation [8.10513799293732]
  We present ReART, a reference-guided retrieval and refinement framework.<n>Our method decomposes test captions and each image annotation in the EmoArt database into structured visual fields.<n>Our system ranks 2nd in Track 1 of the AffectiveArt 2026 Grand Challenge, achieving a perfect AAS of 1.00 and an overall score of 0.78.
  arXiv  Detail & Related papers  (2026-08-23T09:56:30Z)
• What Can I Edit? Open-Ended Strategy Discovery and the Emotion Editability Landscape [26.199100714806765]
  EmoScope is a framework that reframes the task from "how should I edit?" to "what can I edit?"<n>It first discovers an image-specific editable space through emotion-conditioned affordance reasoning.<n>EmoScope selects target-emotion-adaptive strategies rather than applying a uniform template.
  arXiv  Detail & Related papers  (2026-07-27T01:22:54Z)
• EmoKGEdit: Training-free Affective Injection via Visual Cue Transformation [7.245162028678732]
  EmoKGEdit is a novel training-free framework for precise and structure-preserving image emotion editing.<n>We construct a Multimodal Sentiment Association Knowledge Graph to disentangle the relationships among objects, scenes, attributes, visual clues and emotion.<n>EmoKGEdit achieves excellent performance in both emotion fidelity and content preservation, and outperforms the state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-01-18T09:20:09Z)
• EmoCtrl: Controllable Emotional Image Content Generation [9.677863079897735]
  We introduce Controllable Emotional Image Content Generation (C-EICG)<n>C-EICG aims to generate images that remain faithful to a given content description while expressing a target emotion.<n>EmoCtrl is supported by a dataset annotated with content, emotion, and affective prompts.
  arXiv  Detail & Related papers  (2025-12-27T02:18:36Z)
• EmoStyle: Emotion-Driven Image Stylization [8.734768359185106]
  Affective Image Stylization (AIS) is a task that applies artistic styles to evoke specific emotions while preserving content.<n>We present EmoStyle, a framework designed to address key challenges in AIS, including the lack of training data and the emotion-style mapping.<n>Our work establishes a foundation for emotion-driven image stylization, expanding the creative potential of AI-generated art.
  arXiv  Detail & Related papers  (2025-12-05T07:15:02Z)
• Affective Image Editing: Shaping Emotional Factors via Text Descriptions [46.13506671212571]
  We introduce AIEdiT for Affective Image Editing using Text descriptions.<n>We build the continuous emotional spectrum and extract nuanced emotional requests.<n>AIEdiT achieves superior performance, effectively reflecting users' emotional requests.
  arXiv  Detail & Related papers  (2025-05-24T13:46:57Z)
• EmoEdit: Evoking Emotions through Image Manipulation [62.416345095776656]
  Affective Image Manipulation (AIM) seeks to modify user-provided images to evoke specific emotional responses.<n>We introduce EmoEdit, which extends AIM by incorporating content modifications to enhance emotional impact.<n>Our method is evaluated both qualitatively and quantitatively, demonstrating superior performance compared to existing state-of-the-art techniques.
  arXiv  Detail & Related papers  (2024-05-21T10:18:45Z)
• VLLMs Provide Better Context for Emotion Understanding Through Common Sense Reasoning [66.23296689828152]
  We leverage the capabilities of Vision-and-Large-Language Models to enhance in-context emotion classification.<n>First, we prompt VLLMs to generate natural language descriptions of the subject's apparent emotion in relation to the visual context.<n>Second, the descriptions, along with the visual input, are used to train a transformer-based architecture.
  arXiv  Detail & Related papers  (2024-04-10T15:09:15Z)
• Emotion Rendering for Conversational Speech Synthesis with Heterogeneous Graph-Based Context Modeling [50.99252242917458]
  Conversational Speech Synthesis (CSS) aims to accurately express an utterance with the appropriate prosody and emotional inflection within a conversational setting. To address the issue of data scarcity, we meticulously create emotional labels in terms of category and intensity. Our model outperforms the baseline models in understanding and rendering emotions.
  arXiv  Detail & Related papers  (2023-12-19T08:47:50Z)
• StyleEDL: Style-Guided High-order Attention Network for Image Emotion Distribution Learning [69.06749934902464]
  We propose a style-guided high-order attention network for image emotion distribution learning termed StyleEDL. StyleEDL interactively learns stylistic-aware representations of images by exploring the hierarchical stylistic information of visual contents. In addition, we introduce a stylistic graph convolutional network to dynamically generate the content-dependent emotion representations.
  arXiv  Detail & Related papers  (2023-08-06T03:22:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.