# CoEmoGen: Towards Semantically-Coherent and Scalable Emotional Image Content Generation

arXiv: https://arxiv.org/abs/2508.03535 · HTML: https://mlsanity.com/paper/2508.03535/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 52 references that are in the map.
- First posted on arXiv 5 Aug 2025.

## Builds on (most cited first, 26 of 26)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [EmoSet: A Large-scale Visual Emotion Dataset with Rich Attributes](https://mlsanity.com/paper/2307.07961/) (2023)
- [Affective Image Content Analysis: Two Decades Review and New Perspectives](https://mlsanity.com/paper/2106.16125/) (2021)
- [MultiBooth: Towards Generating All Your Concepts in an Image from Text](https://mlsanity.com/paper/2404.14239/) (2024)
- [rPPG-MAE: Self-supervised Pre-training with Masked Autoencoders for Remote Physiological Measurement](https://mlsanity.com/paper/2306.02301/) (2023)
- [Visual Large Language Models for Generalized and Specialized Applications](https://mlsanity.com/paper/2501.02765/) (2025)
- [Learning Multi-level Deep Representations for Image Emotion Classification](https://mlsanity.com/paper/1611.07145/) (2016)
- [AUFormer: Vision Transformers are Parameter-Efficient Facial Action Unit Detectors](https://mlsanity.com/paper/2403.04697/) (2024)
- [DataDream: Few-shot Guided Dataset Generation](https://mlsanity.com/paper/2407.10910/) (2024)
- [Stimuli-Aware Visual Emotion Analysis](https://mlsanity.com/paper/2109.01812/) (2021)
- [GPT as Psychologist? Preliminary Evaluations for GPT-4V on Visual Affective Computing](https://mlsanity.com/paper/2403.05916/) (2024)
- [SATO: Stable Text-to-Motion Framework](https://mlsanity.com/paper/2405.01461/) (2024)
- [Advancing Generalizable Remote Physiological Measurement through the Integration of Explicit and Implicit Prior Knowledge](https://mlsanity.com/paper/2403.06947/) (2024)
- [Image Sentiment Transfer](https://mlsanity.com/paper/2006.11337/) (2020)
- [ANT: Adaptive Neural Temporal-Aware Text-to-Motion Model](https://mlsanity.com/paper/2506.02452/) (2025)
- [FEALLM: Advancing Facial Emotion Analysis in Multimodal Large Language Models with Emotional Synergy and Reasoning](https://mlsanity.com/paper/2505.13419/) (2025)

## Built on by (most cited first, 9 of 9)

- [DeltaVLA: Prior-Guided Vision-Language-Action Models via World Knowledge Variation](https://mlsanity.com/paper/2603.08361/) (2026)
- [Emotion-Director: Bridging Affective Shortcut in Emotion-Oriented Image Generation](https://mlsanity.com/paper/2512.19479/) (2025)
- [EmoStyle: Affective Conditioning of Style-Specialist Experts for Emotional Image Generation](https://mlsanity.com/paper/2607.10165/) (2026)
- [Oracle Noise: Faster Semantic Spherical Alignment for Interpretable Latent Optimization](https://mlsanity.com/paper/2604.23540/) (2026)
- [What Can I Edit? Open-Ended Strategy Discovery and the Emotion Editability Landscape](https://mlsanity.com/paper/2607.23920/) (2026)
- [EmoScene: A Dual-space Dataset for Controllable Affective Image Generation](https://mlsanity.com/paper/2604.00933/) (2026)
- [Z2-Sampling: Zero-Cost Zigzag Trajectories for Semantic Alignment in Diffusion Models](https://mlsanity.com/paper/2604.23536/) (2026)
- [Learning to Use Imagination: Progress-Conditioned Future Utilization for World Action Models](https://mlsanity.com/paper/2609.06578/) (2026)
- [Beyond Emotion Prompts: Fine-Grained Text-to-Image Generation Driven by Valence-Arousal-Dominance](https://mlsanity.com/paper/2609.24215/) (2026)

## Abstract (arXiv)

Emotional Image Content Generation (EICG) aims to generate semantically clear and emotionally faithful images based on given emotion categories, with broad application prospects. While recent text-to-image diffusion models excel at generating concrete concepts, they struggle with the complexity of abstract emotions. There have also emerged methods specifically designed for EICG, but they excessively rely on word-level attribute labels for guidance, which suffer from semantic incoherence, ambiguity, and limited scalability. To address these challenges, we propose CoEmoGen, a novel pipeline notable for its semantic coherence and high scalability. Specifically, leveraging multimodal large language models (MLLMs), we construct high-quality captions focused on emotion-triggering content for context-rich semantic guidance. Furthermore, inspired by psychological insights, we design a Hierarchical Low-Rank Adaptation (HiLoRA) module to cohesively model both polarity-shared low-level features and emotion-specific high-level semantics. Extensive experiments demonstrate CoEmoGen's superiority in emotional faithfulness and semantic coherence from quantitative, qualitative, and user study perspectives. To intuitively showcase scalability, we curate EmoArt, a large-scale dataset of emotionally evocative artistic images, providing endless inspiration for emotion-driven artistic creation. The dataset and code are available at https://github.com/yuankaishen2001/CoEmoGen.