EmoGen: Emotional Image Content Generation with Text-to-Image Diffusion Models

TL;DR

EmoGen introduces a novel approach for generating images that accurately reflect specific emotions by mapping emotion categories into a semantic space aligned with CLIP, improving emotional fidelity and semantic clarity.

Contribution

The paper proposes a new task of emotional image content generation and develops an emotion space with a mapping network to enhance emotion-faithful image synthesis.

Findings

Outperforms state-of-the-art methods in emotion accuracy and semantic clarity

Introduces three new metrics: emotion accuracy, semantic clarity, semantic diversity

Enables applications in emotion understanding and emotional art design

Abstract

Recent years have witnessed remarkable progress in image generation task, where users can create visually astonishing images with high-quality. However, existing text-to-image diffusion models are proficient in generating concrete concepts (dogs) but encounter challenges with more abstract ones (emotions). Several efforts have been made to modify image emotions with color and style adjustments, facing limitations in effectively conveying emotions with fixed image contents. In this work, we introduce Emotional Image Content Generation (EICG), a new task to generate semantic-clear and emotion-faithful images given emotion categories. Specifically, we propose an emotion space and construct a mapping network to align it with the powerful Contrastive Language-Image Pre-training (CLIP) space, providing a concrete interpretation of abstract emotions. Attribute loss and emotion confidence are further proposed to ensure the semantic diversity and emotion fidelity of the generated images. Our method outperforms the state-of-the-art text-to-image approaches both quantitatively and qualitatively, where we derive three custom metrics, i.e., emotion accuracy, semantic clarity and semantic diversity. In addition to generation, our method can help emotion understanding and inspire emotional art design.