EmotiCrafter: Text-to-Emotional-Image Generation based on Valence-Arousal Model
This work addresses the need for users to create emotionally nuanced image content, which is incremental as it builds on existing emotional image generation by moving from discrete categories to continuous control.
The paper tackles the problem of generating emotionally rich images from text prompts by introducing a continuous emotional image content generation task, using Valence-Arousal values to capture subtle emotions, and reports that their method outperforms existing techniques in generating images with specific emotions and desired content.
Recent research shows that emotions can enhance users' cognition and influence information communication. While research on visual emotion analysis is extensive, limited work has been done on helping users generate emotionally rich image content. Existing work on emotional image generation relies on discrete emotion categories, making it challenging to capture complex and subtle emotional nuances accurately. Additionally, these methods struggle to control the specific content of generated images based on text prompts. In this work, we introduce the new task of continuous emotional image content generation (C-EICG) and present EmotiCrafter, an emotional image generation model that generates images based on text prompts and Valence-Arousal values. Specifically, we propose a novel emotion-embedding mapping network that embeds Valence-Arousal values into textual features, enabling the capture of specific emotions in alignment with intended input prompts. Additionally, we introduce a loss function to enhance emotion expression. The experimental results show that our method effectively generates images representing specific emotions with the desired content and outperforms existing techniques.