EmoCtrl: Controllable Emotional Image Content Generation
This work addresses the need for controllable emotional image generation for applications in creative fields, representing a novel method for a known bottleneck rather than a foundational advancement.
The paper tackled the problem of generating images that are both faithful to a content description and expressive of a target emotion, addressing the gap where existing models either lack emotional awareness or distort content. The result was EmoCtrl, which outperformed existing methods in quantitative and qualitative experiments, with user studies confirming strong alignment with human preference.
An image conveys meaning through both its visual content and emotional tone, jointly shaping human perception. We introduce Controllable Emotional Image Content Generation (C-EICG), which aims to generate images that remain faithful to a given content description while expressing a target emotion. Existing text-to-image models ensure content consistency but lack emotional awareness, whereas emotion-driven models generate affective results at the cost of content distortion. To address this gap, we propose EmoCtrl, supported by a dataset annotated with content, emotion, and affective prompts, bridging abstract emotions to visual cues. EmoCtrl incorporates textual and visual emotion enhancement modules that enrich affective expression via descriptive semantics and perceptual cues. The learned emotion tokens exhibit complementary effects, as demonstrated through ablations and visualizations. Quantatitive and qualatitive experiments demonstrate that EmoCtrl achieves faithful content and expressive emotion control, outperforming existing methods across multiple aspects. User studies confirm EmoCtrl's strong alignment with human preference. Moreover, EmoCtrl generalizes well to creative applications, further demonstrating the robustness and adaptability of the learned emotion tokens.