Visual Story Generation Based on Emotion and Keywords
This work addresses the problem of creating interactive and emotionally coherent visual stories for users in creative applications, but it appears incremental as it combines existing methods like diffusion models with user input mechanisms.
The paper tackles automated visual story generation by proposing a pipeline that allows user control over events and emotions, generating coherent stories with corresponding illustrations using narrative generation with keywords and emotion labels, and image generation with diffusion models, achieving a system that integrates object recognition for future story development.
Automated visual story generation aims to produce stories with corresponding illustrations that exhibit coherence, progression, and adherence to characters' emotional development. This work proposes a story generation pipeline to co-create visual stories with the users. The pipeline allows the user to control events and emotions on the generated content. The pipeline includes two parts: narrative and image generation. For narrative generation, the system generates the next sentence using user-specified keywords and emotion labels. For image generation, diffusion models are used to create a visually appealing image corresponding to each generated sentence. Further, object recognition is applied to the generated images to allow objects in these images to be mentioned in future story development.