VisAgent: Narrative-Preserving Story Visualization Framework
This work addresses the practical application of story visualization for users needing coherent narrative-driven image sequences, though it appears incremental as it builds on existing methods by adding narrative-focused agents.
The paper tackled the problem of story visualization by addressing the lack of narrative essence in existing methods, proposing VisAgent, a training-free multi-agent framework that improved the capture of narrative meaning and nuances in generated images.
Story visualization is the transformation of narrative elements into image sequences. While existing research has primarily focused on visual contextual coherence, the deeper narrative essence of stories often remains overlooked. This limitation hinders the practical application of these approaches, as generated images frequently fail to capture the intended meaning and nuances of the narrative fully. To address these challenges, we propose VisAgent, a training-free multi-agent framework designed to comprehend and visualize pivotal scenes within a given story. By considering story distillation, semantic consistency, and contextual coherence, VisAgent employs an agentic workflow. In this workflow, multiple specialized agents collaborate to: (i) refine layered prompts based on the narrative structure and (ii) seamlessly integrate \gt{generated} elements, including refined prompts, scene elements, and subject placement, into the final image. The empirically validated effectiveness confirms the framework's suitability for practical story visualization applications.