VisuCraft: Enhancing Large Vision-Language Models for Complex Visual-Guided Creative Content Generation via Structured Information Extraction

TL;DR

VisuCraft is a framework that significantly improves large vision-language models' ability to generate complex, creative, and visually grounded long-form texts by integrating structured visual information and dynamic prompt generation.

Contribution

It introduces a multimodal structured information extractor and a dynamic prompt module to enhance LVLMs' creative and visual fidelity capabilities.

Findings

Outperforms baseline LVLMs in creativity and instruction adherence

Achieves significant improvements in story and poetry generation

Validated on the ImageStoryGen-500K dataset with VisuGen Metrics

Abstract

This paper introduces VisuCraft, a novel framework designed to significantly enhance the capabilities of Large Vision-Language Models (LVLMs) in complex visual-guided creative content generation. Existing LVLMs often exhibit limitations in maintaining high visual fidelity, genuine creativity, and precise adherence to nuanced user instructions when generating long-form texts. VisuCraft addresses these challenges by integrating a multimodal structured information extractor (E) and a dynamic prompt generation module (G). The extractor distills fine-grained visual attributes from input images into a rich, structured representation, which the dynamic prompt module then combines with user instructions to create highly optimized prompts for underlying LVLMs (e.g., LLaVA, InstructBLIP). Evaluated on the self-constructed ImageStoryGen-500K dataset using VisuGen Metrics (Visual Grounding, Creativity, and Instruction Adherence), VisuCraft consistently outperforms baseline LVLMs across tasks like story generation and poetry composition. Our results demonstrate remarkable improvements, particularly in creativity and instruction adherence, validating VisuCraft's effectiveness in producing imaginative, visually grounded, and user-aligned long-form creative text. This work unlocks new potential for LVLMs in sophisticated creative AI applications.