TaleWeave AI: Automated Visual Storytelling with Generative AI

The rapid advancement of Generative Artificial Intelligence (GenAI) has enabled novel applications in creative content generation. This paper introduces TaleWeave AI, an AIpowered web application designed to transform user-provided keywords into coherent, multiparagraph narrative stories, with each paragraph subsequently illustrated by AI-generated images. TaleWeave AI integrates Large Language Models (LLMs), specifically Google Gemini, for narrative synthesis and offers a choice of image generation models, including Stable Diffusion or the Gemini Vision API, for visual enhancement. The system features a FastAPI backend for processing and a React frontend for an interactive user experience, facilitating a seamless workflow from keyword input to the final visually enriched story. We present the system architecture, methodology, and qualitative results demonstrating its capability to produce contextually relevant text and image pairings. TaleWeave AI aims to democratize creative storytelling, providing an accessible tool for applications in education, entertainment, and content creation. While acknowledging current limitations in visual consistency and subjective quality assessment, this work highlights the potential of combining state-of-the-art AI models for automated visual narrative generation.