AI-Powered Visual Storytelling System An intelligent system that transforms visual content into compelling narratives through deep learning and natural language processing.

The AI-Powered Visual Storytelling System is designed to bridge the gap between visual perception and narrative generation by transforming static images into cohesive, context-aware stories. Moving beyond traditional object-focused captioning, the system employs a sophisticated architecture that integrates CNNs and Vision Transformers for deep feature extraction with GPT-based language models for constructing narrative arcs. Built using a robust technical stack including Python, TensorFlow, and PyTorch, the system supports diverse storytelling styles and multi-format exports. Empirical results indicate high technical efficiency, achieving an overall accuracy rate exceeding 85% and a threefold increase in training speed compared to traditional CNN+LSTM models. Furthermore, specific system modules demonstrated a reliability rate of up to 99.5%, highlighting the framework's effectiveness in generating automated, meaningful, and contextually rich narratives from visual content. This work was conducted at Arab International University (AIU), Syria. The official website of the university is: https://www.aiu.edu.sy (https://www.aiu.edu.sy/)