The integration of multi-modal artificial intelligence (AI) for context-aware storytelling in image analysis represents a significant advancement in the field. By combining visual, textual, and auditory data, AI systems can now interpret complex scenarios, recognise objects, actions, and scenes, and generate coherent narratives. This paper explores a unified AI framework leveraging Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), scene graph models, and multi-modal techniques to enhance narrative coherence. The proposed framework is evaluated using quantitative metrics, such as precision, recall, and F1 score, alongside qualitative measures like user satisfaction and narrative fluency. Applications across autonomous systems, healthcare diagnostics, and interactive media highlight the transformative potential of this approach. By combining these various AI techniques, the framework is able to not only improve narrative coherence but also provide a more immersive and engaging experience for users. The results of the evaluation demonstrate the effectiveness of this approach in creating compelling and coherent narratives across a range of applications. The integration of AI techniques in narrative generation allows for a more holistic evaluation of the generated content, taking into account both quantitative and qualitative metrics. This comprehensive approach ensures that the narratives produced are not only technically accurate but also engaging and satisfying for users. By utilizing AI techniques, developers can fine-tune the narratives to cater to different user preferences and create a more personalized experience. This level of customization can lead to increased user satisfaction and retention, ultimately benefiting the overall success of the application.