Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{172980,
        author = {Heramb Haridas and Vaishnavi Borkar and Saniya Bangare and Prof. Siddhartha Chandra},
        title = {Advanced AI-Driven Solutions for Virtual Fitting and Personalized Fashion E-Commerce},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {9},
        pages = {1649-1661},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=172980},
        abstract = {The rapid growth of ecommerce in fashion has high- lighted critical challenges, such as the inability to physically try on clothes, limited personalized guidance, and the need for real- time customer support. This paper presents an AI-driven fashion ecommerce platform that addresses these issues through the integration of advanced artificial intelligence tools. Key features include a Virtual Try-On system, which leverages computer vision and deep learning to allow users to visualize clothing items on their own images, enhancing purchase confidence. Additionally, a Clothes Replacement Tool utilizes the” Segment Anything” model (SAM) and Stable Diffusion techniques to enable users to apply different clothing patterns or designs to their uploaded images, further personalizing their shopping experience. The platform also includes an AI-powered Chatbot that provides immediate customer support using natural language processing to resolve user queries in real time. Lastly, a Personalized Recommendation System offers tailored clothing suggestions based on users’ preferences and current fashion trends.

Our methodology combines pose detection, segmentation, and stable diffusion inpainting, allowing for a robust virtual try-on experience and flexible clothing customization. We achieved 92% of Pose Detection Accuracy and 94.5% of Gesture Responsive- ness for Dynamic virtual try-on. This research demonstrates a significant impact on user engagement, reducing return rates and improving satisfaction with fit and appearance. Initial testing has shown clothes replacement features offer users an immersive, interactive and fast experience that closely simulates in-store try- ons in less than 30 seconds. Through a combination of machine learning models and innovative AI approaches, this platform represents a step forward in personalized, immersive ecommerce, indicating that AI-driven fashion solutions can effectively trans- form online shopping experiences and enhance user trust in digital fashion retail.},
        keywords = {Virtual Try-On, Pose Detection, Computer Vision, Deep Learning, Chatbot Assistance, Personalized Recommendations, Stable Diffusion Inpainting, Customer Support, Segmentation Models, User Experience, Machine Learning in Fashion, Fixed Ratio, Generative AI, Digital Smart Fashion},
        month = {February},
        }