In industries where the appearance, performance, and durability of fabric directly affect the end product, textile quality is crucial. Traditional textile quality inspection methods are manual, time-consuming, prone to human error, and difficult to scale. As the demand for high-quality fabrics grows, there is a pressing need for more efficient, accurate, and scalable inspection systems. This paper proposes an automated fabric defect detection system using YOLOv8, a state-of-the-art object detection model known for its real-time processing and high accuracy. The system incorporates a hybrid backbone fusion, which combines the strengths of multiple backbone architectures to enhance feature extraction and improve defect detection precision. The system identifies and classifies defects such as holes, stains, surface imperfections, and weaving inconsistencies. Additionally, it provides real-time monitoring, defect tracking, and immediate alert generation via a web-based dashboard. With a mean Average Precision (mAP) of 94%, the system outperforms traditional methods in accuracy, scalability, and operational efficiency. Furthermore, it offers a low-cost, scalable solution that significantly improves quality control in textile manufacturing.