The textile industry faces significant challenges due to waste from defective fabrics. Traditional human inspection is labor-intensive and prone to errors, making consistent quality control difficult. This research develops an Automated Fabric Inspection System using Real-Time Models for object Detection (RTMDet) to address these issues. By integrating high-resolution cameras and advanced object detection algorithms, the system accurately identifies defects of various types and scales in real-time. While previous research often relied on YOLO-based models, this work is the first to apply RTMDet in the textile industry, chosen for its promising balance of speed and accuracy for real-time tasks. The implementation of this system is expected to reduce waste, enhance production efficiency, and ensure higher quality standards. Initial experiments on denim fabric demonstrate the system’s potential in detecting defects such as streaks, chalk, nips, holes, tag pins, and threads. A comparative analysis reveals that the AI system is approximately 2.5 times more efficient than manual inspection, significantly reducing inspection time and labor costs, offering a promising solution for modernizing quality control in fabric manufacturing.