The rapid growth of e-commerce and the increasing demand for online clothing shopping have elevated the importance of accurate clothing quality assessment. In response to this demand, we present a novel mobile application that leverages deep learning techniques for pixel-level analysis on clothing items. The proposed application empowers users to capture images of clothing and receive real-time quality assessments in large datasets. The inputs will be the collection of large set of images for training and traditional machine learning models cannot provide sufficient accuracy. This paper addresses the challenge of quality assessment through a comprehensive pipeline Large Language models (LLM) based deep learning algorithm called ClothQualityFinder (CQF) that involves data collection, preprocessing and the application of deep learning algorithms namely Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs). This paper includes a detailed examination of pixel-level analysis, encompassing aspects such as color analysis, texture recognition, and contour detection. The resulting model demonstrates good accuracy, making it a valuable tool for consumers and retailers alike.