Fashion is a multibillion-dollar industry that concerns many people both socially and culturally. Thanks to social networks, there is a lot of data about the fashion industry on the internet. This has led researchers to shift their attention to this area, especially recently. This paper proposes an end-to-end framework to build an AI fashioner that can diagnose clothing compatibility and generate recommendations to improve compatibility. First, fashion compatibility reviews are analyzed, and incompatible clothing items are identified for each outfit combination. Next, the items of clothing that make up the outfit combination are separated using Mask R-CNN. Then, the incompatible clothing items were removed from the outfit combination, and the most similar outfit combinations were identified among the compatible clothing items. In addition, an attribute detection network was developed to extract the attributes of compatible outfits with the same category in the detected compatible outfits. Finally, recommendation sentences are generated using the detected attributes, and encoder-decoder models are used to train a deep network that generates recommendations from clothing images. Extensive experiments based on existing datasets demonstrate the effectiveness of the proposed method.