In the industrial field, deep-learning-based image anomaly detections are attracting attention because of some of their advantages. The deep-learning-based models can overcome the shortcomings of traditional methods, such as human eye detection and rule-based machine detection. When using deep learning, which has many advantages, one of the limitations is that anomalous products are difficult to obtain. Since most industrial products do not have defects, unsupervised learning detection models are strongly required. We propose a new model based on the variational autoencoder (VAE), which is a generative model applicable to detection by unsupervised learning. VAE is a model for optimizing parameters or latency based on a loss function that is the sum of several terms, and in our proposed method, original weights are given to these terms. In addition, our model dynamically and adaptively explores a ratio of weights. We have developed a dynamic weighted VAE adapted to area under the receiver operating characteristic curve (AUROC, AUC) using validation data. We have already reported the efficiency of the AUC-adapted VAE; however, this method is not unsupervised learning, and a method that does not use validation data was desired. In this paper, we discuss the previous method in more detail and describe the new method, which is fully unsupervised learning, by conducting additional experiments. The results of several experiments show that the proposed method is potentially effective for some actual industrial product image datasets while maintaining unsupervised learning.