Colorization is the process of converting grayscale photos into colorful ones that are more visually appealing. Previously, a wide range of colorization techniques has been developed, which require the involvement of the human brain which consumes a lot of time and energy. In today’s world, there are many procedures that will automatically convert the grayscale image to a color image. Most of the conversion techniques incorporate elements of deep learning, machine learning, and art. This study gives a novel technique for coloring grayscale images that makes use of GAN and U-Net model characteristics. By using this technique, the model is able to learn how to colorize images from a trained U- Net. Additionally, the Fusion layer is used to combine the global priors for each class with the local information finds for each class, which are based on small image patches. This produces colorization outcomes that are more attractive on a visual level. Finally, the results of the method were obtained by doing an evaluation based on user research and comparing it to the state-of-the-art