Recently, there has been increased interest in the application of Generative Adversarial Networks (GANs) to the creation of artistic images. The art community has been particularly drawn to GAN's capacity to reconstruct and produce a new artistic image in the desired style. While gradient disappearance during the training phase is a challenge for conventional GAN techniques, which frequently lead to the creation of images with subpar artistic quality, these techniques have shown impressive success in synthesizing images with a naturalistic appearance. With differing degrees of success, several attempts have been made to address these issues. The goal of this research is to use the Deep Convolutional Generative Adversarial Network (DCGAN) to produce artistic images of superior quality. The Coco Africa Mask dataset was used to run the simulation. The proposed method produced images that were subjected to quantitative analysis. When compared to other cutting-edge techniques, the discriminator's and DCGAN's images are more visually appealing and closely resemble authentic works of art. In comparison to other simulation methods, the proposed method performs better on the CelebFace dataset, yielding an FID of 11.21, an IS score of 9.67, and an SSIM of 0.95. The Coco Africa Mask dataset yields a low FID of 9.15, a high IS score of 12.82, and an SSIM of 0.87. The artist can create excellent look-alike images with the aid of the results.