A review of the field of image creation uses generative artificial intelligence methods. Examples include Generative Adversarial Networks, Conditional GANs, Deep Neural Networks, Creative Adversarial Networks, and Neural Style Transfer. This analysis examines how generative AI techniques are applied to image generation. Various techniques are examined, including GANs, cGANs, DNNs, CANs, and neural style transfer, to create realistic and visually appealing images. The purpose of this study is to analyze existing research and works in the area of image generation using generative AI techniques using a literature review approach. Various research papers, articles, and publications are reviewed to identify the methodology, algorithms, and implementation details of the mentioned techniques. This study indicates that generative AI techniques, particularly GAN, cGAN, DNN, CAN, and neural style transfer can generate high-quality images. Using a generative and discriminative model, GANs generate realistic images. Conditional GANs provide enhanced control over image generation. DNNs can capture complex image patterns and produce visually appealing outputs. Multi-generator CANs produce diverse images. An artistic style can be transferred to images through neural style transfer. The originality of this review lies in the comprehensive review and analysis of different generative AI techniques used for image generation.