Artificial Intelligence (AI) has significantly transformed the field of computer graphics, particularly in image generation. Traditional graphics techniques relied heavily on manual design, mathematical models, and rendering algorithms. However, modern AI-driven approaches such as Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and Diffusion Models have enabled computers to automatically generate highly realistic images from data or textual descriptions. This paper explores how AI enhances image generation in computer graphics, analyzes major techniques, compares their performance, and discusses current challenges and future directions. The study highlights that AI-based image generation improves efficiency, creativity, and realism across industries such as gaming, film production, healthcare visualization, and virtual reality