Generative models have become a cornerstone in the field of artificial intelligence, particularly for image synthesis, enabling the creation of high-quality, realistic images across various domains. This chapter provides a comprehensive overview of key generative models, including Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), Denoising Diffusion Probabilistic Models (DDPMs), and more. We delve into the architectures, sub-models, and unique capabilities of each, highlighting their applications in image generation, translation, and enhancement. Additionally, we discuss the challenges these models face, such as training instability and computational complexity, and explore future directions in generative image synthesis. This exploration provides a deep understanding of how these models are shaping the future of AI-driven creativity and design.