An unified framework that combines image deblurring and colorization using Generative Adversarial Networks (GANs) to improve image quality. The process begins with a Convolutional Neural Network (CNN) designed to minimize the difference between blurred input images and their sharp reference counterparts, effectively reducing blur. Following this, the framework employs a GAN-based approach for image colorization. The system consists of Deep Neural Networks (DNNs), featuring a generator that converts grayscale images into vivid, colorized versions, and a discriminator that evaluates the authenticity of the generated outputs. By leveraging adversarial training, the model learns intricate patterns and textures, producing visually appealing results. The performance of the proposed method is assessed using essential image quality metrics, such as Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM). This integrated methodology represents a significant advancement in automated image enhancement, with potential applications in areas like digital preservation and media restoration.