Neural style transfer (NST) is a technology in computer vision that merges the stylistic features of one image with the content of another, rooted in research by Gatys et al. (2016) using a deep convolutional neural network (CNN). This technique, enhanced by architectures like VGG19, allows for the transfer of textures, colors, and characteristics from famous artworks onto photographs, with subsequent studies improving resolution and execution speed. The process involves pre-processing images to ensure consistent dimensions, using pre-trained CNN models to extract image features, and employing a loss function to minimize differences between content and style representations. The loss function incorporates content and style losses, calculated through layer activations and the Gram matrix for style comparison, while gradient descent adjusts the combined image to align with desired features. Despite challenges, successful experiments have demonstrated the potential of NST in creating visually appealing images on consumer-level devices, highlighting the importance of pre-processing and feature extraction in achieving quality results.