Image Generation with Quantum Generative Adversarial Networks Using Numeric and Fashion Mnist Images

This study explores the frontiers of generative modelling by introducing quantum principles into the picture synthesis process via Quantum Generative Adversarial Networks (QGANs). QGANs provide a novel method to image production by utilising the intrinsic features of quantum systems to improve both the quantity and variety of generated images. Using the Fashion-MNIST dataset and Numeric dataset, which consists of 28×28 grayscale images depicting various fashion products, this study investigates the potential of QGANs in creating realistic and diversified fashion images across multiple classes. While this study, Obtained 0.50 Discriminator Loss along with 0.98 as Generator Loss on 90<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">th</sup> Epoch for numeric dataset. This research demonstrates that QGANs can surpass classical models in terms of image generation, as evidenced by improved metrics and computational advantages. Additionally, by integrating physics principles such as the conservation of quantum information, this QGAN framework paves the way for disruptive advancements in computer vision, fashion design, and digital media production.