Generative AI Platform for Applying Artistic Styles to Images

Users can now alter photographs to resemble well-known artists thanks to artistic style transfer, which has attracted a lot of attention. In order to accomplish artistic style transfer, this research study investigates CycleGAN, a deep learning method for unpaired image-to-image translation. Users can submit photographs and choose artistic styles for real-time processing with an easy-to-use web application. Benefits of the suggested approach include enhanced generalizability, increased accessibility, and unsupervised learning. Claude Monet's creative style is effectively applied to user photographs using CycleGAN, which retains content and adds stylistic aspects like colour palettes and brushstrokes. An analysis conducted quantitatively with the MiFID score validates the model's efficacy. This study opens up new avenues for investigating CycleGAN for user-centered picture editing and the transmission of artistic styles.