Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{194985,
        author = {Ragipati Karthik and Anjali Paladi and Barre Ruchitha and Challa Taruni and Chinni Akanksha},
        title = {ARTISTIC IMAGE GENERATION USING NEURAL STYLE TRANSFER},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {8210-8215},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=194985},
        abstract = {Neural Style Transfer (NST) refers to a deep learning method that produces artistic images through a combination of content and style of another image. This paper is an artistic image generating system that works on an arbitrary style transfer model that is built around an already trained Convolutional Neural Network, which is VGG19. The suggested solution supports several invisible styles with effective feedforward inferencing, unlike the conventional techniques that involve retraining whenever the style changes. Content and style features have been mined out of various network layers and optimized loss function is used to trade content integrity and aesthetic appearance. Visual appeal of aesthetically pleasing stylized images achieved through experimental results, but structural integrity is preserved, indicates that neural style transfer is useful in creative and digital art applications.},
        keywords = {Neural Style Transfer, Arbitrary Stylization Model, Deep Learning, Convolutional Neural Network, VGG19.},
        month = {March},
        }