2024, Vol. 5, Issue 1, Part A
Imagining the Unseen: Text-driven realism in artificial image generation
Author(s): Chinni Mohith and Jaya Venkatesh
Abstract: This project employs Generative Adversarial Networks (GANs) to tackle the task of generating realistic images from textual descriptions. GANs consist of a generator and a discriminator network engaged in a competitive learning process, enabling the creation of high-quality images. By incorporating natural language processing techniques, we connect textual input to the generator, allowing for the synthesis of images that align closely with provided descriptions. Our methodology involves training the GAN on diverse datasets, optimizing for both visual fidelity and semantic coherence. Through extensive experimentation and evaluation, we showcase the model's effectiveness in transforming text into visually convincing images. This research contributes to the evolving landscape of text-to-image synthesis, demonstrating the potential of GANs in bridging the gap between language and visual representation.
DOI: 10.22271/27083969.2024.v5.i1a.36
Pages: 01-06 | Views: 681 | Downloads: 321
Download Full Article: Click Here
How to cite this article:
Chinni Mohith, Jaya Venkatesh. Imagining the Unseen: Text-driven realism in artificial image generation. Int J Electr Data Commun 2024;5(1):01-06. DOI: 10.22271/27083969.2024.v5.i1a.36
