• Ritika Shaw
• Gaurav Kashyap
• Sahil
• Bhavesh Diwedi
• Akhil Khandelwal

This article provides an overview of Generative AI Text-to-Image Generation, a cutting-edge technology that leverages artificial intelligence to create visual content based on textual input. This innovation eliminates the need for traditional image creation methods. In 2010, the concept of Generative Adversarial Networks (GANs) was introduced. This innovative approach enables the generation of images, illustrations, and graphics by interpreting and translating text prompts into visual representations, eliminating the need for traditional image creation methods. In this article, we delve into the history of this field, summarize its core functionalities, explore potential solutions to enhance accuracy and quality, comprehend the underlying mechanisms, and discuss potential research gaps to further advance Generative AI Text-to-Image Generation.

Attentional Generative Network, EntityDrawBench, FID score, IS score, CLIP models, Latent Space, DrawBench Benchmark, R-precison(%), Guided Diffusion, semantic consistency, T5-XXL encoder, Diffusion Dequantization-Inpainting Model, COCO dataset, CUB dataset, STEM, GAN, Stable Diffusion.

"A comprehensive review of Generative AI Text To Image Generator", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 11, page no.e138-e145, November-2023, Available :http://www.jetir.org/papers/JETIR2311422.pdf

"A comprehensive review of Generative AI Text To Image Generator", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 11, page no. ppe138-e145, November-2023, Available at : http://www.jetir.org/papers/JETIR2311422.pdf