• Vaibhav Sawate
• Dr. Snehal Rathi
• Gunjan Ghuguskar
• Darshan Kotecha
• Sahil Savardekar

The most difficult jobs in computer vision is creating a picture from various data formats, such as text, scene graphs, and object layouts. Furthermore, manually taking pictures from various angles in order to create an object or a product can be time-consuming and complex. Deep learning and artificial intelligence algorithms have now made it feasible to create fresh images from various kinds of data. For this reason, a lot of work has recently been put into creating image-generating techniques, with remarkable success. In light of this, we provide a thorough analysis of current picture creation techniques in our study, to the best of our author’s knowledge. As a result, an explanation of each image creation method is carried out according to the primary goal, the type of data utilized, and the nature of the employed algorithms. Additionally, the suggested methods are shown in order to discuss each image-generating category. A live implementation of the DALL-E model by ChatGPT is also been implemented. To further explain the latest advancements and pinpoint strengths and limits, a comparing performance of current solutions is presented together with a discussion of the assessment metrics appropriate for each picture-generating category. Finally, the issues that this topic is currently facing are discussed. Here, in this paper we deal with creating a picture from simple “text” data formats and prompts. The selected method makes it simpler to create images from user-provided text inputs by combining many pre-trained models with expertise in computer vision and natural language processing (NLP). Simplifying the process of creating unique photos and creating new opportunities for advertising, content, and art are the objectives. While guaranteeing the accuracy and quality of the information produced, the study also investigates the performance and adaptability of several AI models.

Gemini, Bing, Copilot, OpenAI, Transformers, Diffusion, Neural Networks, GAN, VAE, BERT, AutoEncoders, ReactJS

"Exploring AI Image Generation: A Comparative Insights from API Integration", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 12, page no.a724-a728, December-2024, Available :http://www.jetir.org/papers/JETIR2412065.pdf

"Exploring AI Image Generation: A Comparative Insights from API Integration", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 12, page no. ppa724-a728, December-2024, Available at : http://www.jetir.org/papers/JETIR2412065.pdf