Offline AI image generation android application

The literature survey shows that Generative AI, particularly diffusion-based models, has significantly improved the quality and automation of image generation from natural-language prompts. Existing research demonstrates that techniques such as Natural Language Processing, Generative AI, diffusion models, GANs, and Stable Diffusion can effectively transform textual descriptions into realistic visual content.     The framework includes the text processing stage, embedding generation, r e a l i s t i c i ma g e generatsicoenn,e construction, and visualization of results to generate high-quality, realistic 3D objects as well as 3D multi-object scenes. The incorporation of modern AI techniques helps achieve better semantic interpretation and quality.   In comparison with conventional solutions, the system eliminates the need for complex manual workflows in the development of 3D objects. Gaming, virtual environment applications, simulations, and education are just a few examples of potential uses of the system.

[1]                     Muhammad Rizwan, Muhammad Awais, Muhammad Usman (2025). “An Implementation of MagicCraft: Generating Interactive 3D Objects and Their Behaviors from Text for Commercial Metaverse Platforms”, International Journal of Artificial Intelligence and Virtual Environments, vol. 12, no. 3, pp. 45–58.  [2]                    Rishabh Jain, Ankit Sharma, Priya Gupta (2024). “Utilizing Generative AI for Text-to-Image Generation”, Journal of Advanced Computing and Artificial Intelligence, vol. 9, no. 2, pp. 101–110.  3                          Harsh Patel, Sneha Kulkarni, Rahul Mehta (2024). “Conversion of Text-to-Image Generation”, International Journal of Machine Learning and Intelligent Systems, vol. 8, no. 4, pp. 67–76.  4                          Xinyang Chen, Zhenyu Chen, Xiaoxiao Long (2024). “VariedDreamer: Efficient Text-to-3D Generation via Optimizing Fine Geometric Details”, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2345–2356.  5                          Szymon Kuc, Jakub Nowak, Tomasz Wlodarczyk (2023). “Generating Digital Models Using Text-to-3D and Image-to-3D Prompts: Critical Case Study”, Journal of Digital Modeling and Simulation, vol. 15, no. 1, pp. 88–99. 6                          Yifan Zhou, Rui Chen, Xiaolong Wang (2024).“From Cards to Creatures: Interactive 3D Generation Using Generative AI”, International Conference on Virtual Reality and Intelligent Systems, pp. 145–154.  [7]                     Zhenyu Chen, Xiaoxiao Long, Xinyang Chen (2024). “HumanRef-GS: Image-to-3D Human Generation With Reference-Guided Diffusion and 3D Gaussian Splatting”, IEEE Transactions on Visualization and Computer Graphics, vol. 30, no. 5, pp. 567–579.  [8]                     Daniel Park, Kevin Liu, Michael Brown (2024). “From Voices to Worlds: Developing an AI-Powered Framework for 3D Object Generation in Augmented Reality”, International Journal of Augmented Reality and AI Applications, vol. 11, no. 2, pp. 34–46.  [9]                     Yuan Yao, H. Zhang, W. Li (2024). “Automated Construction Scheduling using Deep Reinforcement Learning”, Automation in Construction, vol. 162, pp. 104–118. [10]                 Farhad Habibi, O. Taghipour Birgani, H. Koppelaar, S. Radenovic (2018). “Using Fuzzy Logic to Improve the Project Time and Cost Estimation based on Project Evaluation and Review Technique (PERT)”, Journal of Project Management, vol. 3, no. 4, pp. 183–196.