Authors: Prof. Sachin Dhawas, Dhruv Gonnade, Chetan Parate, Gaurav Madavi, Vighnesh Durge, Girish Charpe
Abstract: In today’s digital age, video content plays a major role in communication, learning, and marketing. However, creating animated videos is still a complex and time-consuming task that requires technical skills, expensive software, and professional expertise. Because of this, many students, educators, and small businesses find it difficult to create high-quality animation content. To solve this problem, we developed “Animator”, an AI-powered text-to-video animation system that makes video creation simple and accessible for everyone. The system allows users to generate complete animated videos just by entering a text prompt. It uses advanced technologies such as natural language processing for script generation, Stable Diffusion for image creation, AnimateDiff for animation, and text-to-speech models for voiceover generation. It also automatically generates subtitles and combines all elements into a final video. The system is designed using multiple modules, including input processing, script generation, visual creation, audio generation, subtitle generation, and video rendering. By automating these steps, the system reduces manual effort, saves time, and lowers the cost of video production. The results show that the proposed system can generate quality animated videos efficiently with minimal user input. This project demonstrates how artificial intelligence can act as a powerful creative tool and make content creation easier, faster, and more accessible for everyone.
International Journal of Science, Engineering and Technology