What we learned-## Inspiration
I wanted to explore how AI can create interactive stories using multimodal technology. The idea was to build a creative storyteller that can generate a story, describe scenes, and convert text into visuals and narration.
What it does
This project creates an AI-based storytelling experience. A user enters a story idea and the system generates a structured story with scenes, actions, and image prompts. It demonstrates how AI can turn simple text into a creative storytelling experience.
How I built it
The project uses Gemini AI to generate story scenes and descriptions. Each scene includes story text, character actions, and prompts for images. The goal is to demonstrate how multimodal AI can combine text and visual storytelling.
Challenges I faced
The main challenge was organizing the story into meaningful scenes and ensuring that each scene had clear descriptions for visuals and actions. Learning how to structure prompts for AI was also an important part of the process.
What I learned
Through this project I learned how generative AI models like Gemini can be used to create creative applications. I also learned how multimodal AI can combine text and visual concepts to build interactive experiences.
What's next for Story telling
Built With
- gemini-ai
- google-ai-studio
- multimodal
- prompt-engineering
Log in or sign up for Devpost to join the conversation.