AI StoryTeller is a premium web application that breathes life into your photos. By leveraging the power of BLIP (Image Captioning) and Google Gemini 2.0, it transforms visual moments into enchanting, human-like stories with just a few clicks.
- π¨ Premium Dark UI: A modern, immersive interface featuring glassmorphism, smooth animations, and a "Magic" aesthetic.
- πΌοΈ Instant Image Preview: See your moments immediately before they are transformed.
- π€ Gemini 2.0 Powered: Utilizes the latest
gemini-2.0-flashmodel for intelligent and creative storytelling. - π Genre & Mood Control: Guide the AI's creativity by selecting specific genres (Fantasy, Sci-Fi, Mystery) and moods (Whimsical, Cinematic, Tense).
- β‘ Real-time Feedback: Engaging loading states and refined error handling ("Magic Interrupted") for a seamless experience.
- Backend: FastAPI (Python)
- AI Models:
- Image Captioning: Salesforce BLIP
- Storytelling: Google Gemini 2.0 Flash
- Frontend: Vanilla HTML5, CSS3 (Modern Glassmorphism Design), JavaScript (ES6+)
- Environment: Python Dotenv for secure key management.
git clone https://github.com/yourusername/AI-StoryTeller.git
cd AI-StoryTellerpython -m venv venv
# On Windows:
.\venv\Scripts\activate
# On macOS/Linux:
source venv/bin/activatepip install -r requirements.txtCreate a .env file in the root directory and add your Google Gemini API key:
GEMINI_API_KEY=your_actual_api_key_herepython -m app.mainHead over to http://127.0.0.1:8000 to start crafting your stories!
- Secure Keys: The
.envfile is protected and ignored by Git. - Private Media: The
uploads/directory and temporary image files are excluded from commits to ensure your privacy.
This project is licensed under the MIT License.