README.md

metadata

title: Ravi
emoji: 🚀
colorFrom: red
colorTo: red
sdk: docker
app_port: 8501
tags:
  - streamlit
pinned: false
short_description: ravi

README.md for HF Spaces

---

title: AI Video Generator emoji: 🎬 colorFrom: blue colorTo: purple sdk: streamlit sdk_version: 1.28.0 app_file: app.py pinned: true license: apache-2.0 models: - stabilityai/stable-diffusion-2-base tags: - text-to-video - video-generation - stable-diffusion - tts

🎬 AI Video Generator - Hugging Face Spaces Edition

Generate animated videos from text using AI models, optimized for Hugging Face Spaces with GPU support.

Features

• 🎨 AI-Powered Scene Generation: Uses Stable Diffusion for creating scenes
• 🎙️ Natural Voice Narration: Edge-TTS for realistic voice synthesis
• ⚡ GPU Acceleration: Runs on free HF Spaces GPU
• 🎬 Multiple Styles: Cartoon, Anime, Realistic, Watercolor, Fantasy
• 📥 Direct Download: Export as MP4

How to Use

1. Enter Script: Write your story in the text area
2. Process: Click "Process Script" to break into scenes
3. Preview: Review generated scenes
4. Generate: Create the final video
5. Download: Save your video

Examples

Try these example prompts:

• Fantasy adventures
• Sci-fi stories
• Educational content
• Children's tales

Technical Details

• Image Generation: Stable Diffusion 2 Base
• Voice Synthesis: Microsoft Edge-TTS
• Video Processing: MoviePy
• GPU: NVIDIA T4 (when available)

Limitations

• Max video length: ~60 seconds
• Processing time: 2-5 minutes
• GPU availability may vary

Credits

Built with ❤️ using:

• Hugging Face Diffusers
• Streamlit
• MoviePy
• Edge-TTS