Nexa.ai / README.md
umar8902's picture
Update README.md
e162f12 verified
|
Raw
History Blame Contribute Delete
1.34 kB
---
title: Nexa AI
emoji: ๐Ÿš€
colorFrom: blue
colorTo: green
sdk: docker
app_port: 7860
pinned: false
---
# Nexa AI - Video Text Overlay & AI Assistant
This app provides a professional AI assistant with real-time web search, image generation, and a powerful **Video Text Overlay** tool.
## Features
- **Video Text Overlay**: Upload a video and add custom text with transitions (Fade In/Out).
- **AI Assistant**: Powered by Qwen 2.5 and local fallback models.
- **Web Search**: Multi-engine fallback (DDG, Bing, Wikipedia).
- **Image Generation**: High-quality visuals via Pollinations AI.
- **File Analysis**: PDF, Docx, and Image OCR.
## Hugging Face Spaces Deployment
1. Create a new Space on [Hugging Face](https://huggingface.co/new-space).
2. Select **Docker** or **Blank** (this app is designed to run as a Python Space).
3. If using **Docker**, use the `python:3.10` base image.
4. Upload all files from this repository.
5. Ensure `requirements.txt` is present.
6. The app will automatically run on port 7860.
### URL Generation API
You can generate videos via a direct URL:
`https://your-space-url.hf.space/generate?video=VIDEO_URL&text=HELLO&pos=bottom`
## Stack
- **Backend**: Flask
- **Video Processing**: MoviePy
- **Frontend**: HTML5, CSS3, JavaScript (Lucide Icons, Marked.js)
- **Deployment**: Hugging Face Spaces