---
title: Video AdGenesis Studio
emoji: 🎬
colorFrom: blue
colorTo: purple
sdk: docker
sdk_version: latest
pinned: false
license: mit
---

# Video Genesis Studio

AI-powered video generation studio with React frontend and FastAPI backend. Create professional videos from text prompts and images using cutting-edge AI models.

## Features

✨ **AI Video Generation**
- KIE Veo 3.1 integration for high-quality video generation
- Text-to-video and image-to-video support
- Real-time progress tracking

🖼️ **Image Processing**
- Intelligent image compression
- Multiple format support
- Automatic optimization

🎬 **Video Processing**
- Frame extraction
- Video trimming and concatenation
- Full ffmpeg integration

## Setup

### Environment Variables

Set these in your Hugging Face Space settings:

**Required:**
- `KIE_API_KEY` - Get from https://kie.ai/api-key

**Optional:**
- `VITE_GEMINI_API_KEY` - For Gemini AI features
- `OPENAI_API_KEY` - For GPT-4o prompt generation
- `REPLICATE_API_TOKEN` - For Replicate video generation
- `VITE_API_BASE_URL` - Your Space URL (auto-set by HF, but can override)
- `ENVIRONMENT` - Set to `production`

### Getting Your API Keys

1. **KIE API Key** (Required):
   - Visit https://kie.ai/api-key
   - Sign up or log in
   - Copy your API key

2. **Gemini API Key** (Optional):
   - Visit https://makersuite.google.com/app/apikey
   - Create a new API key
   - Copy the key

3. **OpenAI API Key** (Optional):
   - Visit https://platform.openai.com/api-keys
   - Create a new secret key
   - Copy the key

4. **Replicate Token** (Optional):
   - Visit https://replicate.com/account/api-tokens
   - Create a new token
   - Copy the token

## Usage

1. **Set Environment Variables**:
   - Go to your Space settings
   - Add all required environment variables
   - Save and restart the Space

2. **Access the App**:
   - Your Space will be available at: `https://your-username-video-genesis-studio.hf.space`
   - The frontend loads automatically
   - API docs available at: `/docs`

3. **Generate Videos**:
   - Enter a text prompt
   - Optionally upload images
   - Select video model and settings
   - Click generate and wait for results

## API Endpoints

- `GET /health` - Health check
- `GET /docs` - API documentation (Swagger UI)
- `POST /api/veo/generate` - Start video generation
- `GET /api/veo/status/{task_id}` - Check generation status
- `POST /api/prompts/generate` - Generate prompts with AI

## Technical Details

- **Backend**: FastAPI (Python 3.11)
- **Frontend**: React + TypeScript + Vite
- **Video Processing**: FFmpeg
- **AI Models**: KIE Veo 3.1, Gemini, GPT-4o

## License

MIT License