ai-video-gen

# AI Video Generation Skill

Generate complete videos from text descriptions using AI.

## Capabilities

1. **Image Generation** - DALL-E 3, Stable Diffusion, Flux
2. **Video Generation** - LumaAI, Runway, Replicate models
3. **Voice-over** - OpenAI TTS, ElevenLabs
4. **Video Editing** - FFmpeg assembly, transitions, overlays

## Quick Start

```bash
# Generate a complete video
python skills/ai-video-gen/generate_video.py --prompt "A sunset over mountains" --output sunset.mp4

# Just images to video
python skills/ai-video-gen/images_to_video.py --images img1.png img2.png --output result.mp4

# Add voiceover
python skills/ai-video-gen/add_voiceover.py --video input.mp4 --text "Your narration" --output final.mp4
```

## Setup

### Required API Keys

Add to your environment or `.env` file:

```bash
# Image Generation (pick one)
OPENAI_API_KEY=sk-...              # DALL-E 3
REPLICATE_API_TOKEN=r8_...         # Stable Diffusion, Flux

# Video Generation (pick one)
LUMAAI_API_KEY=luma_...           # LumaAI Dream Machine
RUNWAY_API_KEY=...                # Runway ML
REPLICATE_API_TOKEN=r8_...        # Multiple models

# Voice (optional)
OPENAI_API_KEY=sk-...             # OpenAI TTS
ELEVENLABS_API_KEY=...            # ElevenLabs

# Or use FREE local options (no API needed)
```

### Install Dependencies

```bash
pip install openai requests pillow replicate python-dotenv
```

### FFmpeg

Already installed via winget.

## Usage Examples

### 1. Text to Video (Full Pipeline)

```bash
python skills/ai-video-gen/generate_video.py \
  --prompt "A futuristic city at night with flying cars" \
  --duration 5 \
  --voiceover "Welcome to the future" \
  --output future_city.mp4
```

### 2. Multiple Scenes

```bash
python skills/ai-video-gen/multi_scene.py \
  --scenes "Morning sunrise" "Busy city street" "Peaceful night" \
  --duration 3 \
  --output day_in_life.mp4
```

### 3. Image Sequence to Video

```bash
python skills/ai-video-gen/images_to_video.py \
  --images frame1.png fram...

# AI Video Generator

Complete end-to-end AI video creation system.

## ✅ Installation Status

- [x] FFmpeg installed
- [x] Python 3.11.9 available
- [ ] Python dependencies (run `setup.bat`)
- [ ] API keys configured

## Quick Start

### 1. Install Dependencies

```bash
cd skills/ai-video-gen
pip install -r requirements.txt
```

Or run `setup.bat`

### 2. Configure API Keys

Copy `.env.example` to `.env` and add your keys:

```bash
copy .env.example .env
notepad .env
```

**Minimum required:**
- `OPENAI_API_KEY` - For both image (DALL-E) and voice (TTS)

**Optional but recommended:**
- `LUMAAI_API_KEY` - For video generation (has free tier!)
- `REPLICATE_API_TOKEN` - Alternative for images/video

### 3. Generate Your First Video

```bash
python generate_video.py --prompt "A serene mountain landscape at sunset" --output test.mp4
```

With voiceover:

```bash
python generate_video.py \
  --prompt "A futuristic city with flying cars" \
  --voiceover "Welcome to the future" \
  --output future.mp4
```

## What You Need to Sign Up For

### Free/Cheap Options (Start Here)

1. **OpenAI** - https://platform.openai.com
   - Get API key for DALL-E + TTS
   - Cost: ~$0.05-0.10 per video (image + voice)
   
2. **LumaAI** - https://lumalabs.ai
   - Free tier: 30 generations/month
   - Then $1-2 per video

**Total cost to start: $0-0.15 per video**

### Premium Options (Better Quality)

3. **Runway** - https://runwayml.com
   - Higher quality video generation
   - ~$0.50-1.00 per 5-second video

4. **ElevenLabs** - https://elevenlabs.io
   - Best voice quality
   - ~$0.30 per 1K characters

5. **Replicate** - https://replicate.com
   - Multiple AI models
   - Pay-per-use, very cheap

## Examples

### Simple Video
```bash
python generate_video.py --prompt "Ocean waves crashing" --output waves.mp4
```

### Multi-Image to Video
```bash
python images_to_video.py --images img1.png img2.png img3.png --output slideshow.mp4
```

### Add Narration to Existing Video
```bash
python add_vo...