Ai Media

# ai-media - AI Media Generation

Full-stack AI media generation powered by GPU server (RTX 3090/3080/2070S).

## Capabilities

1. **Image Generation** — Photorealistic images via ComfyUI (z-image, Juggernaut XL)
2. **Video Generation** — Video synthesis via ComfyUI (AnimateDiff, LTX-2)
3. **Talking Heads** — Animated talking faces via SadTalker
4. **Voice Synthesis** — Natural TTS via Voxtral (whisper.cpp)

## GPU Server

- **Host:** `${GPU_USER}@${GPU_HOST}`
- **SSH Key:** `~/.ssh/id_ed25519_gpu`
- **ComfyUI:** `/data/ai-stack/comfyui/ComfyUI/` (port 8188)
- **SadTalker:** `/data/ai-stack/sadtalker/`
- **Voxtral:** `/data/ai-stack/whisper/`
- **Output:** `/data/ai-stack/output/`

## Usage

### Generate Image

```bash
./scripts/image.sh "lady on beach at sunset" realistic
./scripts/image.sh "cyberpunk cityscape" artistic
```

**Arguments:**
- `$1`: Prompt text
- `$2`: Style (realistic|artistic) — optional, default: realistic

**Output:** Path to generated image (e.g., `/data/ai-stack/output/image_001.png`)

### Generate Video

```bash
./scripts/video.sh "waves crashing on shore" animatediff 4
./scripts/video.sh "city traffic timelapse" ltx2 8
```

**Arguments:**
- `$1`: Prompt text
- `$2`: Model (animatediff|ltx2) — optional, default: animatediff
- `$3`: Duration in seconds — optional, default: 4

**Output:** Path to generated video (e.g., `/data/ai-stack/output/video_001.mp4`)

### Generate Talking Head

```bash
./scripts/talking-head.sh "Hello, I'm Agent" gentle input.jpg
./scripts/talking-head.sh "Welcome to the future" neutral photo.png
```

**Arguments:**
- `$1`: Speech text
- `$2`: Voice style (gentle|neutral|energetic) — optional, default: gentle
- `$3`: Avatar image path — optional, generates default if not provided

**Output:** Path to talking head video (e.g., `/data/ai-stack/output/talking_001.mp4`)

### Generate Audio

```bash
./scripts/audio.sh "This is a test message" en male
./scripts/audio.sh "Bonjour le monde" fr female
```

**Arguments:**
- `$1`:...

# ai-media - Quick Start

AI media generation skill for OpenClaw/EvoClaw agents.

## Installation

```bash
# Clone/copy to your skills directory
cp -r skills/ai-media ~/.openclaw/skills/

# Or for EvoClaw
cp -r skills/ai-media ~/.evoclaw-hub/skills/
```

## Quick Examples

### Generate an Image
```bash
cd ~/.openclaw/skills/ai-media
./scripts/image.sh "lady on beach at sunset" realistic
```

### Generate a Video
```bash
./scripts/video.sh "waves crashing on shore" animatediff 4
```

### Create Talking Head
```bash
./scripts/talking-head.sh "Hello world!" gentle
```

### Generate Voice Audio
```bash
./scripts/audio.sh "This is a test" en male
```

## Status

✅ **Talking heads** — SadTalker fully working  
⏳ **Video (AnimateDiff)** — Working, automation pending  
⏳ **Video (LTX-2)** — Models ready, workflow integration pending  
⏳ **Image** — Models downloading (z-image 43%, Juggernaut ready)  
⏳ **Audio** — Using gTTS, Voxtral integration pending  

## GPU Server

All generation happens on GPU server `peter@10.0.0.44`:
- **RTX 3090** (primary)
- **RTX 3080** (secondary)  
- **RTX 2070 Super** (tertiary)

SSH key required: `~/.ssh/id_ed25519_alexchen`

## Next Steps

1. ✅ Complete z-image download (9/21 files, ~57% remaining)
2. ✅ Set up LTX-2 ComfyUI workflow
3. Implement ComfyUI API automation (HTTP calls instead of manual)
4. Integrate Voxtral for higher quality TTS
5. Add batch generation support
6. Publish to ClawHub

---

**Maintainer:** Alex Chen  
**Version:** 1.0.0  
**GPU Server:** peter@10.0.0.44