3d-cog

---
name: 3d-cog
description: "Create 3D models from text, images, or sketches. Game assets, product visualization, characters, props, environments. Batch generation. Use for games, AR/VR, e-commerce, 3D printing. Outputs: GLB. Powered by CellCog."
metadata:
  openclaw:
    emoji: "💎"
    os: [darwin, linux, windows]
author: CellCog
homepage: https://cellcog.ai
dependencies: [cellcog]
---

# 3D Cog - AI 3D Model Generation

Create 3D models from text, images, or sketches — production-ready GLB files.

---

## Prerequisites

This skill requires the `cellcog` skill for SDK setup and API calls.

```bash
clawhub install cellcog
```

**Read the cellcog skill first** for SDK setup. This skill shows you what's possible.

**OpenClaw agents (fire-and-forget — recommended for long tasks):**
```python
result = client.create_chat(
    prompt="[your task prompt]",
    notify_session_key="agent:main:main",  # OpenClaw only
    task_label="my-task",
    chat_mode="agent",  # See cellcog skill for all modes
)
```

**All other agents (blocks until done):**
```python
result = client.create_chat(
    prompt="[your task prompt]",
    task_label="my-task",
    chat_mode="agent",
)
```

See the **cellcog** mothership skill for complete SDK API reference — delivery modes, timeouts, file handling, and more.

---

## What CellCog Has Internally

1. **Image-to-3D Model** — Converts reference images into textured 3D models. Supports normal and geometry modes.
2. **Image Generation Models** — Creates optimized reference images from text descriptions or rough sketches before 3D conversion.
3. **Configurable Output** — PBR materials (metallic, roughness, normal textures), polygon count from 40K to 1.5M faces.

The agent orchestrates: **generate/enhance reference image → convert to 3D model → output GLB with textures**.

---

## What You Can Create

- Game assets (characters, weapons, props, vehicles, environment pieces)
- Product visualization (e-commerce 3D viewers, packaging mockups)
- AR/VR