Skill: OpenClaw integration — nano-banana & gpt-image image generation

OpenClaw has recently become very popular. We've added an image-generation skill that supports multiple models and resolutions. Once configured, you can ask the AI to generate images using natural language.

Step 1 — Get an API Key

Register at https://api.morphogen.top and go to the Token Management page to get your API key (format: sk-xxxxxxxx). You'll need this key later.

Step 2 — Configure environment variables

Add the following two variables to the .env file in your ~/.openclaw directory (create the file if it doesn't exist):

# VAPI
VAPI_BASE_URL=https://api.morphogen.top/v1
VAPI_API_KEY=sk-xxxxxx

VAPI_BASE_URL is optional. VAPI_API_KEY is required and should be the key you obtained from https://api.morphogen.top.

Storing the API key in environment variables keeps secrets safer—avoid putting keys directly in code.

Step 3 — Install the skill

On a device with OpenClaw installed, run one of the following commands to install the plugin:

clawhub install vapi-image-gen

# or
clawhub install popdo/vapi-image-gen

After installation, restart ClawHub:

openclaw gateway restart

Example prompts

Once configured, just tell your AI assistant what you want.

1. Basic generation

English	Translation
Draw a sunset over the ocean	Draw a seascape sunset
Generate a cyberpunk city at night	Generate a cyberpunk city night scene
Create a cute cartoon cat illustration	Draw a cute cartoon cat illustration

2. With aspect ratio

English	Translation
Generate a 16:9 wallpaper of a starry sky	Generate a 16:9 starry sky wallpaper
Draw a 2:3 portrait of a fantasy warrior	Draw a 2:3 portrait of a fantasy warrior
Create a 1:1 square avatar of a fox in a suit	Create a 1:1 square avatar of a fox in a suit

3. Save to local

English	Translation
Generate a forest scene and save it	Generate a forest scene image and save locally
Draw 3 variations of a mountain landscape and save	Draw 3 mountain landscape variations and save locally

4. High resolution

English	Translation
Generate a high-res 4K illustration of a dragon	Generate a high-res 4K dragon illustration
Create a 2K detailed city map illustration	Generate a 2K detailed city map illustration

---

Supported models

Model	Quality	Output
nano-banana	Standard	URL
nano-banana-pro ⭐	Better — Default	URL
nano-banana-2	Gen 2	URL
nano-banana-pro-2k	High-res 2K	URL
nano-banana-pro-4k	Ultra 4K	URL
gpt-image-1	High quality	Saved file
gpt-image-1.5	Higher quality	Saved file

---

Image save behavior

Flag	Behavior
(default)	Returns image URL only, no local file
--save	Saves to ~/.openclaw/media/
--oss	Saves to ~/.openclaw/oss/
gpt-image models	Always saved (API returns base64 only)

---

Links

• clawhub skill page