Setup & Installation
openclaw skills install @eric51/ollama-x-z-image-turbo
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install ollama-x-z-image-turbo
What This Skill Does
Generates images locally using Ollama's x/z-image-turbo model and sends them to a WhatsApp recipient. Accepts a text prompt with optional parameters for dimensions, denoising steps, seed, and negative prompt.
Runs image generation on local hardware via Ollama, avoiding cloud API costs and keeping prompts off external servers.
When to use it
- Sending a generated illustration to a WhatsApp contact
- Creating visual references for a group chat discussion
- Generating images at custom resolutions for different layouts
- Reproducing a specific image using a fixed seed value
- Attaching AI-generated artwork to a WhatsApp message caption
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: Generate an image of a robot in a forest and send it to +1234567890
AGENT
- 1Run the runner.py script with the prompt 'a robot in a forest' and default 1024x1024 resolution at 20 steps
- 2Wait for Ollama to generate and save the image to the workspace tmp directory
- 3Send a WhatsApp message to +1234567890 with the generated image file attached
OUTPUT
WhatsApp message delivered to +1234567890 with the robot-in-forest image and optional caption
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.
Ollama installed and running on http://127.0.0.1:11434x/z-image-turbo:latest model pulled in OllamaWhatsApp account configured in OpenClaw