A powerful integration for generating and editing AI images across multiple models using a unified API interface.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install image-router
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install image-router using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is ImageRouter AI Image Generation?
The imagerouter skill provides a streamlined interface to the ImageRouter API, allowing developers to generate images from text or transform existing images using a vast array of AI models. By leveraging Openclaw Skills, users can bypass the complexity of individual model APIs and use a single, consistent set of commands to access top-tier image generation technology.
This skill is built for developers who need flexibility and speed. It abstracts away the differences between various image generation providers, offering a unified endpoint for text-to-image, image-to-image, and inpainting tasks. Whether you are using a test model for prototyping or a high-end production model, this skill ensures your workflow remains consistent and efficient.
ImageRouter AI Image Generation Use Cases
- Rapidly generating unique assets for marketing materials using text-to-image prompts.
- Transforming existing images into new styles through image-to-image processing.
- Performing precision inpainting and object replacement using mask support.
- Batch processing image generations for creative experimentation or dataset creation.
- Integrating AI-driven visual content generation into CI/CD pipelines or automated scripts.
How ImageRouter AI Image Generation Works
- The user identifies a target image model by searching the ImageRouter catalog or selecting popular models via the API.
- A request is constructed using either the JSON endpoint for simple text-to-image tasks or the unified multipart endpoint for advanced editing.
- The skill authenticates with the ImageRouter API using a secure bearer token provided by the user.
- ImageRouter processes the request (generation, transformation, or masking) and returns a comprehensive JSON response including costs and latency.
- The resulting image URL or base64 data is provided to the user for immediate use, download, or further processing by other Openclaw Skills.
ImageRouter AI Image Generation Setup
First, obtain an API key from the ImageRouter dashboard. Ensure you have curl and jq installed for the best experience with Openclaw Skills.
# Set your API Key for easy access
export IMAGEROUTER_API_KEY='YOUR_API_KEY'
# Basic text-to-image generation test
curl 'https://api.imagerouter.io/v1/openai/images/generations' \
-H "Authorization: Bearer $IMAGEROUTER_API_KEY" \
--json '{"prompt": "a cyberpunk city", "model": "test/test"}'
ImageRouter AI Image Generation Data Schema & Taxonomy
The skill utilizes the following parameters to organize requests and process metadata:
| Parameter | Requirement | Description |
|---|---|---|
model |
Required | The ID of the image model (e.g., test/test, gemini). |
prompt |
Optional | Text description of the desired image. |
quality |
Optional | Visual fidelity: auto, low, medium, or high. |
size |
Optional | Dimensions like 1024x1024 or auto. |
response_format |
Optional | Return format: url, b64_json, or b64_ephemeral. |
output_format |
Optional | File type: webp, jpeg, or png. |
ImageRouter AI Image Generation Advanced Features
- Support for multi-image processing (up to 16 input images) for complex compositions and blends.
- Precision inpainting capabilities using specialized mask files for localized image editing.
- Unified endpoint architecture that supports both OpenAI-compatible JSON and multipart form data.
- Ephemeral response options to enhance privacy by preventing sensitive image data from being stored in logs.
- Robust model discovery tools to search and sort available AI models by popularity or date.
SKILL.md
Loading
Related Openclaw Skills
Task Experience Summaries
A specialized knowledge base for diagnosing and resolving common technical hurdles when developing or using Openclaw Skills.
Task Experience Logger
A systematic documentation tool for AI agents to log problems, solutions, and verified configurations into long-term memory.
OpenClaw Plugin Installation Troubleshooter
A comprehensive diagnostic guide designed to identify and resolve common package name mismatches and permission errors during the setup of Openclaw Skills.
Edge TTS English
A high-fidelity text-to-speech engine for AI agents that generates natural-sounding English audio using Microsoft Edge TTS.
Find Skills
The Find Skills tool empowers users to dynamically discover and install modular agent capabilities from the Openclaw Skills ecosystem.
Aili-chan: Persistent Tsundere Persona
A sophisticated emotional immersion skill that transforms AI agents into a persistent, sharp-tongued yet affectionate companion personality.
Featured*
