A comprehensive image generation toolkit for Openclaw Skills that provides a unified interface for 8 industry-leading AI models including Midjourney and Flux.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install image-gen
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-gen 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 Image Generation Skill?
The Image Generation Skill is a robust extension for Openclaw Skills designed to streamline the creation of high-fidelity visual content. It acts as a bridge between your AI agent and top-tier generation engines like Midjourney, Flux, Ideogram, and Recraft. By abstracting the complexity of different API architectures, this skill allows users to generate everything from cinematic masterpieces and photorealistic portraits to vector icons and logos using simple, standardized commands.
This skill is particularly powerful because it handles the heavy lifting of asynchronous polling, especially for Midjourney tasks, ensuring that the developer or user receives a final image URL without managing complex job states. It serves as an essential tool for developers building creative assistants or automated content pipelines within the Openclaw Skills ecosystem.
Image Generation Skill Use Cases
- Creating cinematic and artistic illustrations using Midjourney for high-end creative projects.
- Generating photorealistic product photography and professional portraits with Flux-Pro.
- Designing brand assets, including logos and typography-heavy posters, using Ideogram.
- Producing flat design icons and vector-style illustrations for UI/UX projects via Recraft.
- Rapidly iterating on visual concepts using high-speed models like Flux-Schnell for instant previews.
How Image Generation Skill Works
- The system identifies the user's visual intent and selects the most appropriate model (e.g., Midjourney for art, Flux for realism).
- The skill automatically enhances the user's prompt by adding model-specific quality descriptors like 'cinematic lighting' or 'masterpiece'.
- A CLI command is triggered using the generate.js script, passing parameters for the model, prompt, and aspect ratio.
- The skill manages the request lifecycle, including blocking until asynchronous tasks (like Midjourney's generation grid) are complete.
- The tool returns a unified JSON response containing the primary image URL and an array of all generated variants for the agent to display.
Image Generation Skill Setup
To integrate this into your Openclaw Skills environment, first install the required fal.ai client:
npm install @fal-ai/client
Then, configure your API keys in the ~/.openclaw/openclaw.json configuration file:
{
"skills": {
"entries": {
"image-gen": {
"enabled": true,
"env": {
"FAL_KEY": "your_fal_key_here",
"LEGNEXT_KEY": "your_legnext_key_here"
}
}
}
}
}
Image Generation Skill Data Schema & Taxonomy
The skill produces a structured output that ensures compatibility across different agent interfaces:
| Property | Type | Description |
|---|---|---|
| success | boolean | Confirmation of successful image generation. |
| model | string | The specific AI model ID used for the task. |
| imageUrl | string | The direct link to the primary high-resolution image. |
| images | array | A collection of URLs for all generated images (e.g., the 4 images in a Midjourney grid). |
Image Generation Skill Advanced Features
- Automated Async Polling: Eliminates the need for manual status checks; the skill waits for the final result automatically.
- Midjourney Post-Processing: Supports advanced actions such as upscaling (Subtle/Creative), variations (Subtle/Strong), and rerolling directly from the CLI.
- Consistency Tools: Provides support for reference images with models like Nano Banana to maintain character or style consistency.
- Intelligent Prompt Expansion: Automatically translates simple user requests into highly detailed, model-optimized prompts for better output quality.
SKILL.md
Loading
Related Openclaw Skills
Image Enhancer
An automated utility for upscaling, sharpening, and refining screenshots and digital images for professional use.
GitHub Gem Seeker
A specialized tool for finding and implementing battle-tested open-source GitHub projects to solve technical problems without reinventing the wheel.
ElevenLabs MCP Server
A specialized skill that launches an MCP server to provide comprehensive ElevenLabs audio generation and transcription tools to AI agents.
AudioMind
AudioMind is an all-in-one AI podcast production suite that automates scripting, narration, music generation, and audio mixing in a single command.
Image Generation Skill
A versatile image generation skill that intelligently selects between Midjourney, Flux, and specialty models to create high-quality visuals.
Kling 3.0 Omni Video Generator
A high-performance AI agent skill for generating cinema-quality video and audio-synced content using the Kling 3.0 Omni model.
METADATA
Featured*
