A versatile image generation skill that intelligently selects between Midjourney, Flux, and specialty models to create high-quality visuals.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install image-q
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-q 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?
This skill provides a unified interface for state-of-the-art image generation models including Midjourney, Flux 1.1 Pro, and Ideogram. It simplifies the creative process for Openclaw Skills by automatically selecting the best engine based on user intent, whether that is cinematic realism or vector-style icons. The skill leverages professional-grade APIs from Legnext.ai and fal.ai, ensuring high stability and speed. It is designed to handle complex workflows like asynchronous polling and automated upscaling within a single interaction turn, providing a seamless experience for developers and end-users alike.
Image Generation Skill Use Cases
- Creating cinematic and artistic visuals using Midjourney integrations.
- Generating photorealistic product shots or portraits with Flux 1.1 Pro.
- Designing logos and typography-heavy graphics via Ideogram v3.
- Producing vector art and flat design assets using Recraft v3.
- Rapid prototyping with ultra-fast models like Flux Schnell for quick iterations.
How Image Generation Skill Works
- Analyzes the user request to identify subjects, styles, and specific model requirements.
- Enhances the user prompt with model-specific descriptors for lighting, detail, and composition to ensure high-quality output.
- Executes the generation script via the CLI with appropriate parameters such as aspect ratio and model ID.
- For Midjourney tasks, performs same-turn polling to monitor job status until completion without requiring additional user input.
- Returns high-quality, non-expiring image URLs directly to the user interface.
Image Generation Skill Setup
Install the necessary dependencies and configure your environment variables in your configuration file to start using this part of Openclaw Skills.
npm install @fal-ai/client
Add your API keys to your openclaw.json file:
{
"skills": {
"entries": {
"image-gen": {
"enabled": true,
"env": {
"FAL_KEY": "your_fal_key",
"LEGNEXT_KEY": "your_legnext_key"
}
}
}
}
}
Alternatively, you can use the proxy mode by setting the IMAGE_GEN_PROXY_URL to avoid manual API key management.
Image Generation Skill Data Schema & Taxonomy
The skill utilizes a structured CLI argument system and returns metadata for persistent access and tracking.
| Parameter | Type | Description |
|---|---|---|
| --model | String | ID of the model (e.g., midjourney, flux-pro, sdxl) |
| --prompt | String | The enhanced text description for generation |
| --aspect-ratio | String | Output dimensions (e.g., 16:9, 1:1, 4:3) |
| --job-id | String | Unique identifier for tracking asynchronous tasks |
| --num-images | Number | Number of images to generate (1-4) |
Results are returned as an array of validated URLs, specifically focusing on displayImageUrl or imageUrls to avoid expired temporary links.
Image Generation Skill Advanced Features
- Same-turn polling for Midjourney to ensure results are delivered in a single interaction without extra user prompts.
- Automated upscaling for grid-based generations to provide high-resolution individual files immediately.
- Proxy mode support featuring token-based authentication with 100 free generations for Openclaw Skills users.
- Support for specialized post-generation actions including variations (V1-V4), rerolls, and creative vs. subtle upscaling.
- Multi-model intelligence that maps user intent to the most effective AI model automatically.
SKILL.md
Loading
Related Openclaw Skills
Image Generation Skill
A comprehensive image generation toolkit for Openclaw Skills that provides a unified interface for 8 industry-leading AI models including Midjourney and Flux.
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.
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.
Stock Analysis
A comprehensive toolset for analyzing stocks, company profiles, and financial market data through real-time technical and fundamental insights.
Featured*
