A powerful AI image generation skill integrating Midjourney, Flux, and video creation via a streamlined API wrapper.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install imaginepro-api
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 imaginepro-api 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 ImaginePro AI Image Generation?
ImaginePro AI is a versatile skill designed for developers looking to integrate high-end image and video generation into their automated workflows. It provides a unified interface for industry-leading models including Midjourney v6 and Flux, alongside specialized tools for background removal and prompt enhancement. By utilizing Openclaw Skills, users can automate complex visual tasks directly from their coding environment or AI agent.
This skill simplifies the asynchronous nature of AI generation, offering a robust Python helper script that manages the entire lifecycle from submission to final asset retrieval. Whether you need photorealistic landscapes, stylized character portraits, or virtual try-on mockups, this tool provides the necessary infrastructure for professional-grade AI artistry with minimal configuration.
ImaginePro AI Image Generation Use Cases
- Automated generation of marketing assets using Midjourney or Flux models.
- Virtual try-ons and product mockups using the Nano Banana reference-image model.
- Dynamic video creation from static frames for social media or presentations.
- Batch background removal and image upscaling for e-commerce catalogs.
- Enhancing short user prompts into detailed artistic descriptions to improve output quality.
How ImaginePro AI Image Generation Works
- The user provides an API key via the IMAGINEPRO_API_KEY environment variable to authenticate with the platform.
- A generation request is submitted through the API or helper script, specifying the model (e.g., Midjourney, Flux, Lumi Girl).
- The API returns a unique messageId, and the skill enters an asynchronous polling phase.
- The system checks the generation status (SUBMITTED, PROCESSING, DONE) at regular intervals.
- Once the status reaches DONE, the skill retrieves the final image or video URLs for the user.
- Users can then perform post-processing actions like upscaling or background removal on the resulting assets.
ImaginePro AI Image Generation Setup
To get started, you must obtain an API key from the ImaginePro Platform dashboard. Once obtained, configure your environment:
export IMAGINEPRO_API_KEY="your_api_key_here"
You can then use the included Python script to generate images. For example, to generate a Flux image and wait for the result:
python3 imaginepro_api.py wait --prompt "a futuristic neon city" --model flux
ImaginePro AI Image Generation Data Schema & Taxonomy
The skill interacts with the ImaginePro API v1 and processes data according to the following schema:
| Property | Description |
|---|---|
| messageId | A unique UUID used to track the asynchronous generation task. |
| status | Current state of the task: SUBMITTED, PROCESSING, DONE, or FAIL. |
| images | An array of strings containing the URLs of the generated image assets. |
| credits | The credit cost associated with the operation (e.g., 10 for Midjourney, 6 for Flux). |
| progress | An integer from 0 to 100 representing the completion percentage. |
ImaginePro AI Image Generation Advanced Features
- Multi-model support encompassing Midjourney v6 (Alpha), Flux, Nano Banana, and Lumi Girl.
- Built-in prompt enhancement tool that expands short prompts into high-quality descriptions for free.
- Full support for Midjourney parameters such as --ar, --style raw, and --relax directly within the prompt string.
- Reference-based generation capabilities for virtual staging and style transfer workflows.
- Integrated MJ Video support for generating smooth transitions between start and end frames.
SKILL.md
Loading
Related Openclaw Skills
Home Assistant Control (moltbot-ha)
A powerful CLI-based skill to manage Home Assistant entities, services, and automations with a built-in multi-level safety system.
Carapace Runtime Security
A runtime security shell that hardens AI agents against prompt injection, data exfiltration, and unauthorized operations.
Eridian Carapace
A comprehensive security hardening layer that protects OpenClaw agents from prompt injection, data exfiltration, and unauthorized operations at runtime.
PostNitro Carousel Generator
Automate the creation of professional social media carousel posts from text, articles, or social media threads using AI.
Memori Extension
A memory augmentation and LLM interception tool that provides agents with persistent knowledge retrieval and injection capabilities.
Data Visualization CLI
A powerful toolset for generating Unicode charts, graphs, and ASCII tables directly in the terminal from raw data sources.
Featured*
