A versatile multi-provider image generation engine that unifies 9+ AI services into a single CLI for Openclaw Skills.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install panda-imagine
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 panda-imagine 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 Panda Imagine?
Panda Imagine is a robust image generation framework built for Openclaw Skills. It provides a unified abstraction layer over several industry-leading image generation APIs, including OpenAI, Azure, Google Gemini, OpenRouter, DashScope, MiniMax, Jimeng, Seedream, and Replicate. By consolidating these services into a single tool, it allows developers and AI agents to switch between different models and providers without changing their integration logic.
The skill focuses on providing a professional-grade interface for text-to-image and image-to-image workflows. Whether you need a quick 1K preview or a high-fidelity 2K illustration for production use, Panda Imagine handles the provider-specific parameters, authentication, and file management automatically, making it an essential component for visual content automation.
Panda Imagine Use Cases
- Automating the creation of blog and social media post illustrations using multiple AI models.
- Generating consistent UI/UX design assets and placeholders directly from a development environment.
- Using character reference images to maintain visual consistency across a series of generated assets.
- High-volume batch processing of image tasks for data augmentation or marketing campaigns.
How Panda Imagine Works
- The engine initializes by checking for configuration settings in local EXTEND.md files or environment variables to authenticate with chosen providers.
- It analyzes the command-line arguments to determine the generation requirements, such as the prompt, aspect ratio, and output path.
- The skill applies an intelligent selection logic: if a reference image is provided, it prioritizes models that support image-to-image workflows (like Gemini or OpenAI).
- The script executes the API call to the specific provider, handling model-specific peculiarities and scaling requirements (e.g., 2K presets).
- Upon a successful response, the image is downloaded and saved locally, while failures trigger an automatic retry mechanism (up to 3 times).
Panda Imagine Setup
Panda Imagine requires bun or npx to run. Ensure you have the necessary API keys for your preferred providers set in your environment or EXTEND.md file.
# Basic usage to generate an image
bun scripts/main.ts --prompt "A futuristic city" --image city.png
# Optional: Install Jimeng CLI for advanced reference image support
curl -fsSL https://jimeng.jianying.com/cli | bash
dreamina login
Panda Imagine Data Schema & Taxonomy
| Parameter | Description | Supported Values |
|---|---|---|
--prompt |
Main text description | Any string |
--ar |
Aspect ratio control | 16:9, 1:1, 3:4, etc. |
--quality |
Resolution presets | normal, 2k |
--ref |
Reference image paths | Local file paths |
--provider |
Explicit provider choice | openai, google, dashscope, etc. |
--batchfile |
Batch task configuration | Path to JSON file |
Panda Imagine Advanced Features
- Multi-Provider Failover: Automatically falls back to alternative providers if the primary one is unavailable or unsupported for a specific feature.
- Concurrent Batch Processing: Support for parallel image generation jobs via JSON configuration files to maximize throughput.
- Reference Image Integration: Advanced support for image-to-image workflows across diverse providers, including the Jimeng CLI integration.
- Unified Quality Presets: Standardizes output quality (e.g., 1K/2K) across different provider APIs, ensuring consistent results regardless of the backend model.
SKILL.md
Loading
Related Openclaw Skills
Model Context Transfer
A specialized protocol for transferring conversational context, task states, and project memory between different AI models or agents to ensure zero-loss handoffs.
BeHuman
BeHuman is a psychological prompting framework that adds an inner dialogue layer to AI responses, ensuring they sound like a person rather than a robotic assistant.
EchoMemory: Personal Legacy & AI Persona Creator
EchoMemory is a sophisticated tool for creating personalized digital memorials by distilling chat histories, media, and narratives into interactive AI entities.
eBay Product Research
A specialized AI skill for analyzing eBay market data to identify profitable niches, calculate sell-through rates, and assess competition.
E-commerce Ad Performance Diagnostic Skill
A systematic diagnostic framework for identifying and resolving e-commerce advertising anomalies through comprehensive funnel analysis and cross-metric validation.
panda-knowledge-card
A powerful AI agent skill that transforms text and articles into aesthetically pleasing, structured knowledge card images for social media and educational sharing.
Featured*
