A zero-dependency Python tool for generating and editing high-quality images using the Gemini API and Nano Banana Pro model.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install gemini-image-simple
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 gemini-image-simple 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 Gemini Image Simple?
Gemini Image Simple is a robust, lightweight utility designed to bring high-quality AI image generation and editing to environments where traditional package management is restricted. As a unique entry in the Openclaw Skills library, it operates entirely using the Python standard library, meaning it requires no pip installations, no virtual environments, and functions perfectly on locked-down systems or minimal containers. It leverages Google's Nano Banana Pro (Gemini 3 Pro Image) to provide professional-grade results with zero setup overhead.
This skill is particularly valuable for developers working with Openclaw Skills who need a fail-safe image generation tool that works on free-tier cloud platforms like Fly.io or within constrained Docker images. By utilizing native Python modules like urllib and base64, it ensures maximum compatibility and performance without the bloat of external dependencies.
Gemini Image Simple Use Cases
- Generating photorealistic images from text prompts in environments without pip or uv access.
- Editing existing images by providing natural language instructions and a source file.
- Integrating AI image generation into CI/CD pipelines or lightweight serverless functions.
- Deploying visual AI capabilities to restricted or air-gapped systems where Python 3 is the only available tool.
- Enhancing Openclaw Skills workflows with a reliable, dependency-free media generation layer.
How Gemini Image Simple Works
- The user executes the script via Python 3, passing a text prompt and an optional input image for editing.
- The skill reads the GEMINI_API_KEY from the environment variables to authenticate with Google's AI services.
- Using the built-in urllib.request module, the skill sends a structured JSON payload to the Gemini API endpoint.
- Google's Nano Banana Pro model processes the prompt (and source image, if provided) to generate new visual data.
- The skill receives the base64-encoded image data, decodes it using the native base64 library, and writes the final file to the specified output path.
Gemini Image Simple Setup
To integrate this into your Openclaw Skills setup, ensure you have a valid API key from Google AI Studio. Set your environment variable as follows:
export GEMINI_API_KEY='your_api_key_here'
You can then run the skill immediately using any Python 3.10+ installation:
python3 scripts/generate.py "A cinematic landscape of Mars" mars.png
Gemini Image Simple Data Schema & Taxonomy
The skill manages data primarily through standard file system inputs and outputs without requiring external databases.
| Component | Details |
|---|---|
| Supported Inputs | PNG, JPG, JPEG, GIF, WEBP |
| Output Formats | Generates standard PNG image files |
| Dependencies | Pure Python Standard Library (urllib, json, base64) |
| Model | Defaults to nano-banana-pro-preview (Gemini 3 Pro Image) |
| File Structure | Scripts are contained within the scripts/ directory for modular access |
Gemini Image Simple Advanced Features
- Zero-dependency architecture ensures the skill runs anywhere Python 3 exists.
- Supports advanced image-to-image editing, allowing users to modify existing files with text instructions.
- Built-in support for multiple Google models including Imagen 4.0 Ultra and Gemini 2.5 Flash.
- Designed for seamless integration with other Openclaw Skills via standard CLI interfaces.
- Optimized for high-performance and low-memory usage in containerized environments.
SKILL.md
Loading
Related Openclaw Skills
ClawFlows
A command-line engine designed to search, install, and orchestrate multi-step automations by chaining various Openclaw Skills together.
LiquidSkills: Hyperliquid AI Agent Framework
LiquidSkills provides a specialized knowledge layer for AI agents to bridge the gap between stale training data and production Hyperliquid infrastructure.
SearXNG Search Skill
A privacy-focused metasearch skill that aggregates results from over 70 engines using a self-hosted SearXNG instance.
SearXNG Search Skill
A self-hosted, privacy-respecting metasearch skill that aggregates results from over 70 sources into a structured JSON API.
DS-160 Auto-fill Skill
An intelligent automation skill for completing US nonimmigrant visa DS-160 forms using structured CSV data and AI-assisted captcha solving.
Toggl Time Tracking
A professional time management skill that integrates Toggl Track directly into your AI agent workflow using Openclaw Skills.
METADATA
Featured*
