ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified media Safety 4/5

gemini-image-gen

Generate and edit images via Google Gemini API. Supports Gemini native generation, Imagen 3, style presets, and batch generation with HTML gallery. Zero dependencies — pure Python stdlib.

Why use this skill?

Generate and edit high-quality images using Google Gemini and Imagen 3. A lightweight, dependency-free Python CLI tool for batch creation and style presets.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/iisweetheartii/gemini-image-gen
Or

What This Skill Does

The gemini-image-gen skill is a powerful command-line interface tool designed to facilitate image generation and manipulation through Google's Gemini and Imagen 3 APIs. By leveraging pure Python standard library modules, it offers a lightweight, dependency-free solution for AI-powered visual creation. Users can generate high-quality imagery from text prompts, apply sophisticated style presets, and perform image editing tasks (such as background modification) natively within the terminal. The skill also includes batch processing capabilities, automatically organizing outputs into timestamped folders and generating HTML galleries for quick visual reviews.

Installation

To integrate this skill into your OpenClaw environment, execute the following command in your terminal: clawhub install openclaw/skills/skills/iisweetheartii/gemini-image-gen Ensure you have a valid Google API key, which must be exported as an environment variable: export GEMINI_API_KEY="your-key-here". No additional pip packages are required, as the skill operates entirely on native Python.

Use Cases

This skill is ideal for rapid prototyping of visual content, generating creative assets for marketing, or experimenting with different artistic styles without leaving the command line. Content creators can use the batch generation feature to explore multiple prompt variations simultaneously, while developers can integrate it into automation pipelines using the Python subprocess module. Its editing functionality makes it particularly useful for quick iteration on existing images, such as resizing or altering environmental details.

Example Prompts

  1. "OpenClaw, generate a futuristic cyberpunk city skyline with neon lights using the cyberpunk style preset."
  2. "Create 4 high-quality photorealistic images of a serene mountain landscape at golden hour."
  3. "Edit my existing image at path/to/art.png to change the background to a sunset beach scene using the Gemini engine."

Tips & Limitations

  • Styles: Use the --styles flag to view the full library of preset configurations. Applying styles can significantly alter the outcome, so experiment with combining them with specific descriptive keywords.
  • Performance: While the tool is fast, remember that API usage is subject to Google's rate limits. Batching too many requests at once may trigger cooldowns.
  • Compatibility: The image editing feature currently relies on the gemini engine; ensure you select this engine when performing modifications. The imagen engine is optimized specifically for high-fidelity generation.

Metadata

Stars2387
Views0
Updated2026-03-09
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-iisweetheartii-gemini-image-gen": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#image-generation#ai-art#google-gemini#cli-tools
Safety Score: 4/5

Flags: file-write, file-read, external-api