gemini-image-gen

Generate and edit images via the Gemini Image Generation API with provider fallback.

5|Updated Feb 20, 2026
One-click install
npx skills add https://github.com/best/openclaw-skills --skill gemini-image-gen-best
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gemini-image-gen
Source: https://github.com/best/openclaw-skills/tree/main/gemini-image-gen
Command: npx skills add https://github.com/best/openclaw-skills --skill gemini-image-gen-best

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai, pillow, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the creation and modification of images using advanced AI models, eliminating the need for complex graphic design software or manual editing for many common tasks.

Core Features & Use Cases

  • Text-to-Image Generation: Create original images from detailed text descriptions.
  • Image Editing: Modify existing images based on natural language instructions (e.g., change colors, add elements).
  • Multi-Image Composition: Combine up to 14 images into a single scene.
  • Resolution & Aspect Ratio Control: Specify output size and dimensions.
  • Provider Fallback: Automatically tries multiple AI providers for increased success rates.
  • Use Case: Generate a unique banner image for a blog post based on its topic, or edit a product photo to change its background color.

Quick Start

Use the gemini-image-gen skill to generate an image of a futuristic cityscape at sunset and save it as 'cityscape.png'.

Frequently Asked Questions about gemini-image-gen

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate images from text using the Gemini API?

You can generate images from text using the Gemini API by providing detailed text descriptions to the skill, which executes Python scripts to create original visuals and saves them as image files.

Can I edit existing images and change backgrounds with natural language instructions?

You can edit existing images by providing natural language instructions to the skill, which modifies colors, adds elements, and changes backgrounds based on your commands.

Does this image generation skill support 4K resolution and custom aspect ratios?

Yes, this image generation skill supports 4K resolution and custom aspect ratios. It allows you to specify output size and dimensions through input parameters for precise creative control.

What's the best way to combine multiple images into one scene using AI?

The best way to combine multiple images into one scene is using this skill's multi-image composition feature, which merges up to 14 images through Python scripts into a single output.

Do I need Python and Pillow installed to run AI image generation scripts?

Yes, you need Python and Pillow installed to run these AI image generation scripts. The skill depends on the google-genai and pillow libraries to execute deterministic image processing tasks.

Why does the image generation fail and how does provider fallback work?

If image generation fails, provider fallback automatically attempts the task using multiple AI providers to increase success rates and ensure the image generation process completes successfully.