gemini-imagegen

Generate and refine images via the Gemini API with configurable parameters.

2|1|Updated Apr 17, 2026
One-click install
npx skills add https://github.com/wangrenzhu-ola/GaleHarnessCodingCLI --skill gemini-imagegen-wangrenzhu-ola
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gemini-imagegen
Source: https://github.com/wangrenzhu-ola/GaleHarnessCodingCLI/tree/main/plugins/galeharness-cli/skills/gemini-imagegen
Command: npx skills add https://github.com/wangrenzhu-ola/GaleHarnessCodingCLI --skill gemini-imagegen-wangrenzhu-ola

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Gemini Image Gen provides a streamlined approach to creating and editing visuals by leveraging the Gemini API to translate prompts and reference imagery into polished images, saving time for designers and developers.

Core Features & Use Cases

  • Text-to-image generation, image editing, and multi-turn refinement using iterative prompts.
  • Composition from multiple reference images (up to 14) to blend styles and elements.
  • Lightweight integration with a Python toolchain for batch image work and automation in creative pipelines.

Quick Start

Ask Gemini to generate or refine an image from a text prompt, optionally using reference images for composition.

Frequently Asked Questions about gemini-imagegen

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

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

To generate images from text prompts using the Gemini API, you provide a text description to the Google GenAI Python client, which then creates polished visuals. You can optionally specify image_config parameters like aspect_ratio and image_size.

Can I blend multiple reference images to create a single composition?

Yes, you can blend multiple reference images to create a single composition. The tool supports composing from up to 14 reference images, allowing you to blend styles and elements for automated image creation in design workflows.

Do I need a Gemini API key to edit images with the Google GenAI client?

Yes, you need a Gemini API key to edit images with the Google GenAI client. The API key is required to authenticate requests for text-to-image generation, multi-turn refinements, and image editing tasks.

What is multi-turn refinement for AI image editing?

Multi-turn refinement for AI image editing is the process of iteratively updating visuals using sequential prompts. It allows you to progressively adjust and refine generated images based on reference imagery and new text instructions.

Does this image generation tool work with Python and Pillow for batch automation?

Yes, this image generation tool works with Python and Pillow for batch automation. It offers lightweight integration with a Python toolchain to support batch image work and automate creative pipelines.

What are the limitations when using Gemini for AI art generation?

Limitations when using Gemini for AI art generation include dependency on external API keys and reliance on the Google GenAI Python client. Complex multi-turn refinements using 14 reference images may also require careful prompt engineering to achieve desired outputs.