gemini-imagegen

Generate and edit images using the Gemini API with text prompts.

1|Updated Mar 11, 2026
One-click install
npx skills add https://github.com/JimmyChen-NXP/zephyr-team-activity-dashboard --skill gemini-imagegen-jimmychen-nxp
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gemini-imagegen
Source: https://github.com/JimmyChen-NXP/zephyr-team-activity-dashboard/tree/main/.github/skills/gemini-imagegen
Command: npx skills add https://github.com/JimmyChen-NXP/zephyr-team-activity-dashboard --skill gemini-imagegen-jimmychen-nxp

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill empowers users to generate novel images from text prompts and to edit existing images with natural language instructions, streamlining creative workflows and content creation.

Core Features & Use Cases

  • Text-to-Image Generation: Create unique images based on detailed text descriptions.
  • Image Editing: Modify existing images by describing desired changes.
  • Advanced Features: Supports multi-turn refinement, composition of multiple images, and Google Search grounding for real-world data integration.
  • Use Case: Generate a series of product mockups for a new shoe design, then use the editing feature to change the color of the laces on one of the mockups.

Quick Start

Use the gemini-imagegen skill to generate an image of a futuristic cityscape at sunset.

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 descriptions using Gemini AI?

This Skill performs text-to-image generation by sending natural language prompts to the Gemini API, creating unique visual assets. It requires a valid GEMINI_API_KEY to authenticate requests and return the generated images.

Can I edit existing images and apply multi-turn refinement with Gemini?

Yes, you can edit existing images and apply multi-turn refinement with Gemini by providing natural language instructions. The Skill modifies images iteratively, allowing you to describe desired changes like altering object colors or adjusting composition across multiple interactions.

Do I need a GEMINI_API_KEY and Pillow to use this image generation Skill?

Yes, you need a GEMINI_API_KEY and the Pillow library to use this image generation Skill. The API key authenticates your access to the Gemini API, while Pillow handles image manipulation tasks like processing and composing the generated or edited visual assets.

What is the best way to compose multiple reference images together?

The best way to compose multiple reference images is using the Gemini API's composition feature. This Skill combines elements from several source images into a single output, utilizing Python and Pillow for seamless image manipulation and multi-reference integration.

Does Gemini image generation support Google Search grounding for real-world data?

Yes, Gemini image generation supports Google Search grounding for real-world data integration. This feature allows the Skill to fetch and utilize current real-world information during the text-to-image or image editing process to ensure accurate and relevant visual content.

What are the limitations of using the Gemini API for creative content generation?

Limitations of using the Gemini API for creative content generation include dependency on your GEMINI_API_KEY access level and the specific capabilities of the google-genai library. Complex image manipulation tasks may require multiple refinement iterations to achieve the desired visual output.