gemini-image

Generate images from text prompts and reference images via API.

333|83|Updated Jan 9, 2026
One-click install
npx skills add https://github.com/SpaceZephyr/myskill --skill gemini-image-spacezephyr
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gemini-image
Source: https://github.com/SpaceZephyr/myskill/tree/main/gemini-image
Command: npx skills add https://github.com/SpaceZephyr/myskill --skill gemini-image-spacezephyr

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the friction of turning ideas, photos, and design directions into generated images, making it easier to create visuals without manual illustration work.

Core Features & Use Cases

  • Text-to-Image Creation: Convert a written concept into a fresh AI-generated picture.
  • Image-to-Image Editing: Use an existing image as a reference to create a similar or transformed result.
  • Multi-Image Reference Workflows: Blend two or more reference images into one prompt-driven generation.
  • Use Case: A creator can ask for a product mockup, social post illustration, or style-matched concept image and receive a generated image link.

Quick Start

Use the gemini-image skill to generate a cute orange cat from a text prompt.

Frequently Asked Questions about gemini-image

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

FAQPage Schema
How do I generate images from text prompts?

To generate images from text prompts, use this Skill to process a written concept via API-based prompt construction, returning a usable image link for your visual design needs.

Can I use an existing photo as a reference for image generation?

Yes, you can use an existing photo as a reference for image generation. This Skill supports image-to-image editing and multi-image reference workflows to create similar or transformed visual concepts.

What is the best way to blend multiple reference images into one AI art generation?

The best way to blend multiple reference images is using the multi-image reference workflow, which combines two or more uploaded photos into one prompt-driven generation for creative illustration.

Does this text-to-image tool support API-based prompt construction?

Yes, this text-to-image tool supports API-based prompt construction and image upload support, allowing you to automate visual concept generation and extract the response URL to get a usable image link.

Why use image-to-image editing instead of starting from scratch?

Use image-to-image editing when you need to transform an existing photo into a style-matched concept image, removing the friction of manual illustration work while preserving the original visual direction.