gemini-imagegen

Automates image generation and editing using the Gemini API.

3|1|Updated Jan 15, 2026
One-click install
npx skills add https://github.com/i3ringit/antigravity-cortex --skill gemini-imagegen-i3ringit
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gemini-imagegen
Source: https://github.com/i3ringit/antigravity-cortex/tree/main/.agent/skills/gemini-imagegen
Command: npx skills add https://github.com/i3ringit/antigravity-cortex --skill gemini-imagegen-i3ringit

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

The Gemini image generation skill automates creation and editing of visuals by interfacing with the Gemini API. It enables text-to-image generation, image editing, style transfers, and multi-reference composition to produce logos, stickers, and product mockups, reducing manual design effort.

Core Features & Use Cases

  • Text-to-image generation using Gemini API with adjustable aspect ratios and resolutions.
  • Image editing by applying instructions to existing images.
  • Multi-turn refinement & composition by combining multiple reference images.
  • Use Case: Design a logo with text and a matching sticker set for a product launch.

Quick Start

Use the gemini-imagegen skill to generate a logo from the prompt 'Acme logo with bold sans-serif'.

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 using the Gemini API?

Text-to-image generation with Gemini API converts your written prompts into images at adjustable aspect ratios and resolutions. The skill provides Python scripts that handle API authentication via GEMINI_API_KEY and return generated images ready for use in logos, stickers, or mockups.

Can I edit existing images with Gemini API instructions?

Image editing with Gemini applies your instructions to existing images to modify, enhance, or transform them. The skill automates this workflow, allowing you to refine designs iteratively without manual editing tools.

What do I need to set up before using Gemini image generation?

Prerequisites include a Gemini API key (GEMINI_API_KEY), Python environment with google-genai and Pillow libraries installed. The skill's scripts handle the rest—no additional setup or configuration is required to start generating images.

How do I combine multiple reference images into a single design?

Multi-reference composition uses Gemini to synthesize multiple reference images into one cohesive output. This workflow supports logo design and product mockup creation by blending visual elements across sources in a single generation step.

Can I use Gemini image generation for logo and sticker design workflows?

Yes—the skill is purpose-built for logos, stickers, and product mockups. It handles text-to-image generation, style transfer, and multi-turn refinement, automating the full design iteration cycle for branded assets.

What are the limitations of style transfer with Gemini API?

Style transfer quality depends on reference image clarity and prompt specificity. The skill automates the process but cannot guarantee pixel-perfect results; iterative refinement and multi-turn composition improve outcomes for complex design requests.