gemini-imagegen

Generate and edit images programmatically via the Gemini API.

Updated Mar 9, 2026
One-click install
npx skills add https://github.com/RafayelGardishyan/rafayels-marketplace --skill gemini-imagegen-rafayelgardishyan
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gemini-imagegen
Source: https://github.com/RafayelGardishyan/rafayels-marketplace/tree/main/plugins/rafayels-engineering/.opencode/skills/gemini-imagegen
Command: npx skills add https://github.com/RafayelGardishyan/rafayels-marketplace --skill gemini-imagegen-rafayelgardishyan

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill enables programmatic generation and editing of images via the Gemini API. It supports text-to-image generation, editing existing images, applying style transfers, logo creation with text, and building product mockups or stickers in automated workflows.

Core Features & Use Cases

  • Text-to-image generation from prompts with configurable model, resolution, and aspect ratio.
  • Image editing and multi-turn refinement to iteratively improve visuals.
  • Composition from multiple reference images to create combined scenes, mood boards, or marketing visuals for design workflows.

Quick Start

Generate an image from the prompt "A futuristic cityscape at sunset" using the gemini-3-pro-image-preview model.

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?

You can generate images from text prompts using the Gemini API by configuring the prompt, model, resolution, and aspect ratio. This skill automates text-to-image generation to produce visuals directly from your descriptive inputs.

Can I edit existing images and apply style transfers with Gemini?

Yes, you can edit existing images and apply style transfers with Gemini. The skill supports image editing and multi-turn refinement, allowing you to iteratively improve visuals and modify images within automated workflows.

How do I compose multiple reference images into a single scene?

You can compose multiple reference images into a single scene by using the composition feature. This allows you to combine visuals to create mood boards, marketing assets, or product mockups for design workflows.

Do I need the google-genai and Pillow libraries to automate image generation?

Yes, you need the google-genai and Pillow libraries to automate image generation. These dependencies provide the core API connectivity and image processing capabilities required to handle text-to-image outputs.

What is the best way to create product mockups and logos with text via AI?

The best way to create product mockups and logos with text is through prompt engineering and configurable image generation. This skill supports logo creation with text and building mockups by leveraging the Gemini API.