gemini-image-gen

Generate PNG images from text prompts via the Gemini 2.5 Flash Image API.

Updated Apr 11, 2026
One-click install
npx skills add https://github.com/annquin/revit-bim-workspace --skill gemini-image-gen-annquin
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gemini-image-gen
Source: https://github.com/annquin/revit-bim-workspace/tree/main/skills/gemini-image-gen
Command: npx skills add https://github.com/annquin/revit-bim-workspace --skill gemini-image-gen-annquin

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @google/genai, and includes scripts (resource) components.

What problem does it solve?

Generate images from text prompts using the Gemini 2.5 Flash Image API, producing base64 PNG outputs saved to disk to streamline visual exploration and creative prototyping.

Core Features & Use Cases

  • Generate single or batch images from prompts with configurable model and aspect ratio.
  • Outputs include PNG files, a prompts.json mapping, and a browsable HTML gallery for quick review.
  • Use cases include concept art, marketing visuals, and design exploration workflows.

Quick Start

Provide a prompt and run the Gemini image generator to create an image, then review the resulting gallery.

Frequently Asked Questions about gemini-image-gen

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 in Node.js?

To generate images from text prompts in Node.js, this Skill uses the Gemini 2.5 Flash Image API to create base64 PNG outputs. It processes your prompts and saves the resulting image files directly to disk.

What do I need to set up before generating Gemini images with Node.js?

Before generating Gemini images, you need a Node.js environment with the @google/genai package installed. You must also configure a valid GEMINI_API_KEY in your environment to authenticate API access.

Can I batch generate marketing visuals and save them as PNG files?

Yes, you can batch generate marketing visuals and concept art from prompts. The Skill saves all generated images as PNG files and automatically creates a prompts.json mapping for easy tracking.

Does this image generation workflow include a way to review created images?

This image generation workflow includes a browsable HTML gallery to review created images. Alongside the PNG outputs, it automatically generates an HTML file for quick visual exploration of your designs.

What is the best way to organize AI art generated from multiple prompts?

The best way to organize AI art from multiple prompts is using the included prompts.json mapping. This file tracks your text inputs alongside the corresponding PNG outputs and HTML gallery for streamlined review.

Are there limitations when using the Gemini 2.5 Flash Image API for design exploration?

A limitation of using the Gemini 2.5 Flash Image API for design exploration is that outputs are base64 PNG files saved to disk. You must configure the model and aspect ratio within the Node.js environment before generation.