gemini-imagegen

Generate and edit images using the Gemini API.

Updated Jan 21, 2026

Search Tags:#api #image #composition #gemini #prompts #edit #generate

Ready to run

npx skills add https://github.com/ollieb89/orchestrator --skill gemini-imagegen-ollieb89

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: gemini-imagegen
Source: https://github.com/ollieb89/orchestrator/tree/main/.cursor/skills/gemini-imagegen
Command: npx skills add https://github.com/ollieb89/orchestrator --skill gemini-imagegen-ollieb89

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Gemini-based image generation and editing is streamlined into a reusable skill that handles prompts, edits, and multi-image compositions.

Core Features & Use Cases

Generate images from text prompts using Gemini API (Pro) for high-quality visuals.
Edit existing images with natural language instructions and iterative refinements.
Compose multiple reference images into a single output, enabling complex compositions.
Interactive multi-turn refinement and chat to converge on the desired design.

Quick Start

Prompt it to generate a logo for Acme Corp and save the result as logo.png.

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 edit existing images using Gemini by providing natural language instructions for iterative refinements. The skill handles image editing by processing your commands through the Gemini API, allowing multi-turn refinement to converge on the desired visual design.

Can I compose multiple reference images into a single output with Gemini?▼

Yes, you can compose multiple reference images into a single output with Gemini. The skill supports image composition by combining multiple visual references through the Gemini API to create complex, unified designs based on your inputs.

What do I need to set up before using Gemini for image generation and editing?▼

Before using Gemini for image generation and editing, you need a valid GEMINI_API_KEY and the google-genai client installed. You also need the Pillow library for image I/O to handle saving and loading visual files during your workflow.

Does Gemini image generation support interactive multi-turn chat for design workflows?▼

Gemini image generation supports interactive multi-turn chat for design workflows. This allows you to iteratively refine prompts and edit images through conversational commands, converging on the desired design output through successive chat interactions.

What are the limitations of using natural language prompts for image editing with Gemini?▼

When using natural language prompts for image editing with Gemini, limitations depend on the Gemini API Pro model's interpretation accuracy. Complex compositions may require multiple iterative refinement cycles to achieve precise visual results through the text-to-image workflow.