gemini-image-gen

Generate and edit images from text prompts using Gemini 2.5 Flash Image.

Updated Sep 16, 2025

Search Tags:#composition #gemini #image-generation #text-to-image #prompt-engineering #ai-art

Ready to run

npx skills add https://github.com/kienhaminh/speed-reader --skill gemini-image-gen-kienhaminh

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: gemini-image-gen
Source: https://github.com/kienhaminh/speed-reader/tree/main/.claude/skills/gemini-image-gen
Command: npx skills add https://github.com/kienhaminh/speed-reader --skill gemini-image-gen-kienhaminh

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Generate high-quality images from text prompts using Gemini's image model, with editing, multi-image composition, and iterative refinement.

Core Features & Use Cases

Text-to-Image: Create images from descriptive prompts.
Image Editing: Modify existing images via prompting.
Multi-Image Composition: Combine up to 3 sources into a scene.
Iterative Refinement: Refine results through dialogs with the AI.

Quick Start

Use the helper script to generate an image from a prompt and save to docs/assets/.

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 Gemini?▼

Text-to-image generation with Gemini uses the Gemini 2.5 Flash Image model to create images from descriptive prompts. Provide your text description, configure aspect ratio and safety settings, and the Skill outputs images to ./docs/assets/. You'll need a Gemini API key via google-genai.

Can I edit existing images or combine multiple images into one composition?▼

Yes, the Skill supports image editing by modifying existing images through prompts and multi-image composition that combines up to three input sources into a single scene. Both workflows output to ./docs/assets/ with configurable aspect ratios.

What do I need to get started with text-to-image generation?▼

You need API key access to Gemini through the google-genai dependency, a text prompt describing your desired image, and optional configuration for aspect ratio and safety settings. The Skill handles output management to ./docs/assets/.

How does iterative refinement work with Gemini image generation?▼

Iterative refinement enables dialog-based interaction with the AI model to progressively improve generated images. Submit a prompt, review the output, then refine through follow-up prompts until the result meets your design needs.

What are the limitations of multi-image composition with this Skill?▼

The Skill supports composition with a maximum of three input images combined into a single scene. Aspect ratios and safety settings are configurable, but composition is limited to this three-image constraint.

Can I use this for product photography and branding asset creation?▼

Yes, the Skill is designed for product photography, branding assets, and design workflows. Text-to-image, editing, and composition features support creating marketing materials and design collateral with configurable outputs.