skills.rest
davekilleen
davekilleenCOMMUNITY
Explore all skills by this author →
GitHub

gemini-imagegen

Generate and edit images using Google's Gemini API.

461|129|Updated Jan 26, 2026
Search Tags:#editing#image generation#gemini#text-to-image#ai art#image manipulation
One-click install
npx skills add https://github.com/davekilleen/Dex --skill gemini-imagegen-davekilleen
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gemini-imagegen
Source: https://github.com/davekilleen/Dex/tree/main/.claude/plugins/compound-engineering/skills/gemini-imagegen
Command: npx skills add https://github.com/davekilleen/Dex --skill gemini-imagegen-davekilleen

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates the creation and modification of images using text prompts and existing image inputs, eliminating the need for complex graphic design software for many tasks.

Core Features & Use Cases

  • Text-to-Image Generation: Create entirely new images from descriptive text prompts.
  • Image Editing & Refinement: Modify existing images by providing instructions and the image itself.
  • Multi-Turn Refinement: Iteratively improve generated or edited images through conversational prompts.
  • Image Composition: Combine multiple images based on instructions.
  • Use Case: Generate a logo for a new startup based on a description, then refine its colors and text through a few conversational turns.

Quick Start

Use the gemini-imagegen skill to generate an image of a futuristic cityscape at sunset.

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?▼

Text-to-image generation with the Gemini API is done by providing a descriptive text prompt to the model. This Skill automates creating new images using the google-genai library and requires a GEMINI_API_KEY environment variable.

Can I edit and refine an existing image through conversational prompts?▼

Yes, image editing and multi-turn refinement are supported by providing both the existing image and modification instructions. You can iteratively improve generated or edited images through conversational prompts using the Gemini API.

Does this image generation Skill support combining multiple reference images?▼

Yes, image composition from multiple reference images is supported. You can combine multiple images based on specific instructions using the Gemini API and Pillow library for image manipulation.

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

You need the GEMINI_API_KEY environment variable configured for Google's Gemini API. The Skill also requires the google-genai and Pillow libraries installed to handle the image generation and manipulation tasks.

What's the best way to automate logo creation and text refinement?▼

Automating logo creation and text refinement is achieved by generating an initial image from a text description, then iteratively modifying its colors and text through multi-turn conversational prompts using the Gemini API.

Why use Pillow with the Gemini API for AI art generation?▼

Pillow is used with the Gemini API for image manipulation during AI art generation. It handles the processing and modification of image data returned by the model, enabling both text-to-image creation and image editing.

Related Skills

Explore More Design & Creative Skills→
gvkhoslagvkhosla
49

gemini-imagegen

Generate and edit images via the Gemini API with text prompts.

Community
Intermediate
MudassarAbrarMudassarAbrar

nano-banana-pro-openrouter

Generate or edit images with OpenRouter Gemini 3 Pro at 1K/2K/4K resolutions.

Community
Advanced
SheshiyerSheshiyer
4

nano-banana-2

Generate Gemini 3.1 flash image previews from prompts via the inference.sh CLI.

Community
Intermediate
yxc023yxc023

gemini-imagegen

Generate and edit images using the Gemini API from text prompts and references.

Community
Advanced