skills.rest
potentialInc
potentialIncOFFICIAL
Explore all skills by this author →
WebsiteGitHub

create-image

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

Updated Aug 27, 2026
Search Tags:#ai#gemini#image-generation#prompt#image-editing#batch-generation
One-click install
npx skills add https://github.com/potentialInc/claude-content --skill create-image-potentialinc
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: create-image
Source: https://github.com/potentialInc/claude-content/tree/main/skills/creation/create-image
Command: npx skills add https://github.com/potentialInc/claude-content --skill create-image-potentialinc

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Generating and editing high-quality images typically requires skilled design time and expensive software; this Skill automates AI-driven image creation and edits via Gemini.

Core Features & Use Cases

  • Generate multiple images from prompts using Gemini AI.
  • Edit existing images via text prompts or masks, including background and style changes.
  • Create consistent visuals for product launches, logos, social graphics, and marketing assets.

Quick Start

Generate a batch of AI-generated product images by describing them in prompts and save them to your output directory.

Frequently Asked Questions about create-image

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate AI images from text prompts using Gemini?▼

To generate AI images from text prompts using Gemini, provide your descriptive text to the Skill, which processes it via the Gemini AI API and saves the resulting images to your designated output directory.

Can I edit existing images and change backgrounds with Gemini AI?▼

Yes, you can edit existing images and change backgrounds with Gemini AI by providing text prompts or masks, allowing for targeted style modifications and background changes on your original assets.

Do I need a GEMINI_API_KEY to perform batch image generation?▼

Yes, you need a GEMINI_API_KEY to perform batch image generation, as the Skill requires this key along with network access and the gemini-3-pro-image-preview model id to save results.

What is the best way to create consistent marketing visuals with AI?▼

The best way to create consistent marketing visuals with AI is using batch generation from text prompts, which produces uniform product launch graphics, logos, and social assets saved to a single directory.

Why does Gemini image generation require network access?▼

Gemini image generation requires network access because the Skill must communicate with the Gemini AI API to send your text prompts and receive the generated or edited image results for saving.

Related Skills

Explore More Design & Creative Skills→
EveryIncEveryInc
24.1k

gemini-imagegen

Generate and edit images via the Gemini API with multi-turn refinement.

Official
Advanced
jhlee0409jhlee0409

prompt-strategy

Develop and optimize AI prompt strategies for code generation across multiple models.

Community
Advanced
jesuscottagejesuscottage

thumbnail-generator

Generate and edit YouTube thumbnails by swapping faces and applying style modifications.

Community
Intermediate
antoniolgantoniolg
97

nano-banana-pro

Generate and edit images via the Gemini 3 Pro Image API.

Community
Advanced