skills.rest
jayteealao
jayteealaoCOMMUNITY
Explore all skills by this author →
GitHub

gemini-imagegen

Generate and edit images via the Gemini API with local scripts.

Updated Jan 1, 2026
Search Tags:#API#image#composition#Gemini#edit#generate#reference-images
One-click install
npx skills add https://github.com/jayteealao/blank-template --skill gemini-imagegen-jayteealao
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gemini-imagegen
Source: https://github.com/jayteealao/blank-template/tree/main/.claude/skills/gemini-imagegen
Command: npx skills add https://github.com/jayteealao/blank-template --skill gemini-imagegen-jayteealao

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates the creation and refinement of images using the Gemini API, reducing manual design time and enabling rapid visual iteration.

Core Features & Use Cases

  • Text-to-image generation from prompts using Gemini.
  • Image editing of existing images with natural language instructions.
  • Composition from multiple references by merging several images into a single output.
  • Use cases include branding mockups, social graphics, and quick concept art iterations.

Quick Start

  • Install dependencies: pip install google-genai Pillow
  • Set GEMINI_API_KEY in your environment
  • Run: python scripts/generate_image.py "A futuristic city skyline at sunset" output.png --model gemini-3-pro-image-preview --aspect 16:9 --size 2K

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 with the Gemini API using Python?▼

To generate images with the Gemini API, you need to install the google-genai and Pillow libraries, set your GEMINI_API_KEY environment variable, and run the local generation script with a text prompt to output an image file.

Can I edit an existing image using natural language instructions with Gemini?▼

Yes, you can edit existing images with natural language instructions using the Gemini API, which allows you to perform multi-turn refinements and visual iterations on branding assets or design prototypes.

How do I compose multiple reference images into a single output?▼

You can compose multiple reference images into a single output by using the provided local scripts toolkit, which leverages the Gemini API to merge several images for quick visual composition.

Do I need a specific environment setup to control image aspect ratio and size?▼

You need Python with the google-genai and Pillow dependencies installed, plus a valid GEMINI_API_KEY, to use the aspect_ratio and image_size controls for generating 2K resolution images.

What is the best way to automate design prototyping and visual iterations?▼

Automating design prototyping and visual iterations is best achieved by using the Gemini API to generate and edit images, enabling rapid multi-turn refinements from multiple references for social graphics and concept art.

Are there limitations when using the Gemini API for image generation?▼

Limitations of using the Gemini API for image generation include dependency on a valid GEMINI_API_KEY for access and requiring the Pillow library for local image handling and script execution.

Related Skills

Explore More Design & Creative Skills→
joonlabjoonlab
8

nano-banana-pro

Generate and edit images with Google Gemini models via a command-line interface.

Community
Intermediate
jhlee0409jhlee0409

prompt-strategy

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

Community
Advanced
ollieb89ollieb89

gemini-imagegen

Generate and edit images using the Gemini API.

Community
Intermediate
JimmyChen-NXPJimmyChen-NXP

gemini-imagegen

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

Community
Intermediate