skills.rest
compojoom
compojoomCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

gemini-imagegen

Generates and edits images via the Gemini API using the google-genai library and Pillow.

Updated Aug 23, 2026
Search Tags:#image generation#composition#Python#image editing#Gemini API#prompting#multi-turn chat
One-click install
npx skills add https://github.com/compojoom/safe-engineering-plugin --skill gemini-imagegen-compojoom
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gemini-imagegen
Source: https://github.com/compojoom/safe-engineering-plugin/tree/main/plugins/safe-engineering/skills/gemini-imagegen
Command: npx skills add https://github.com/compojoom/safe-engineering-plugin --skill gemini-imagegen-compojoom

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates the generation and editing of images using the Gemini API, enabling rapid creation and refinement workflows for design, marketing, and concept art.

Core Features & Use Cases

  • Text-to-image generation: Create visuals from prompts, suitable for logos, mockups, and illustrations.
  • Image editing and refinement: Modify existing images and iterate on visual ideas with natural language instructions.
  • Composition from references: Merge or compose multiple reference images into a single output.
  • Use Case: Quickly generate a product concept or marketing visual by describing the look and feel, then refine in a few iterations.

Quick Start

Use the provided Python scripts (scripts/generate_image.py, scripts/edit_image.py, scripts/compose_images.py) to start generating and editing images with Gemini. Ensure GEMINI_API_KEY is set and install dependencies from requirements.txt.

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 using the Gemini API in Python?▼

Image generation with the Gemini API uses provided Python scripts to automate text-to-image creation. You must set your GEMINI_API_KEY and install dependencies like google-genai and Pillow to start producing visuals from prompts.

Can I edit and refine existing images with natural language instructions?▼

Yes, image editing with natural language instructions is supported through the Gemini API. The provided Python scripts let you modify existing images and iterate on visual ideas, automating the refinement workflow for design and concept art.

Do I need a Gemini API key to compose multiple reference images?▼

Yes, a GEMINI_API_KEY is required to compose multiple reference images. The Skill uses the google-genai library and Pillow for image handling to merge or compose reference images into a single output.

What is the best way to automate product concept art generation?▼

Automating product concept art generation is done using the Gemini API with Python scripts. You describe the look and feel, then refine the marketing visual in a few iterations using the included generate and edit scripts.

Does this image generation workflow require specific Python libraries?▼

Yes, the image generation workflow requires the google-genai and Pillow Python libraries. You must install these dependencies from the requirements.txt file before running the provided scripts to handle image processing and API calls.

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
swarmclawaiswarmclawai
636

nano-banana-pro

Generate and edit images via Gemini 3 Pro Image with a Python script.

Official
Intermediate
michaelvolzmichaelvolz

gemini-imagegen

Generate and edit images from text prompts via Gemini API endpoints.

Community
Intermediate
AskTinNguyenAskTinNguyen

gemini-imagegen

Generate, edit, and compose images via the Gemini API using Python scripts.

Community
Advanced