ce-gemini-imagegen

Generate and edit images via the Gemini API from text prompts or reference imagery.

10|Updated Dec 13, 2016

Search Tags:#python #gemini #image-generation #image-editing #reference-images #ai-art

Ready to run

npx skills add https://github.com/vitallium/dotfiles --skill ce-gemini-imagegen-vitallium

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ce-gemini-imagegen
Source: https://github.com/vitallium/dotfiles/tree/main/dot_agents/skills/ce-gemini-imagegen
Command: npx skills add https://github.com/vitallium/dotfiles --skill ce-gemini-imagegen-vitallium

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Generating and editing high-quality images typically requires specialized tools and workflows; this Skill provides a streamlined way to create, edit, and refine visuals using the Gemini API.

Core Features & Use Cases

Text-to-image generation and image editing with iterative refinement.
Multi-turn refinement and composition from multiple reference images.
Adjustable aspect ratios and resolutions; Pro model recommended for composition tasks.

Quick Start

Provide a text prompt to Gemini to generate an image and save the resulting output.

Frequently Asked Questions about ce-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 from a text prompt?▼

To generate images with the Gemini API, you provide a natural language text prompt to the model, which processes the request and outputs the resulting image. The Skill uses the gemini-3-pro-image-preview model to handle text-to-image generation and saves the output.

Can I edit an existing image using Gemini and reference images?▼

Yes, you can edit existing images and compose visuals from multiple reference images using Gemini. The Skill supports multi-turn refinement, allowing you to iteratively adjust and update images based on new text prompts and reference imagery inputs.

Do I need a GEMINI_API_KEY to use Gemini for image generation?▼

Yes, a GEMINI_API_KEY is required to authenticate and use the Gemini image generation Skill. You must configure this environment variable in your Python client to access the google-genai API for generating and editing images.

How do I customize the aspect ratio and image size for Gemini API outputs?▼

You can customize the aspect ratio and image size for Gemini API outputs by specifying these parameters in your Python client request. The Skill processes these configurations alongside your text prompt to generate images with your desired dimensions.

What Python libraries are required for Gemini image editing and generation?▼

The required Python libraries for Gemini image generation and editing are Pillow and google-genai. These dependencies handle image processing tasks and API interactions, enabling text-to-image generation and multi-turn image refinement.

Which Gemini model is recommended for image composition from multiple references?▼

The default gemini-3-pro-image-preview model is recommended for image composition tasks using multiple references. This Pro model provides the capability needed to effectively merge and refine multiple reference images into a single output.