skills.rest
The-Rabak
The-RabakCOMMUNITY
Explore all skills by this author →
GitHub

gemini-imagegen

Generate and edit images with Gemini AI from text prompts and reference inputs.

Updated Mar 3, 2026
Search Tags:#gemini#image-generation#visual-design#image-editing#reference-images#ai-art#multiturn
One-click install
npx skills add https://github.com/The-Rabak/naysmith --skill gemini-imagegen-the-rabak
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gemini-imagegen
Source: https://github.com/The-Rabak/naysmith/tree/main/.github/skills/gemini-imagegen
Command: npx skills add https://github.com/The-Rabak/naysmith --skill gemini-imagegen-the-rabak

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Generate and edit images using the Gemini AI API based on text prompts and reference inputs, enabling rapid visual exploration and production-ready results.

Core Features & Use Cases

  • Text-to-image generation from prompts.
  • Image editing and style transfer by instructions or iterative refinement.
  • Multi-turn composition by combining multiple reference images to produce logos, stickers, or product mockups.

Quick Start

Set GEMINI_API_KEY and run the generation or editing scripts to produce an image from a prompt.

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 Gemini AI?▼

To generate images from text prompts using Gemini AI, you provide your text input and an optional image_config to the generation scripts. The Skill leverages Gemini models like gemini-2.5-flash-image to produce images directly from your descriptions.

Can I use reference images for multi-turn composition and product mockups?▼

Yes, you can use reference images for multi-turn composition to create product mockups, logos, or stickers. The Skill accepts reference inputs to iteratively refine and combine visuals based on your instructions.

Do I need a GEMINI_API_KEY to run the image generation scripts?▼

Yes, you must set the GEMINI_API_KEY environment variable to authenticate API access. This key is required for the scripts to communicate with the Gemini AI models and generate or edit images.

What image configuration parameters can I control during generation?▼

You can control the output dimensions by passing image_config parameters such as aspect_ratio and image_size. These options allow you to tailor the generated images to specific layout requirements.

Does this Skill support style transfer and iterative image editing?▼

Yes, this Skill supports image editing and style transfer through instructional prompts and iterative refinement. You can modify existing images or apply new styles by providing text instructions to the Gemini models.

Which Gemini models are used for the image generation process?▼

The image generation process uses the Gemini models gemini-2.5-flash-image and gemini-3-pro-image-preview. These models handle the text-to-image generation and image editing tasks within the scripts.

Related Skills

Explore More Design & Creative Skills→
boxpboxp

generate-image

Generate and edit images via Gemini 2.5 Flash Image from text prompts.

Community
Basic
Mo7amed-MahmoudMo7amed-Mahmoud

photo-editor

Automate image editing workflows with resizing, cropping, filtering, and optimization.

Community
Intermediate
me2Docme2Doc
6

nano-banana-pro

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

Community
Intermediate
EveryIncEveryInc
24.1k

gemini-imagegen

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

Official
Advanced