What is required to use the Gemini Image skill?

You must have a fal.ai API key configured as the FAL_KEY environment variable in your shell profile (e.g., ~/.zshrc or ~/.bashrc).

How many images can I generate at once?

You can generate between 1 and 4 images per prompt by adjusting the num_images parameter.

Which AI model is used for the generation?

The skill uses Google's Gemini 3 Pro image generation model, accessed through the fal.ai API infrastructure.

Can I generate images in different aspect ratios?

Yes, it supports a wide range of ratios including 1:1, 16:9, 9:16, 3:2, 4:3, and several others to fit various design needs.

What image resolutions does this skill support?

The skill supports three resolution presets: 1K, 2K, and 4K, allowing for everything from quick previews to high-fidelity production assets.

Gemini Image Generator

Name: Gemini Image Generator
Author: bluewaves-creations

bybluewaves-creations

データサイエンスとML

Generates high-quality images from text prompts using Google Gemini 3 Pro via the fal.ai API.

概要

The gemini-image skill empowers Claude to create professional-grade visual assets directly within your development workflow. By leveraging Google's Gemini 3 Pro model through fal.ai, it allows for the generation of high-fidelity images with granular control over resolution (up to 4K), aspect ratios, and output formats. This skill is particularly useful for developers needing rapid UI prototyping, automated content creation, or high-quality placeholder graphics without leaving their terminal or coding environment.

主な機能

Batch generation capabilities for up to 4 images per request
State-of-the-art image generation using Google Gemini 3 Pro
Optional web search integration to inform image generation with current data
Support for professional resolutions including 1K, 2K, and 4K
Extensive aspect ratio options from ultra-wide 21:9 to vertical 9:16
0 GitHub stars

ユースケース

Generating UI/UX mockups and visual assets during frontend development
Automating the creation of blog and social media imagery from text descriptions
Creating high-resolution backgrounds and placeholder graphics for web applications

概要

主な機能

Batch generation capabilities for up to 4 images per request
State-of-the-art image generation using Google Gemini 3 Pro
Optional web search integration to inform image generation with current data
Support for professional resolutions including 1K, 2K, and 4K
Extensive aspect ratio options from ultra-wide 21:9 to vertical 9:16
0 GitHub stars

ユースケース

Generating UI/UX mockups and visual assets during frontend development
Automating the creation of blog and social media imagery from text descriptions
Creating high-resolution backgrounds and placeholder graphics for web applications