skills.rest
ttmouse
ttmouseCOMMUNITY
Explore all skills by this author →
𝕏@ttmouseGitHub

gemini-gen

Generate images from text prompts using Google's Gemini models.

35|10|Updated Dec 29, 2025
Search Tags:#image generation#visuals#gemini#creative#text-to-image#ai art
One-click install
npx skills add https://github.com/ttmouse/skills --skill gemini-gen
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gemini-gen
Source: https://github.com/ttmouse/skills/tree/main/gemini-gen
Command: npx skills add https://github.com/ttmouse/skills --skill gemini-gen

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This skill allows users to generate images based on text prompts using Google's Gemini models, providing a powerful tool for visual content creation.

Core Features & Use Cases

  • Image Generation: Creates images from descriptive text prompts.
  • Model Selection: Supports various Gemini image models with different aspect ratios and resolutions.
  • Quota Management: Prioritizes standard resolution models to conserve quota, only using high-resolution models when explicitly requested.
  • Automatic Opening: On macOS, generated images are automatically opened in the default viewer.
  • Use Case: Generate a photorealistic image of a "cyberpunk cat wearing a tiny hat" for a social media post.

Quick Start

Use the gemini-gen skill to generate an image of a serene mountain landscape at sunset.

Frequently Asked Questions about gemini-gen

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate images using Gemini from text prompts?▼

To generate images using Gemini, you provide descriptive text prompts that the model translates into visual content. This skill defaults to the 'gemini-3-pro-image' model for 1:1 aspect ratio to optimize quota usage.

Can I configure aspect ratios and resolutions for AI art generation?▼

Yes, AI art generation supports configurable aspect ratios and resolutions. It prioritizes standard resolution models to conserve quota, only utilizing high-resolution models when you explicitly request them.

What do I need for secure API access to generate text-to-image visuals?▼

Secure API access for text-to-image visuals requires native token authentication. This is supported via Alma's antigravity-auth plugin, ensuring your credentials are safely managed during the image generation process.

Does image generation work with macOS to automatically open files?▼

Image generation works seamlessly with macOS. Upon successfully generating an image from your text prompt, the system automatically opens the output file in your default image viewer for immediate review.

Why does the model default to standard resolution for AI art?▼

The model defaults to standard resolution for AI art to optimize quota usage. High-resolution models are only invoked when explicitly requested, conserving your API limits during routine image generation tasks.

Related Skills

Explore More Design & Creative Skills→
SpillwaveSolutionsSpillwaveSolutions
1

mastering-github-cli

Centralize GitHub CLI operations for repository search, CI/CD monitoring, and workflow automation.

Official
Intermediate
Dante-danDante-dan

dan-publish-all

Publish markdown articles across multiple content platforms with generated visual assets.

Community
Advanced
ArnavPuriArnavPuri
3

image-generation

Generate and edit images using the Gemini 3.1 Flash Image Preview model.

Community
Intermediate
zendev-shzendev-sh
177

goai-sdk

Integrate AI models and services into Go applications via a unified SDK.

Official
Advanced