oma-image

Generate images from text prompts using multi-vendor AI models.

1|Updated Mar 21, 2026
One-click install
npx skills add https://github.com/first-fluke/mapple --skill oma-image
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: oma-image
Source: https://github.com/first-fluke/mapple/tree/main/.agents/skills/oma-image
Command: npx skills add https://github.com/first-fluke/mapple --skill oma-image

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill enables users to generate images and visual assets efficiently through authenticated multi-vendor routing, simplifying access to diverse AI image models and managing cost, quality, and style customization.

Core Features & Use Cases

  • Multi-vendor Image Generation: Routes prompts to Codex, Pollinations, and Gemini, allowing comparison and flexible use of various AI image models.
  • Authenticated Workflow: Handles vendor login states securely to ensure access to protected APIs and CLI tools.
  • Use Case: Create concept art or product images for marketing, with options to compare different styles or models in a single command.

Quick Start

Use the oma-image skill to generate a landscape scene based on your prompt with default settings.

Frequently Asked Questions about oma-image

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

FAQPage Schema
How do I generate AI images from text prompts using multiple models?

You can generate AI images from text prompts by routing requests to multi-vendor models like Codex, Pollinations, and Gemini. This Skill handles authenticated workflows and allows optional style, size, and vendor selection for visual content creation.

What is multi-vendor prompt routing for AI art generation?

Multi-vendor prompt routing directs text prompts to AI image models like Codex, Pollinations, and Gemini. This mechanism allows you to compare outputs, manage costs, and flexibly use various models within a single command.

Can I use a reference image to guide AI image generation?

Yes, you can use reference images to guide AI image generation. The Skill supports reference images alongside text prompts to steer visual output and provides manifests for reproducibility across selected AI models.

How do I compare different AI image models for the same prompt?

You compare different AI image models by using multi-vendor routing to send a single prompt to Codex, Pollinations, and Gemini. This allows you to evaluate quality and style differences side-by-side for visual content comparison tasks.

Do I need to manage API logins for each AI image generation vendor?

No, you do not need to manually manage API logins for each vendor. The Skill features an authenticated workflow that securely handles vendor login states, ensuring protected access to AI image generation APIs and CLI tools.

Are generated AI images reproducible for later design review?

Yes, generated AI images are reproducible for later design review. The Skill provides manifests for reproducibility, ensuring you can track the specific prompts, styles, sizes, and vendor models used to create visual assets.