generate-image

Generate and edit images from text prompts and reference images via OpenRouter.

74|5|Updated Dec 10, 2025
One-click install
npx skills add https://github.com/dralkh/seerai --skill generate-image-dralkh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: generate-image
Source: https://github.com/dralkh/seerai/tree/main/skills/generate-image
Command: npx skills add https://github.com/dralkh/seerai --skill generate-image-dralkh

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, and includes scripts (resource) components.

What problem does it solve?

It removes the friction of turning a written idea or an existing picture into a polished image, so you can create visuals without manual design work or complex tooling.

Core Features & Use Cases

  • Text-to-Image Generation: Create photorealistic scenes, illustrations, concept art, and visual assets from a prompt.
  • Image Editing: Modify an existing image by describing the change you want, such as adjusting colors, adding objects, or refining composition.
  • Flexible Creative Workflows: Useful for presentation visuals, marketing graphics, document illustrations, and quick concept exploration.

Quick Start

Ask the skill to generate or edit an image from your prompt, and provide an input image if you want to modify an existing file.

Frequently Asked Questions about generate-image

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

FAQPage Schema
How do I generate images from text prompts?

Image generation from text prompts creates photorealistic scenes and illustrations by processing descriptive input. This skill uses OpenRouter image models to transform written ideas into visual assets for presentations and marketing.

Can I edit an existing image by describing changes?

Editing an existing image by describing changes allows you to modify colors, add objects, or refine composition. This skill processes reference images using base64 handling to apply requested modifications to your input files.

Do I need an OpenRouter API key to generate images?

An OpenRouter API key is required to generate images using this skill. The script validates your API key during execution with a .env fallback mechanism to ensure secure authentication before processing requests.

What image models work with text-to-image generation?

Text-to-image generation works with OpenRouter image models, including Flux. These models process your text prompts to create visual assets ranging from concept art to photorealistic scenes for creative workflows.

How do I save generated images to a file?

Saving generated images to a file is handled automatically by the skill's output file saving logic. After processing your text prompt or reference image, the script writes the resulting image data to your local file system.

What is the best way to create concept art for presentations?

Creating concept art for presentations is best done by providing descriptive text prompts to an image generation tool. This skill quickly produces visual assets from prompts, removing manual design work for documents and general creative use.