skills.rest
shushuzn
shushuznCOMMUNITY
Explore all skills by this author →
GitHub

generate-image

Generate or edit images from natural-language prompts via OpenRouter models.

4|Updated Mar 2, 2026
Search Tags:#image generation#image editing#gemini#openrouter#creative assets#flux#prompt to image
One-click install
npx skills add https://github.com/shushuzn/Rairos --skill generate-image-shushuzn
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: generate-image
Source: https://github.com/shushuzn/Rairos/tree/main/skills/generate-image
Command: npx skills add https://github.com/shushuzn/Rairos --skill generate-image-shushuzn

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Generate or modify images from text prompts so you can quickly produce usable artwork, photos, or visual assets without manual design work.

Core Features & Use Cases

  • General-purpose image generation + editing: Create photos, illustrations, concept art, and marketing/slide visuals, with support for both generation and image edits.
  • Model flexibility via OpenRouter: Use Gemini 3.1 Flash Image Preview or FLUX.2 Pro for high-quality results, and FLUX.2 Flex for faster generation when editing is not needed.
  • Practical workflow support: Save outputs automatically to a PNG file and edit an existing image by providing an input image and an instruction prompt.

Quick Start

Run the script with your prompt to generate an image and save it as generated_image.png in the current directory.

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 automatically?▼

To generate images from text prompts, the Skill processes your natural-language input to produce visual content and automatically saves the output as a PNG file in your current directory.

Can I edit an existing image using a prompt instead of starting from scratch?▼

Yes, you can edit an existing image by providing an input image alongside an instruction prompt, applying modifications and photo-style transformations without manual design work.

What image generation models can I use through OpenRouter?▼

You can use OpenRouter-supported image models including Gemini 3.1 Flash Image Preview and FLUX.2 Pro for high-quality results, or FLUX.2 Flex for faster generation when image editing is not required.

Do I need an API key to generate concept art or presentation assets?▼

Yes, you need an OPENROUTER_API_KEY to generate concept art or presentation assets, which must be retrieved from a .env environment file or passed explicitly as a parameter.

What is the best way to create marketing visuals without manual design work?▼

Using prompt-driven image generation is the best way to quickly create marketing visuals without manual design, producing usable photos, illustrations, and slide assets from natural-language descriptions.

Are there limitations when using FLUX.2 Flex for image generation?▼

FLUX.2 Flex is limited to faster image generation and does not support the image editing mode, unlike Gemini 3.1 Flash Image Preview or FLUX.2 Pro which handle both generation and edits.

Related Skills

Explore More Design & Creative Skills→
robinbarvaagrobinbarvaag

generate-image

Generate and edit images from prompts via the OpenRouter API.

Community
Intermediate
techwolf-aitechwolf-ai
95

techwolf-logo

Copy official TechWolf SVG and PNG logo files for consistent branding.

Official
Basic
CyangZhouCyangZhou
2

Image_Generation_Expert

Generate images from textual prompts with configurable style and size.

Community
Basic
RDCrystalLabRDCrystalLab

OpenRouter Image Gen

Generate AI images via OpenRouter APIs with configurable models and parameters.

Official
Intermediate