skills.rest
gabrielvuksani
gabrielvuksaniCOMMUNITY
Explore all skills by this author →
GitHub

generate-image

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

Updated Aug 23, 2026
Search Tags:#image generation#multimodal#image editing#visual assets#openrouter#artwork#prompt-to-image
One-click install
npx skills add https://github.com/gabrielvuksani/wotann --skill generate-image-gabrielvuksani
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: generate-image
Source: https://github.com/gabrielvuksani/wotann/tree/main/skills/scientific/generate-image
Command: npx skills add https://github.com/gabrielvuksani/wotann --skill generate-image-gabrielvuksani

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

It solves the problem of creating or modifying images on demand without relying on manual design workflows, so you can quickly produce visuals for your projects.

Core Features & Use Cases

  • Image generation and editing: Create new images or edit existing ones using OpenRouter vision-capable image generation models.
  • Model flexibility: Use recommended defaults for quality or switch models based on cost and edit capability.
  • Scientific/creative visual workflows: Turn prompts into photoreal art, illustrations, concept visuals, and presentation/poster graphics, while steering diagrammatic content to schematics when appropriate.

Quick Start

Run the script to generate a new image from a description prompt by executing the command: python scripts/generate_image.py "A beautiful sunset over mountains".

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 natural-language prompts using OpenRouter?▼

To generate images from natural-language prompts using OpenRouter, run the provided Python script with your text description. This calls OpenRouter image generation models to create photos, illustrations, or concept art from your prompt.

Can I edit an existing image file by providing a text prompt?▼

Yes, you can edit an existing image file by providing an input file alongside a text prompt. The Skill calls the OpenRouter chat completions endpoint with image and text modalities to apply your modifications.

Do I need an OpenRouter API key to run prompt-to-image generation?▼

Yes, prompt-to-image generation requires an OPENROUTER_API_KEY. You must configure this key in your .env file or environment variables to authenticate OpenRouter chat completions endpoint requests.

What types of visual assets can I create with multimodal image generation?▼

Multimodal image generation supports creating general-purpose photos, illustrations, artwork, concept visuals, and presentation graphics. It steers diagrammatic content toward schematics to suit various scientific and creative workflows.

Can I switch OpenRouter models for image editing based on cost and capabilities?▼

Yes, you can switch OpenRouter models for image editing based on cost and capabilities. The Skill provides recommended defaults for quality but allows you to select vision-capable models that support your specific editing requirements.

Related Skills

Explore More Design & Creative Skills→
agoodwayagoodway
1

bootstrap-fly-env-sync

Generate batched fly secrets set commands from local .env files.

Official
Intermediate
archibatearchibate
6

image-generation

Generate images from text prompts via Z.ai's glm-image endpoint.

Community
Intermediate
Sma1lboySma1lboy
94

image-gen

Generate custom images from text prompts via the MiniMax image-01 API.

Community
Intermediate
MooseGoose0701MooseGoose0701
1.1k

gemini-imagegen

Generate and edit images using Google Gemini multimodal models via the API.

Community
Intermediate