skills.rest
LeonChaoX
LeonChaoXCOMMUNITY
Explore all skills by this author →
GitHub

generate-image

Generate or edit images from text prompts via OpenRouter and save as PNG files.

783|65|Updated Feb 27, 2026
Search Tags:#image editing#visual assets#openrouter#generate#artwork#prompt to image#concept art
One-click install
npx skills add https://github.com/LeonChaoX/qinyan-academic-skills --skill generate-image-leonchaox
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: generate-image
Source: https://github.com/LeonChaoX/qinyan-academic-skills/tree/main/skills/03-%E5%AD%A6%E6%9C%AF%E6%BC%94%E7%A4%BA%E4%B8%8E%E5%8F%AF%E8%A7%86%E5%8C%96/generate-image
Command: npx skills add https://github.com/LeonChaoX/qinyan-academic-skills --skill generate-image-leonchaox

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

generate-image helps you quickly create or revise high-quality images from natural-language prompts, avoiding slow manual design work.

Core Features & Use Cases

  • General-purpose image generation: Produce photos, illustrations, artwork, and concept visuals for research and communication needs.
  • Image editing from an existing picture: Modify elements in a user-provided image using editing instructions (e.g., change background, remove text, add objects).
  • Model flexibility via OpenRouter: Use Gemini image preview for quality or FLUX for generation/editing needs, while saving outputs as PNG files.

Quick Start

Ask your agent to generate a new image from the prompt "A modern scientific poster hero image showing a DNA double helix in glowing blue tones" and save it to hero.png using the generate-image skill.

Frequently Asked Questions about generate-image

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

FAQPage Schema
How do I generate concept art from a text prompt for presentation materials?▼

To generate concept art from a text prompt, the Skill uses OpenRouter image models to process natural language descriptions and save the resulting visual assets as a local PNG file, reducing manual illustration effort.

Can I edit an existing image by changing the background or removing text?▼

Yes, you can edit an existing image by providing the picture alongside text instructions to modify elements like backgrounds or remove text, using OpenRouter models to apply the changes and save the output locally.

Do I need an OpenRouter API key to generate images?▼

Yes, you need an active OpenRouter API key and a supported model, such as Gemini image preview or FLUX, to handle the prompt-to-image processing and execute image generation or modification tasks.

What is the best way to create general-purpose artwork using FLUX or Gemini models?▼

The best way to create general-purpose artwork is routing prompts through OpenRouter to select FLUX for generation needs or Gemini for high-quality visual previews, automatically saving the final output as a PNG file.

What image formats are supported when saving generated visual assets?▼

Generated visual assets are saved locally as PNG files, ensuring that outputs from both image creation and editing tasks are stored in a standard, high-quality raster format on your machine.

Related Skills

Explore More Design & Creative Skills→
yf8578yf8578
1

generate-image

Generate and edit AI images via the OpenRouter API using Python requests.

Community
Intermediate
alohaysalohays
5

slide-excellence

Review presentation slides for visual, pedagogical, and proofreading issues.

Community
Advanced
rickyanandarickyananda
1

dspy

Build and optimize declarative language model programs with structured signatures.

Community
Advanced
jason660519jason660519

stable-diffusion-image-generation

Generate images from descriptive prompts using Stable Diffusion pipelines in Python.

Community
Advanced