generate-image

Generate or edit images from natural-language prompts via OpenRouter and save PNG files.

21|2|Updated Dec 8, 2025

Search Tags:#image generation #Gemini #image editing #API key #OpenRouter #FLUX #scientific illustrations

Ready to run

npx skills add https://github.com/silverstein/claude-scientific-skills-desktop --skill generate-image-silverstein

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: generate-image
Source: https://github.com/silverstein/claude-scientific-skills-desktop/tree/main/corpus/generate-image
Command: npx skills add https://github.com/silverstein/claude-scientific-skills-desktop --skill generate-image-silverstein

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

It solves the time-consuming challenge of producing clear scientific illustrations and diagrams from text prompts, as well as iterating on existing images for posters, figures, and explanations.

Core Features & Use Cases

Image generation for scientific concepts: Turn detailed prompts into diagrams, schematics, infographics, and concept visualizations suitable for research communication.
AI image editing: Modify existing images by changing colors, adding/removing elements, and performing style transfers based on an editing instruction.
Model flexibility via OpenRouter: Supports generation and editing with Gemini image models and FLUX models, selecting the best fit for quality vs speed.

Quick Start

Use the image-generation skill to create a new scientific figure by running the provided script with your prompt, then use an input image to edit a specific part when you need revisions.

Frequently Asked Questions about generate-image

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

FAQPage Schema

How do I generate scientific illustrations from text prompts?▼

To generate scientific illustrations from text prompts, provide a natural-language description of your diagram or schematic. The script sends the prompt to OpenRouter image-capable chat completions and saves the returned base64-encoded image to a PNG file.

Do I need an OpenRouter API key to edit existing images?▼

Yes, an OpenRouter API key is required to edit existing images. You must supply the input image along with targeted edit instructions, and the script processes the revision by routing the request through OpenRouter image-capable chat completions.

Can I use FLUX or Gemini models for scientific diagram generation?▼

Yes, you can use FLUX or Gemini models for scientific diagram generation. The script supports model flexibility via OpenRouter, allowing you to select between Gemini and FLUX models to balance quality and speed for your visual outputs.

What is the best way to iterate on scientific figures for posters?▼

The best way to iterate on scientific figures for posters is to first generate the base visual from a detailed prompt, then apply targeted edit instructions to the saved PNG file for revisions like changing colors or adding and removing elements.

Does this image generation method output formats other than PNG?▼

No, this image generation method only outputs PNG files. The script specifically decodes the base64-encoded image returned from the OpenRouter API and saves the final scientific illustration or edited visual directly to a PNG file.

Are there limitations when creating infographic-style visuals with AI?▼

A key limitation when creating infographic-style visuals with AI is the dependency on text prompt clarity for scientific accuracy. Additionally, all outputs are constrained to PNG format and require routing through OpenRouter, meaning API access is mandatory for generation.