generate-image

Generate and edit images from prompts using Gemini 3 Pro Image Preview or Flux.2 Pro.

Updated Apr 26, 2026
One-click install
npx skills add https://github.com/GongXLiang/plot-study --skill generate-image-gongxliang
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: generate-image
Source: https://github.com/GongXLiang/plot-study/tree/main/.claude/plugins/cache/claude-scientific-writer/claude-scientific-writer/2f80d2aed0e6/.claude/skills/generate-image
Command: npx skills add https://github.com/GongXLiang/plot-study --skill generate-image-gongxliang

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Generate and edit high-quality images using AI models, enabling users to create visuals for presentations, marketing, and concept art without needing advanced design skills.

Core Features & Use Cases

  • Generate new images from natural language prompts using AI models (Gemini 3 Pro Image Preview, Flux.2 Pro) or edit existing images with prompts and an input image.
  • Flexible model and output options to fit product, marketing, and documentation workflows; supports both generation and editing tasks.
  • Use cases include hero images for slides, illustrations for articles, marketing visuals, and concept art for ideation.

Quick Start

Use the generate-image script to create or modify an image by providing a descriptive prompt, for example: "A futuristic city skyline at dusk" and let the tool handle generation and saving to a local 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 AI images from text prompts for presentations?

To generate AI images from text prompts, provide a descriptive natural language prompt like "A futuristic city skyline at dusk" to the script. The AI model handles image generation and saves the output directly to a local file for use in presentations or documents.

Can I edit an existing image using AI and a text prompt?

Yes, you can edit an existing image by providing both an input image and a modification prompt. The tool supports image editing tasks by passing the source file alongside your text instructions to the selected AI model.

Do I need an OpenRouter API key to generate images?

Yes, an API key is required to authenticate requests with the AI models. The tool includes error handling for missing API keys, ensuring you are prompted to configure your credentials before attempting to generate or edit images.

What AI models are available for generating concept art and marketing visuals?

Available AI models include Gemini 3 Pro Image Preview and Flux.2 Pro. These models support generating high-quality marketing visuals and concept art from natural language prompts based on your specific workflow requirements.

What's the best way to save generated AI images to a specific local path?

The best way to save generated images is by configuring the output path within the script parameters. This allows the tool to directly write the generated or edited visual to your specified local file destination.

Why does my AI image generation script fail to run?

Your AI image generation script may fail if the requests dependency is missing or the API key is not configured. The tool includes error handling to catch missing API keys, but you must ensure the Python environment has the required dependencies installed.