generate-image

Generate and edit images using OpenRouter AI models via a Python script.

4|Updated Jan 6, 2026
One-click install
npx skills add https://github.com/flight505/claude-project-planner --skill generate-image-flight505
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: generate-image
Source: https://github.com/flight505/claude-project-planner/tree/main/project_planner/.claude/skills/generate-image
Command: npx skills add https://github.com/flight505/claude-project-planner --skill generate-image-flight505

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Generate and edit AI-powered images using OpenRouter models for photos, illustrations, and visual assets. This skill streamlines the creation of marketing visuals, concept art, and presentation graphics without leaving your workflow.

Core Features & Use Cases

  • Generate high-quality images from text prompts using multiple AI models.
  • Edit existing images by applying prompts to modify visuals.
  • Select models, handle input images via the scripts, and save outputs for documents, slides, or websites.
  • Use cases include marketing visuals, product concept art, and workflow mockups.

Quick Start

Use the scripts/generate_image.py script to generate or edit images:

  • python scripts/generate_image.py "A beautiful sunset over mountains"
  • python scripts/generate_image.py "Make the sky purple" --input photo.jpg
  • python scripts/generate_image.py "Abstract art" --model "black-forest-labs/flux.2-pro"

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 using OpenRouter?

You can generate AI images from text prompts by running the Python script with your prompt and an OpenRouter API key. This automates image generation for photos, illustrations, and concept art directly within your workflow.

Can I edit existing photos by applying text prompts to modify visuals?

Yes, you can edit existing photos by passing an input image file and a text prompt to the script. This applies AI-driven modifications to your visuals, allowing you to alter specific elements like changing a sky color.

Do I need an API key to generate AI images for marketing visuals?

Yes, generating AI images for marketing visuals requires an OPENROUTER_API_KEY. You must configure this key in your environment to authenticate requests to the OpenRouter models used by the script.

How do I select a specific AI model like flux.2-pro for image generation?

You can select a specific AI model for image generation by passing the model argument with your desired model identifier to the script. This allows you to choose models like black-forest-labs/flux.2-pro for tailored outputs.

What Python dependencies are required to automate image generation?

Automating image generation requires the Python requests library to handle HTTP calls to OpenRouter. You also need the generate_image.py script included in the skill's scripts component to execute the process.

What output formats are supported when creating visual assets for presentations?

The script supports saving image outputs in common formats suitable for documents, slides, and websites. This ensures generated visual assets for presentations integrate smoothly into your existing files.