openai-image-gen

Batch generate images from prompts via the OpenAI Images API.

117|8|Updated Jan 20, 2026
One-click install
npx skills add https://github.com/geezerrrr/motive --skill openai-image-gen-geezerrrr
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-image-gen
Source: https://github.com/geezerrrr/motive/tree/main/Motive/Resources/Skills.bundle/openai-image-gen
Command: npx skills add https://github.com/geezerrrr/motive --skill openai-image-gen-geezerrrr

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This skill enables batch generation of images from natural-language prompts using the OpenAI Images API, turning ideas into visuals without manual drawing.

Core Features & Use Cases

  • Random prompt sampler and an index.html gallery to quickly visualize results.
  • Model and parameter controls: choose gpt-image-*, dall-e-2, or dall-e-3 models, adjust size and quality, and tailor outputs with background, format, and style options (where supported).
  • Local workflow: saves generated images, a prompts.json, and a browsable gallery for sharing or review.

Quick Start

Run the Python script to generate images and open the locally generated index.html gallery.

Frequently Asked Questions about openai-image-gen

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

FAQPage Schema
How do I batch generate images from prompts using the OpenAI Images API?

To batch generate images from prompts using the OpenAI Images API, run the provided Python script to call the API with your prompts, saving generated images and a browsable index.html gallery locally.

Do I need an OPENAI_API_KEY to generate images with this Python script?

Yes, you need the OPENAI_API_KEY environment variable set to authenticate requests when you generate images with this Python script using the OpenAI Images API.

Can I use dall-e-2 and dall-e-3 models to batch generate different image sizes and formats?

Yes, you can use dall-e-2, dall-e-3, or gpt-image-* models to batch generate images, with controls to adjust output size, quality, background, format, and style options where supported.

How does the local gallery work for visualizing OpenAI Images API results?

The local gallery works by saving generated images and a prompts.json file locally, then automatically generating a browsable index.html file for quick visualization and sharing of your OpenAI Images API results.

What is the best way to visualize multiple images generated from natural-language prompts?

The best way to visualize multiple images generated from natural-language prompts is using the random prompt sampler and the locally generated index.html gallery to quickly review and share results.