imagegen

Generate and edit images via the OpenAI Image API using a bundled CLI.

3|3|Updated Apr 5, 2026
One-click install
npx skills add https://github.com/diegocamara89/ai-skills-hub --skill imagegen-diegocamara89
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: imagegen
Source: https://github.com/diegocamara89/ai-skills-hub/tree/main/all-skills/imagegen
Command: npx skills add https://github.com/diegocamara89/ai-skills-hub --skill imagegen-diegocamara89

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openai, Pillow, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill automates the creation and modification of images for projects, reducing manual graphic design time and enabling rapid visual ideation.

Core Features & Use Cases

  • Deterministic generation via the bundled CLI for reproducible results.
  • Image edits with optional masks and per-image inputs to refine outputs.
  • Batch processing through JSONL prompts for large-scale visual assets.
  • Use cases include website hero images, product shots, UI assets, game art, and marketing visuals.

Quick Start

Install dependencies and run the imagegen CLI with a sample prompt to generate an image.

Frequently Asked Questions about imagegen

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

FAQPage Schema
How do I batch generate images with OpenAI using JSONL prompts?

You can batch generate images with OpenAI by processing JSONL prompts through the bundled CLI to create large-scale visual assets. This automates repetitive graphic design tasks, enabling rapid batch processing for projects requiring multiple images.

Can I edit existing images and apply masks with the OpenAI Image API?

Yes, you can edit existing images with the OpenAI Image API by applying optional masks and per-image inputs to refine outputs. This allows targeted modifications to specific image regions, streamlining visual ideation and asset modification.

What's the best way to get reproducible results when generating visual assets?

The best way to achieve reproducible results when generating visual assets is through deterministic generation via a bundled CLI. This ensures consistent image outputs across repeated runs, which is essential for reliable design workflows and UI assets.

Do I need an OpenAI API key to automate website hero images and game art?

Yes, you need to configure an OPENAI_API_KEY to automate the creation of website hero images and game art. This key connects your CLI commands to the OpenAI Image API for deterministic generation and batch processing.

Does batch processing images through a CLI support marketing visuals for apps?

Batch processing images through a CLI fully supports generating marketing visuals for apps. By supplying JSONL prompts, you can automate the creation of product shots and UI assets, reducing manual graphic design time.

Why use prompt augmentation for UI assets and product shots?

Prompt augmentation enhances CLI commands to refine UI assets and product shots by expanding simple text into detailed instructions. This improves the OpenAI Image API output quality and ensures generated marketing visuals match specific design workflows.