openai-image-gen

Generate images from prompts via the OpenAI Images API and compile a browsable gallery.

327|85|Updated Jan 29, 2026
One-click install
npx skills add https://github.com/letta-ai/lettabot --skill openai-image-gen-letta-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-image-gen
Source: https://github.com/letta-ai/lettabot/tree/main/.skills/openai-image-gen
Command: npx skills add https://github.com/letta-ai/lettabot --skill openai-image-gen-letta-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill automates batch image creation using the OpenAI Images API, producing multiple visuals from prompts and assembling them into a browsable gallery.

Core Features & Use Cases

  • Batch image generation from prompts via the OpenAI Images API.
  • Random prompt sampler and resulting gallery that includes a prompts.json mapping.
  • Output artifacts: an index.html gallery and a JSON file of prompts for easy sharing and reproducibility.
  • Use Case: teams quickly generate visual concepts for marketing, product design, or creative exploration.

Quick Start

Set the OPENAI_API_KEY environment variable, then run the generator:

  • Set: export OPENAI_API_KEY="your-key"
  • Run: python3 {baseDir}/scripts/gen.py Optional: pass --count, --model, --size to customize output, e.g.: python3 {baseDir}/scripts/gen.py --count 8 --model gpt-image-1

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 AI images from prompts using the OpenAI Images API?

You can batch-generate AI images from prompts by running the provided Python script, which calls the OpenAI Images API and compiles the retrieved visuals into a browsable HTML gallery.

Do I need an OpenAI API key to generate images and compile a browsable gallery?

Yes, you must set the OPENAI_API_KEY environment variable before running the generator to authenticate OpenAI Images API requests and retrieve your batch-generated visuals.

Can I customize image size and model for batch AI image generation?

Yes, you can pass optional arguments like --count, --model, and --size to the generator script to customize the batch image output, such as selecting gpt-image-1.

What output artifacts are created when generating AI art for creative workflows?

The batch image generation process outputs an index.html browsable gallery and a prompts.json file, providing easy sharing and reproducibility for marketing or product design concepts.

What is the best way to explore visual concepts for product design quickly?

Using a random prompt sampler to batch-generate AI images via the OpenAI Images API provides rapid visual concepts, assembling the results into a browsable gallery for creative exploration.

Does batch image generation work for marketing teams needing reproducible AI art?

Yes, marketing teams can batch-generate AI art from prompts, with a prompts.json mapping ensuring reproducibility and an index.html gallery enabling easy visual concept sharing.