skills.rest
workboy
workboyCOMMUNITY
Explore all skills by this author →
GitHub

gpt-image-2

Generate images from prompts and edit existing images via the gpt-image-2 API.

4|Updated Apr 23, 2026
Search Tags:#image generation#prompt#base64#gpt-image-2#image edits#sub2api
One-click install
npx skills add https://github.com/workboy/gpt-image-2 --skill gpt-image-2-workboy
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gpt-image-2
Source: https://github.com/workboy/gpt-image-2/tree/main
Command: npx skills add https://github.com/workboy/gpt-image-2 --skill gpt-image-2-workboy

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

It helps you turn text prompts into images, and also modify an existing image using image-to-image edits, without manually calling an image API.

Core Features & Use Cases

  • Text-to-Image Generation: Create new images from a prompt with a configurable size and number of outputs.
  • Image-to-Image Editing: Use a provided local image as the base and apply a prompt to edit/transform it (switches to the edits endpoint automatically).
  • Gateway Integration: Sends requests to a user-configured sub2api gateway using environment variables for authentication.

Quick Start

Use the gpt-image-2 skill to generate a 1024x1024 image by setting SUB2API_BASE_URL and SUB2API_API_KEY, then ask it to run the prompt "A futuristic city at sunset, cyberpunk style".

Frequently Asked Questions about gpt-image-2

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

FAQPage Schema
How do I generate images from text prompts using the gpt-image-2 model?▼

To generate images from text prompts, the Skill sends your prompt to the /v1/images/generations endpoint of the gpt-image-2 model. It requires configuring the SUB2API_BASE_URL and SUB2API_API_KEY environment variables to authenticate the request.

Can I edit an existing local image with gpt-image-2?▼

Yes, you can edit an existing local image by providing it as a base along with a prompt. The Skill automatically switches to the /v1/images/edits endpoint to perform image-to-image transformations based on your instructions.

Do I need an API key to use the image generation gateway?▼

Yes, you need to set the SUB2API_API_KEY and SUB2API_BASE_URL environment variables. These credentials are required to authenticate and route your image generation or editing requests through the sub2api gateway.

What is the best way to prototype concept art using image-to-image edits?▼

The best way to prototype concept art is by supplying a base image and a transformation prompt. The Skill processes this via the /v1/images/edits endpoint, allowing rapid visual iterations without manual API calls.

How do I configure the output size when creating marketing visuals?▼

You can configure the output size and the number of outputs when generating marketing visuals. The Skill passes these parameters to the /v1/images/generations endpoint, allowing you to create images like a 1024x1024 visual.

Related Skills

Explore More Design & Creative Skills→
okbest2024okbest2024

whatsapp-business

Manage WhatsApp Business API messaging and templates with OAuth authentication via Maton gateway.

Community
Intermediate
atro2829-hubatro2829-hub

image-generation

Generate images from text prompts and return base64-encoded data.

Community
Intermediate
jason660519jason660519

stable-diffusion-image-generation

Generate images from descriptive prompts using Stable Diffusion pipelines in Python.

Community
Advanced
happycapy-aihappycapy-ai
137

nano-banana-pro

utility for generating and editing images with adjustable precision and scale.

Community
Intermediate