skills.rest
landfill
landfillCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

gpt-image-1-5

Generate and edit images with OpenAI's GPT Image 1.5 via CLI.

Updated Dec 26, 2025
One-click install
npx skills add https://github.com/landfill/devtool-and-rule --skill gpt-image-1-5
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gpt-image-1-5
Source: https://github.com/landfill/devtool-and-rule/tree/main/skills/gpt-image-1-5
Command: npx skills add https://github.com/landfill/devtool-and-rule --skill gpt-image-1-5

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openai, Pillow.

What problem does it solve?

Automates image generation and editing using OpenAI's GPT Image 1.5 with deterministic CLI usage, including optional masks for precise inpainting.

Core Features & Use Cases

  • Generation: Text-to-image generation with size and background controls
  • Editing: Mask-based editing for precise changes (inpainting)
  • Deterministic Output: Save outputs to user-specified paths with consistent filenames
  • Usage: Quick-start examples to generate product mockups or edit existing images

Quick Start

Generate a 1024x1024 image from the prompt "A futuristic cityscape at sunset" and save as city.png.

Frequently Asked Questions about gpt-image-1-5

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

FAQPage Schema
How do I generate images from text prompts using OpenAI?▼

Text-to-image generation converts natural language prompts into images via OpenAI's API. This Skill automates that process with CLI arguments for prompt, size, and background options, then saves the output to your specified path with a consistent filename.

Can I edit existing images with inpainting and masks?▼

Mask-based inpainting modifies specific regions of an image while preserving the rest. This Skill supports uploading an existing image and mask to target precise edits, letting you change details without regenerating the entire image.

How do I configure and pass my OpenAI API key to the image generation tool?▼

API key management accepts credentials via command-line arguments or environment variables, avoiding hardcoded secrets. Set your key either way, and the Skill authenticates requests to OpenAI's endpoints automatically.

What image sizes and quality options are available for generation?▼

The Skill lets you specify output dimensions and quality settings at generation time. Supported sizes and quality levels are configurable via CLI arguments, so you can optimize for your use case before the request reaches OpenAI.

Do I need additional libraries beyond OpenAI to use image editing features?▼

Pillow is required alongside the OpenAI dependency to handle image processing and mask operations. Both dependencies are bundled, so install them together to enable full generation and editing functionality.

What's the difference between full-image editing and mask-based inpainting?▼

Full-image edits regenerate an entire image from a new prompt, while mask-based inpainting preserves masked regions and modifies only the unmasked area. Use inpainting for surgical changes and full edits for wholesale image regeneration.

Related Skills

maragudkmaragudk
48

nanobanana

Generate and edit images via text prompts using the nanobanana CLI.

Official
Intermediate
SJTU-IPADSSJTU-IPADS
7

image-utils

Automate deterministic image editing tasks on image collections with Pillow.

Official
Intermediate
akhilksap2026akhilksap2026

photo-editor

Automate image resizing, cropping, filtering, and optimization with Python code.

Community
Intermediate
peteromalletpeteromallet
97

stable-diffusion-image-generation

Generate and edit images from text prompts using Stable Diffusion pipelines.

Community
Intermediate