Gpt Image 1 5

Wraps OpenAI's GPT Image 1.5 for both text-to-image generation and editing with optional masks. You get three quality levels, multiple aspect ratios including auto-sizing, and transparent background support. The editing mode is solid: point it at an existing image and describe your changes, or use a mask for precise inpainting. It runs via uv and saves timestamped PNGs to your working directory. Handles API key from args or environment. One nice touch is the dual editing approach, letting you either rework the whole image or target specific regions with a transparency mask. Straightforward if you need OpenAI image generation wired into Claude without leaving the terminal.

skills.sh installs: 620
GitHub stars: 301
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add intellectronica/agent-skills --skill gpt-image-1-5 --agent claude-code

Installs into .claude/skills of the current project.

Files

GPT Image 1.5 - Image Generation & Editing

Generate new images or edit existing ones using OpenAI's GPT Image 1.5 model.

Generation: Uses the Responses API with image_generation tool
Editing: Uses the Image API for reliable mask-based inpainting

Usage

Run the script using absolute path (do NOT cd to skill directory first):

Generate new image:

uv run ~/.claude/skills/gpt-image-1-5/scripts/generate_image.py --prompt "your image description" --filename "output-name.png" [--quality low|medium|high] [--size 1024x1024|1024x1536|1536x1024|auto] [--background transparent|opaque|auto] [--api-key KEY]

Edit existing image (without mask - full image edit):

uv run ~/.claude/skills/gpt-image-1-5/scripts/generate_image.py --prompt "editing instructions" --filename "output-name.png" --input-image "path/to/input.png" [--size 1024x1024|1024x1536|1536x1024|auto] [--api-key KEY]

SKILL.md on GitHub

Details

Repository: github.com/intellectronica/agent-skills
Categories: AI & Agent Building, Generative Media
First seen: Jun 3, 2026