skills.rest
Aadi-110i
Aadi-110iCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

gpt-image

Generate and edit images with OpenAI GPT-Image-2 via the inference.sh CLI.

Updated Jul 28, 2026
Search Tags:#image generation#image editing#openai#text-to-image#inpainting#inference.sh#gpt-image-2
One-click install
npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill gpt-image-aadi-110i
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gpt-image
Source: https://github.com/Aadi-110i/PEP-PROJECT/tree/main/skills/gpt-image
Command: npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill gpt-image-aadi-110i

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Creating product mockups, marketing visuals, or edited photos normally requires design tools or manual image editing. This Skill lets you generate and modify images directly from text prompts using OpenAI's GPT-Image-2 model through the inference.sh CLI. ## Core Features & Use Cases - Text-to-Image Generation: Create images from text prompts with control over quality (low/medium/high), resolution (256–4096px), output format (PNG, JPEG, WebP), and batch size (up to 10 images). - Image Editing & Inpainting: Edit existing images using reference images, combine multiple reference images into one scene, or perform mask-based inpainting to replace specific regions. - Use Case: A marketer needs four logo variations for a coffee shop. Run a single command with the prompt, set n to 4 and quality to medium, and receive four PNG options in one batch. ## Quick Start Ask the AI to generate an image of a cat astronaut floating in space using the gpt-image skill with high quality settings.

Frequently Asked Questions about gpt-image

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

FAQPage Schema
How do I generate images with GPT-Image-2 from the command line?▼

Run belt app run openai/gpt-image-2 with a JSON input containing your prompt. You can add parameters like quality, width, height, and n to control output. The inference.sh belt CLI must be installed and authenticated with belt login first.

How to edit an existing image with OpenAI GPT-Image-2?▼

Pass one or more reference image URLs in the images array along with a prompt describing the edit, such as changing the background. For region-specific edits, also provide a mask image URL to perform inpainting on the masked area.

What image sizes and formats does GPT-Image-2 support?▼

GPT-Image-2 supports any resolution from 256 to 4096 pixels in 32-pixel increments for both width and height. Output formats include PNG, JPEG, and WebP, with an optional compression level from 0 to 100 for JPEG and WebP.

How much does GPT-Image-2 image generation cost?▼

Approximate pricing per image is $0.006 for low quality, $0.024 for medium, and $0.21 for high quality. Larger resolutions cost more. Run belt app get openai/gpt-image-2 for full pricing details.

Can GPT-Image-2 generate multiple images in one request?▼

Yes, set the n parameter between 1 and 10 to generate a batch of images from a single prompt. This is useful for producing multiple logo or design variations in one run.

Related Skills

Explore More Design & Creative Skills→
genmedia-labsgenmedia-labs
12

image-inpainting

Performs mask-driven image inpainting via the RunComfy CLI using Z-Image Turbo Inpainting.

Official
Intermediate
iterationlayeriterationlayer
2

image-transformation-api

Apply ordered image operations and return base64-encoded JSON.

Official
Advanced
inference-shinference-sh
688

p-image

Generate and edit images with Pruna P-Image models via inference.sh CLI.

Official
Intermediate
inference-shinference-sh
688

flux-image

Generate images with FLUX models via the inference.sh CLI.

Official
Intermediate