GPT Image 2 Editing

OpenAIimage

Published April 21, 2026

About

GPT Image 2 Editing supports image editing and multi-image synthesis with high-quality results.

Documentation

OpenAI GPT Image 2 Edit

Precision image editing powered by OpenAI's GPT Image 2. Modify existing images with natural language — swap backgrounds, combine multiple sources, add or remove elements — while preserving the original style and quality.

Highlights

Multi-image synthesis — Accepts up to 16 input images in a single request. Combine product photos into a gift basket, merge reference images into a cohesive scene, or apply style from one image to another.

Context-aware editing — Understands what to change and what to preserve. Edits blend naturally with surrounding pixels, maintaining lighting consistency, material textures, and perspective.

High-fidelity input — Processes source images at full resolution without downsampling. Fine details like fabric weave, text on labels, and subtle gradients survive the editing process.

Pricing

QualityStandard SizeLarge (21:9 / 9:21)
Low$0.015$0.03
Medium$0.05$0.08
High$0.20$0.30

Standard covers most aspect ratios (1:1, 2:3, 3:2, 4:3, 16:9, etc). Large applies to ultra-wide/tall formats only.

When to Use

✅ Good fit❌ Consider alternatives
Product photo background swapsGenerating images from zero (use Generation model)
Combining multiple items into one scenePixel-perfect mask control (limited stability)
Packaging and label visualizationReal-time interactive editing
Style transfer across imagesVideo frame manipulation
Adding text overlays to existing photosSimple crops or color adjustments

Input Requirements

  • Images provided as publicly accessible URLs
  • Supported formats: PNG, JPEG, WebP
  • Up to 16 images per request
  • Max file size: 50MB per image
  • For best results: use consistent lighting and resolution across input images

Technical Specs

SpecValue
InputText prompt + 1–16 image URLs
OutputPNG, JPEG, or WebP
Resolution655,360 – 8,294,400 total pixels
Max edge3,840 px
Aspect ratioUp to 3:1
Edge constraintMultiples of 16
ExecutionAsync (submit → poll for result)

Related

Try GPT Image 2 Editing

Test this model in the Sandbase Playground with your own prompts.

Open in Playground

Related Models