Available now

GPT Image 2: image editing

By OpenAI

OpenAI's GPT Image 2 creates detailed images from text and edits up to 16 images, with a mask and a transparent background when you need them.

Model ID
Maker
OpenAI

Input

Fields marked * are required. Review the price before generating.

Example prompt. Edit it or write your own.

The images to use as a reference for the generation. A maximum of 16 images are allowed.

Uploading a file needs an account. Create account

JPEG, PNG, WebP · up to 25 MB · 0/16

Use 'auto' to infer from input images.

White marks regions to edit and black marks regions to keep.

Uploading a file needs an account. Create account

JPEG, PNG, WebP · up to 25 MB

Additional settings

Use 'auto' to let the model pick the best quality for the prompt.

Starting price$0.12 / image

You sign up first. Your settings are kept.

About this model

Overview

GPT Image 2 turns a written brief into up to 10 images per run, in preset shapes or a size of your own, at low, medium or high quality. It can leave the background transparent for logos, stickers and cutouts.

The edit mode uses up to 16 images as references for a new picture. A mask limits the change to the white area and leaves the rest as it was.

What you can build

  • Illustrations and simple infographics with short labels
  • Logos and stickers on a transparent background
  • Product scenes built from your reference photos
  • Touch-ups inside a masked area

Prompting tips

  • Spell out any words that should appear in the image, in quotes, and say where they go.
  • Shape the idea at low or medium quality, then render the final at high.
  • For edits, say what changes and what stays; add a mask when only one area should change.

What to check

Proofread text and inspect edges, repeated objects and edited regions.

Inputs

  • Prompt (required): The prompt for image generation.
  • Images (required): The URLs of the images to use as a reference for the generation. A maximum of 16 images are allowed.
  • Image Size (optional): The size of the generated image. Use 'auto' to infer from input images. Options: Square HD, Square, Portrait 4:3, Portrait 16:9, Landscape 4:3, Landscape 16:9, Auto (size of your image).
  • Background (optional): Background for the generated image. Options: auto, transparent, opaque.
  • Quality (optional): Quality for the generated image. Use 'auto' to let the model pick the best quality for the prompt. Options: auto, low, medium, high.
  • Number of Images (optional): Number of images to generate. From 1 to 10.
  • Output Format (optional): Output format for the images. Options: jpeg, png, webp.
  • Mask (optional): Mask image URL. White marks regions to edit and black marks regions to keep.

Output and limits

  • Image sizes: Square HD (1024×1024), Square (512×512), Portrait 4:3 (768×1024), Portrait 16:9 (576×1024), Landscape 4:3 (1024×768), Landscape 16:9 (1024×576), Auto (size of your image).
  • File formats: JPEG, PNG, WEBP.
  • Up to 10 images per run.
  • Small or dense text in the image can come out misspelled.
  • Hands, crowds and complex poses can show artifacts; generate a few variations and pick the best.
  • Some prompts or outputs can be refused by safety checks.

Price guide

  • auto · up to / high · up to: $0.74 / image
  • low · up to: $0.12 / image
  • medium · up to: $0.26 / image