GPT Image 2.6 AI image editor

GPT Image 2.6 AI image editor on Morphic
Create now

OpenAI's editor: precise, steady edits. Characters and products stay put.

Every image model

One workspace
ChatGPT Images 2.6OpenAI
GPT Image 2.5OpenAI
Nano Banana 2.1Google DeepMind
Nano Banana ProGoogle DeepMind
Seedream 5.0 ProByteDance
Grok Imagine Image 2.0xAI
Ideogram 4.5Ideogram
Krea 3Krea

Edited the GPT Image 2.6 way

Start editing

Edit an image the GPT Image 2.6 way

  1. 01

    Add your image

    Upload the photo or design you want to change, plus a reference if a character or product has to stay the same.

  2. 02

    Name one change

    Say what changes and list what stays: the subject, the light, the framing. One change per round holds best.

  3. 03

    Refine round by round

    Check the result, then make the next change. Compare models side by side on the Canvas when a result drifts.

Start editing

GPT Image 2.6 editing use cases

Swap one thing, keep the room

Change a sofa, a coat or a color and keep the light, the framing and everything around it. GPT-Image-2.6 Sunburst is the model OpenAI built for steadier edits.

Before and after: a living room with a grey linen sofa, then the same room with a terracotta boucle sofa

One character, new scenes

Start from a reference sheet and place the same character anywhere. In ChatGPT, save the reference once and call it back by name; on Morphic, attach the sheet to every edit.

A gouache cartographer from a reference sheet, then the same character reading a map on a sea cliff

Restore an old photo

Clear scratches, dust and fading from a family print and keep the people, the scene and the black and white exactly as they were.

Before and after: a scratched, faded 1960s beach picnic snapshot, then the same photo restored

Stills that move

Turn a finished edit into a short loop for a listing, a post or an app screen. On Morphic, ask Copilot to animate the still. This loop was made from a GPT Image 2.5 edit with MiniMax H3 Max Turbo.

Edit prompt examples

Before and after: a woman in a camel coat on a rooftop at golden hour, then the same shot in an emerald velvet coat

Change a color

Change the coat to deep emerald velvet. Keep her pose, face and the light.

Edit prompt
Before and after: a living room with a grey linen sofa, then the same room with a terracotta boucle sofa

Swap an object

Swap the grey sofa for a terracotta bouclé sofa. Keep the room and the light.

Edit prompt
Before and after: a timber cabin in a pine forest on an overcast afternoon, then at blue hour with lit windows

Change the time of day

Make it blue hour with warm light in every window. Keep the cabin and trees.

Edit prompt
A gouache cartographer from a reference sheet, then the same character reading a map on a sea cliff

Character, new scene

The cartographer from the sheet, same coat and satchel, reading a map on a sea cliff.

Edit prompt
Before and after: a clear cocktail in a crystal coupe on a marble bar, then the same drink in deep ruby red

Change one detail

Make the drink deep ruby red with an orange twist. Keep the glass and the bar.

Edit prompt
Before and after: an alpine lake with a red canoe in summer, then the same lake with golden larches and mist

Change the season

Turn the season to autumn: golden larches and morning mist. Keep the canoe.

Edit prompt

Related workflows

Jewelry campaign

Jewelry campaign

One product shot becomes a full campaign pack with hero shots, angles, and format variations.

Try this workflow
Image reverse engineer

Image reverse engineer

Get a detailed prompt extracted from a reference image, and then a fresh recreation.

Try this workflow
Paradox frames

Paradox frames

Flash paradox photographs — any collision, any country

Try this workflow
Food photo studio

Food photo studio

Turn any dish photo or description into a styled, editorial-quality food photograph.

Try this workflow
Character age progression

Character age progression

Upload a photo of a person or character and get a single grid image showing them at different life stages, from baby to elderly.

Try this workflow

Color grade cinema

Set the look with one reference image. Apply that exact grade to any scene or batch.

Try this workflow

All on Morphic

Your complete image stack

Models

GPT Image 2.5, Nano Banana 2.1, Seedream 5.0 Pro, Grok Imagine Image 2.0, and more. Pick the look and swap mid-project.

Reference images

Add a character sheet or a product photo as a reference, so one mascot or product line keeps its look in every edit.

Image to video

Animate a finished still into a short clip, so the mascot you designed can wave on repeat.

Workflows

Turn a finished edit into a one-click Workflow. Rerun, share, or favorite it for fast reuse.

Simple pricing

Get started for free today, with the option to upgrade or cancel anytime.

Basic

$19/ month
billed as $228 per year

2400 monthly credits

1 user only

All models

Workflows

Standard

$24/ month
billed as $288 per year

3625 monthly credits

1 user only

All models

Workflows

Pro

$45/ month
billed as $540 per year

6350 shared monthly credits

1 user

+ up to 4 more at extra cost

All models

Workflows

Max

$170/ month
billed as $2040 per year

24650 shared monthly credits

1 user

+ up to 9 more at extra cost

All models

Workflows

Enterprise

For higher limits

Custom

pricing and billing terms

High-volume credits
Custom seat limits
All models
Workflows
Pricing Gradient

Free

For playing around

$0

forever free

Up to 20 credits
1 user only
Limited models
Workflows
Compare plan details

FAQs

What is the GPT Image 2.6 AI image editor?
GPT Image 2.6, sold in ChatGPT as ChatGPT Images 2.6, is OpenAI's image model released on November 4, 2026. OpenAI built it for more control over editing rounds: GPT-Image-2.6 Sunburst holds characters, products and brand details steadier across a chain of edits, and you can mark exactly where a change goes. On Morphic, the same edits run today on GPT Image 2.5 Sunburst.
How do I edit one part of an image without changing the rest?
Name the single change, then list what has to stay: the product, the light, the framing, the camera angle. Make one change per round. If a region has to stay identical, paste the approved change back into the original rather than asking again.
What is image markup in GPT Image 2.6?
Markup is a mark you draw on the image to show where an edit should land, such as a circle around a sign or an arrow at a sleeve, while you write the change in words. On Morphic, name the spot in the prompt instead, such as the box front, the second sign from the left, or only the scarf.
Can GPT Image 2.6 keep the same character across edits?
Yes, with a reference. In ChatGPT, save a reference image under a name and type the name in later chats. On Morphic, attach the reference to each edit; GPT Image 2.5 takes up to 10. Repeat the details that must not change, such as the outfit and colors, in every prompt.
Can GPT Image 2.6 turn an image into a GIF?
In ChatGPT, yes: upload a still and ask to animate it, then change the speed in the chat. On Morphic, ask Copilot to animate your still into a short looping clip: describe the motion and say it should end where it starts.
Is GPT Image 2.6 on Morphic?
Not yet. Its predecessor, GPT Image 2.5 Flare and Sunburst, edits on Morphic today with up to 10 reference images, on the paid plans. Every example on this page was made on Morphic with GPT Image 2.5, and the loop with MiniMax H3 Max Turbo. Morphic has a free plan, so you can open the workspace and try the wider catalog first.

You might also like