Sign in

GPT Image 2.6 — AI image generator and editor

Try a starting brief

Enter a prompt before generating.

Preview

GPT Image 2.6 preview

Create and refine product images with GPT Image 2.6

Create product scenes and revise existing images with GPT Image 2.6. Choose Flare for rapid exploration or compare Sunburst for detailed reference edits. Both accept up to 16 references and an optional mask. Quality controls rendering effort; complexity controls planning. Begin with a small image and check product shape and lettering before increasing resolution.

1K / 2K / 4K · Flare / Sunburst
Model versions
Flare / Sunburst

Choose Flare for quick iteration or Sunburst for detailed edits.

Output resolution
1K / 2K / 4K

Use automatic sizing, an aspect ratio or custom pixels.

Image references
Up to 16

Add a matching PNG mask for a targeted edit.

Choose the workflow that matches your brief

A focused starting point

Preserve the mug, lid and camera angle while changing only the tabletop and light. Describe one edit per round so you can identify what changed.

Know the boundaries

This page offers still-image generation and masked editing. Transparent backgrounds are experimental. SVG and GIF controls are not provided here; inspect lettering and alpha edges before delivery.

Review and download

Inspect the full image, then zoom into text, edges, reflections and object geometry. Download the accepted version and keep the prompt and settings so the next edit has a clear baseline.

From poster layout to material detail

SceneFlare created these illustrations to show how to describe typography, light and texture in a prompt.

Poster layout and typography

The dark blue headline stands out against warm paper, with tide lines filling the lower half. Specify the exact wording and give the main line a clear place in the layout.

Poster layout and typography

Light and material detail

Cool light picks out the ridges of the glass shell, and warm reflections reveal its curve. Describe the material and light direction, then zoom in to inspect the edges and texture.

Light and material detail

Create with a focused brief

01

Prepare the source and brief

Choose a mode first. Use clear source media you have permission to use, identify each reference’s role, and state what should remain unchanged.

02

Set scope and review the price

Select the smallest useful resolution, duration or image count for the first attempt. Review the displayed credits before submitting. Change one setting at a time when comparing versions.

03

Review and download

Inspect the full image, then zoom into text, edges, reflections and object geometry. Download the accepted version and keep the prompt and settings so the next edit has a clear baseline.

Questions before you create

What are the important limits?

This page offers still-image generation and masked editing. Transparent backgrounds are experimental. SVG and GIF controls are not provided here; inspect lettering and alpha edges before delivery.

How is the displayed price calculated?

The generator displays the site’s credit price for the selected settings. Resolution, duration, output count and reference inputs can affect it. Provider dollar estimates are not the site’s selling price. Review credits before submitting; generating another version is a new paid request.

Are the page visuals model samples?

The examples are from SceneFlare. The linked generation record documents the separate model test.

Create with a focused brief

Preserve the mug, lid and camera angle while changing only the tabletop and light. Describe one edit per round so you can identify what changed.

Flare / Sunburst

Model versionsChoose Flare for quick iteration or Sunburst for detailed edits.

1K / 2K / 4K

Output resolutionUse automatic sizing, an aspect ratio or custom pixels.

Up to 16

Image referencesAdd a matching PNG mask for a targeted edit.

Check mask edges

TipZoom in where the edit meets the original.