OpenAI · Image model · Released November 2026

GPT Image 2.6 image generator

OpenAI’s GPT Image 2.6 comes in two models: Flare for fast iteration and Sunburst for detailed work. On Flowith both can export animated GIFs and SVGs, not just stills.

GPT Image 2.6 on Flowith, prompt below (GPT Image 2.6)
GPT Image 2.6 on Flowith, prompt below

Prompt: Editorial portrait of a woman in a translucent iridescent raincoat standing in soft rain, a band of prism light across her face, pale blue backdrop, 35mm film grain. Run it

GPT Image 2.6 on Flowith

The settings you get in the Flowith composer. Checked on November 14, 2026.

Models
GPT Image 2.6 Flare and GPT Image 2.6 Sunburst
Sizes
From 21:9 to 9:21, up to 3840 px on the long side
Quality
Low, medium, high, xhigh, max
Formats
PNG, JPEG, WebP, animated GIF, SVG
Animated GIF
1 to 60 seconds, smooth, natural or stop-motion movement
Input
Text and reference images

What GPT Image 2.6 is good at

Flare or Sunburst

OpenAI positions Flare for fast iteration. Use it to explore; switch to Sunburst for the final, detailed image.

Animated GIFs

OpenAI added animated GIF output. On Flowith pick a length from 1 to 60 seconds and a movement style.

SVG export

Ask for an SVG and get a vector file for logos, icons and simple illustrations.

Markup-guided edits

OpenAI’s guide covers editing by marking up an image and a complexity setting for how much detail to draw.

How to use GPT Image 2.6 on Flowith

  1. Step 1

    Open Flowith with GPT Image 2.6 picked

    The button above opens a canvas with the model already selected in the composer.

  2. Step 2

    Write the prompt

    Attach reference images from the canvas or your library to hold a face, product or style.

  3. Step 3

    Choose size, aspect ratio and format

    Generate, and the image lands on the canvas.

  4. Step 4

    Keep going

    Select the image to edit, upscale, remove the background or vary it, or use it as the start frame of a video.

GPT Image 2.6 vs other image models on Flowith

All of these run on the same canvas, so you can try one prompt on several models and keep the best take.

ModelSizesReference imagesPick it for
Seedream 5.5 1K, 1.5K, 2KUp to 10Transparent PNGs, repeated edits
GPT Image 2.6 Up to 3840 pxYesText in images, GIF and SVG output
Nano Banana 2.1 1K, 2K, 4KUp to 14Many references, extreme ratios
Nano Banana Pro 1K, 2K, 4KYes4K detail

GPT Image 2.6 questions

GPT Image 2.6 is OpenAI’s image generation and editing family, released in November 2026 as two API models, Flare and Sunburst. In ChatGPT it is called Images 2.6.
Flare is built for fast iteration, so use it while exploring. Sunburst is the detailed model for the final image. Both are on Flowith.
Yes. On Flowith choose GIF for an animation from 1 to 60 seconds, or SVG for a vector file.
Up to 3840 px on the long side, for example 3840 × 2160, or 2880 × 2880 square.
Signing up is free. Each generation spends Flowith credits, and the cost depends on the settings you choose. Current rates for every model are on the pricing page.

Sources

The Keeper · film
The Keeper · film
Product photo
Product photo
The Keeper · film
The Keeper · film
Poster
Poster
Character · Fennec
Character · Fennec
3D illustration
3D illustration
Portrait
Portrait
The Keeper · film
The Keeper · film

Every frontier model. One canvas.

Text, image and video models side by side. Compare them on the same prompt, pick one per shot, or let the agent choose.

Start flowing.

Write it, picture it, film it. One sentence is enough to begin.