DEV Community: Flixly

GPT Image 2.6 Is Live on Flixly: Flare and Sunburst, With Real Examples

Flixly — Thu, 05 Nov 2026 16:31:14 +0000

GPT Image 2.6 is live on Flixly. OpenAI's newest image model comes in two versions: Flare, the fast everyday model, and Sunburst, the precision model for fine detail, text and careful edits. Both can create an image from a prompt or edit images you upload, up to 16 at a time. Open Sunburst or Flare in the Image Generator, pick a quality from Low to Maximum, and Flixly shows the credit price before you generate.

New: animated GIFs. GPT Image 2.6 can also make looping GIFs of 4 to 16 frames, from a prompt or from your own picture: choose GIF as the output format. See how to make GIFs with GPT Image 2.6 for six examples and tips.

What is GPT Image 2.6?

GPT Image 2.6 is the next version of OpenAI's GPT Image family, after GPT Image 2.5. As with 2.5, it ships as two models:

Flare is built for speed. It gives fast, high-quality images with natural lighting, rich textures and complex layouts, and handles most everyday work.
Sunburst is built for precision. It spends longer on each image for extra fidelity on intricate detail and lettering, and its edits stay close to your instruction: the subject and composition hold across many rounds of changes.

On Flixly, each model has a generation version and an edit version, all in the same model picker.

What you can control on Flixly

	Create from a prompt	Edit your images
Models	GPT Image 2.6 Flare, GPT Image 2.6 Sunburst	GPT Image 2.6 Flare Edit, GPT Image 2.6 Sunburst Edit
Quality	Low, Medium, High, Extra high, Maximum	Medium, High, Extra high, Maximum
Output size	1024 × 1024, 1536 × 864, 864 × 1536	The same three, plus 1536 × 1024, 1024 × 1536, 1536 × 1152, 1152 × 1536, or Auto to keep your image's shape
Images in	None	1 to 16
Background	Auto, opaque or transparent	Auto, opaque or transparent
Format	PNG, JPEG or WebP	PNG, JPEG or WebP

New images from GPT Image 2.6 cost the same credits as GPT Image 2.5 at each quality. Edits are priced by the number of images you send, so a quick one-image edit costs less than a 16-image composition. The exact price is shown before you generate.

Real examples

Every image below was made on Flixly with GPT Image 2.6, with the prompt and settings shown. Each is the first result we got, resized for the web and otherwise unedited. The times run from pressing Generate to the finished image.

Sunburst: a poster with exact lettering

GPT Image 2.6 Sunburst, High quality, 864 × 1536. It took 45 seconds.

A vintage-style travel poster for a fictional coastal town called "Port Lumen". Bold Art Deco headline "PORT LUMEN" across the top, a smaller line "EST. 1924 · THE LIGHTHOUSE COAST" beneath it, and a footer reading "Ferries daily · Pier 3". A tall striped lighthouse at dusk, sailboats, warm sunset gradient, screen-printed texture, crisp clean lettering.

All three lines of text came out exactly as written, including the middle dots, and the poster keeps a consistent screen-printed look from the border to the rocks.

Sunburst edit: same poster, winter night

GPT Image 2.6 Sunburst Edit, Medium quality, 864 × 1536, with the poster above as the only image. It took 41 seconds.

Turn this into a winter night: snow on the rocks, roofs and railings, gentle snowfall, a deep blue night sky with stars, warm glowing windows, the lighthouse beam still on. Keep every word of the lettering, the layout, the borders and the poster style exactly as they are.

The season, sky and light changed, and the snow sits on the rocks and roofs. The headline, both text lines, the borders and the boats stayed where they were. That is the kind of scoped edit Sunburst is built for.

Sunburst at Maximum: an illustrated cutaway

GPT Image 2.6 Sunburst, Maximum quality, 1536 × 864. It took 104 seconds.

A detailed illustrated cutaway of a lighthouse, like a page from a vintage science book. Label each level with neat hand-lettered captions and leader lines: "LAMP ROOM", "WATCH ROOM", "KEEPER'S QUARTERS", "OIL STORE", "SPIRAL STAIR". Title at the top: "HOW A LIGHTHOUSE WORKS". Cream paper, ink linework, muted watercolor, tiny keeper figure climbing the stairs.

Every label we asked for is there, spelled right and pointing at the right level, and the model added its own panels on the lens, the beam at sea and the keeper's work. Maximum quality is the setting for dense pages like this, where small text has to stay sharp.

Flare: a candid street photo

GPT Image 2.6 Flare, Medium quality, 1536 × 864. It took 35 seconds.

Candid street photograph at dawn in Hanoi's Old Quarter: a woman in a conical hat ladles pho from a steaming pot at a tiny sidewalk stall, plastic stools, motorbikes blurred in the background, soft golden side light through the steam, natural skin texture, 35mm film look.

Flare is the everyday model: natural light, believable texture and a busy layout, at Medium quality in about half a minute.

Flare edit: two images, one scene

GPT Image 2.6 Flare Edit, Medium quality, 1536 × 864, from two images we made with Flare first: a studio portrait and a product shot of a bicycle. It took 39 seconds.

Photograph of the woman from the first image riding the red bicycle from the second image along a rainy Paris street at night. Keep her face, silver hair, freckles and mustard raincoat, and keep the bicycle's red frame, wicker basket and cream tyres. Wet cobblestones, café lights reflecting, slight motion blur, cinematic 35mm look.

The rider keeps her silver hair, freckles and raincoat, and the bicycle keeps its red frame, basket and cream tyres. You can send up to 16 images in one edit: characters, products, places or a style reference.

GPT Image 2.6 vs GPT Image 2.5

The same poster prompt and settings (Sunburst, High, 864 × 1536) on both versions, run on the same day:

GPT Image 2.5 Sunburst	GPT Image 2.6 Sunburst

Both versions set every word correctly here. The 2.6 poster has more going on in the scene, with a keeper's cottage, a pier, a town on the far shore and a beam across the sky, and a more finished Art Deco frame. One prompt is not a benchmark, so try your own brief on both. Both versions stay on Flixly, and projects built on 2.5 keep working as they are.

Which one should I use?

Flare for most images: photos, product shots, social posts and quick variations. Start at Medium and step up when you need more detail.
Sunburst when precision matters: posters and layouts with text, intricate illustrations, and edits that must leave everything else alone.
Edit versions when you start from images: restyle a picture, change the season or time of day, or combine up to 16 references into one scene. Use Auto size to keep your source image's shape.

How to use GPT Image 2.6 on Flixly

Open the Image Generator with GPT Image 2.6 Sunburst or GPT Image 2.6 Flare selected.
To edit, switch to Image to image and upload your image, plus up to 15 more, or open Sunburst Edit or Flare Edit directly.
Describe the image or the change. Put any words that must appear in quotation marks, and say what must stay the same.
Choose the quality, the output size, the background and the format. The credit price updates as you go.
Press Generate. Your image is saved to your history, where you can download it or edit the result again.

Try GPT Image 2.6 on Flixly. Originally published on the Flixly blog.

GPT Image 2.6 vs 2.5 vs 2.0: Character Consistency and Real Results

Flixly — Thu, 05 Nov 2026 16:26:27 +0000

Can GPT Image keep one character consistent across the keyframes of a 2-minute video? We gave GPT Image 2.6, 2.5 and 2.0 the same reference and six shots, plus five more tests: text, instructions, a portrait, an illustration and an edit. Every image below is the first result we got on Flixly, with the same prompt and settings.

TL;DR: For keyframes, GPT Image 2.6 Sunburst was the most consistent: across six shots of a short film it kept the same face, freckles and eyebrow scar, and followed each shot's direction best. 2.5 Sunburst held the face almost as well. 2.0 kept the outfit but let the face drift. All three spelled text correctly. 2.0 still offers 2K, 4K and custom sizes.

What is the difference between GPT Image 2.6, 2.5 and 2.0?

They are three generations of OpenAI's image model, and all three are on Flixly:

GPT Image 2.0 is the earlier model with one version. On Flixly it goes up to 4K, with custom sizes at 2K and 4K.
GPT Image 2.5 introduced two versions: Flare for fast everyday images and Sunburst for precision. It added transparent backgrounds and quality levels up to Maximum.
GPT Image 2.6 keeps the Flare and Sunburst split and the same controls, and is the newest. Read the GPT Image 2.6 launch post for more examples.

To keep the test fair, we compared each newer model's precision version, Sunburst, with GPT Image 2.0, all at High quality and 1024 × 1024.

Specs on Flixly

	GPT Image 2.0	GPT Image 2.5 (Flare, Sunburst)	GPT Image 2.6 (Flare, Sunburst)
Quality	Low, Medium, High	Low to Maximum (5 levels)	Low to Maximum (5 levels)
Output size	1K, 2K or 4K, with custom sizes at 2K and 4K	1024 × 1024, 1536 × 864, 864 × 1536; more shapes and Auto for edits	The same as 2.5
Images per edit	Up to 16	Up to 16	Up to 16
Transparent background	No	Yes	Yes
Formats	PNG, JPEG, WebP	PNG, JPEG, WebP	PNG, JPEG, WebP
Price at High quality	Higher	Lower	The same as 2.5

Flixly shows the exact credit price for each model and setting before you generate.

Character consistency: six keyframes for a 2-minute short

A 2-minute film is roughly 12 to 24 shots. Most AI video workflows, including Story Creator, start each shot from a keyframe: a still image that the video model animates. If the character's face changes between keyframes, it changes between shots, and the film falls apart. So this is the test that matters most for video.

We made one reference image of a character, Mira, with a different model, so no version had a head start. It has details that are easy to check: a copper bob, green eyes, freckles, a small scar through one eyebrow, a navy sweater with a white anchor, and a mustard scarf.

Each version got the same reference image and the same six shot descriptions, at High quality in 16:9. Every prompt began with this line, followed by the shot:

Keyframe for a short film. The woman from the reference image, Mira: the same face, short copper-red bob, green eyes, freckles, the small scar through her eyebrow, navy knitted sweater with the white anchor and the mustard-yellow scarf.

Shot	Description
1	Wide shot from below: Mira climbs the spiral iron stairs inside an old lighthouse at night, holding a glowing lantern.
2	Medium shot: Mira stands on the lighthouse balcony in a storm, rain lashing, her scarf whipping in the wind, gripping the railing.
3	Close-up of Mira's face lit by the warm glow of the great lighthouse lamp at night, determined expression.
4	Side view: Mira rows a small wooden boat through thick fog at dawn.
5	Mira kneels on a pebble beach, helping a soaked old fisherman out of the surf.
6	Mira laughs at a table by the window of a cosy harbour café, holding a steaming mug.

In each storyboard below, shots 1 and 2 are on the top row, 3 and 4 in the middle and 5 and 6 at the bottom.

Here are the two face-forward shots next to the reference, one version per row (2.0, then 2.5, then 2.6), with the reference on the left, the lamp close-up in the middle and the café on the right:

Result: 2.6 and 2.5 kept Mira. 2.0 kept her clothes.

The outfit held on all three. Every keyframe from every version has the copper bob, the anchor sweater and the mustard scarf. That much works on any of them.
The face is where they differ. 2.5 and 2.6 kept the same face, the freckles and the scar on the same eyebrow in every shot where the face is visible, including the laughing café shot. 2.0 kept the scar in the close-up but lost it in the café, where her face also came out slimmer and more polished than the reference.
2.6 followed the shot directions best. It was the only one to give the rowing shot a real side angle; 2.0 and 2.5 framed it face-on. It also made the widest low angle on the stairs and added lightning to the storm without being asked, and its café shot is the most lived-in.
Size matters for video. In 16:9, 2.0 returned 1280 × 720 keyframes and 2.5 and 2.6 returned 1536 × 864, which gives the video model more detail to work from.

For a 2-minute film, that means using GPT Image 2.6 Sunburst for keyframes, or 2.5 Sunburst if your project already uses it, and giving every shot the same reference image. Story Creator offers GPT Image 2.5 Sunburst for keyframes today; to use 2.6, make your keyframes in the Image Generator with GPT Image 2.6 Sunburst Edit. Name the details that must not change in each prompt, as we did with the scar, the anchor and the scarf.

Test 1: a recipe card full of text

A minimalist recipe card on linen paper titled "LEMON OLIVE OIL CAKE". Under the title, a neatly typeset ingredient list: "200 g flour", "3 eggs", "150 ml olive oil", "2 lemons, zested", "180 g sugar". At the bottom: "Bake 45 min at 180°C". A small watercolor lemon illustration in the corner, soft daylight, top-down photo.

Result: a three-way tie on accuracy. All three spelled every line correctly, including "180°C". 2.0 made the boldest card, with a framed border and a large two-line title. 2.5 placed a smaller card among real lemons. 2.6 kept closest to "minimalist", with a deckle-edged card and the most even spacing, and it was also the fastest of the three here.

Test 2: seven cups, five instructions

Seven teacups in a row on a white wooden shelf, from left to right: red, orange, yellow, green, blue, indigo, violet. The third cup has a small chip on its rim, a black cat sleeps next to the blue cup, and a sticky note on the wall above reads "DO NOT TOUCH". Soft morning light, product photo.

Result: 2.6 was the most literal. All three got seven cups in the right colour order, a chip on the third cup and the note. 2.0 and 2.5 put the cat behind the row of cups. 2.6 curled it up on the shelf right beside the blue cup, which is exactly what the prompt said.

Test 3: a photoreal portrait

Close-up portrait of an elderly fisherman mending a blue net on a wooden dock at golden hour, weathered skin, silver stubble, rope-calloused hands in focus, a seagull on a post behind him, shallow depth of field, 85mm photograph.

Result: all three are convincing. 2.0's net came out teal rather than blue. 2.5 and 2.6 both kept the hands in sharp focus with believable skin. 2.6 added the most texture, in the wool, the stubble and a netting needle in his hand, along with the warmest golden-hour light.

Test 4: a children's book illustration

A children's book illustration of a fox and a badger sharing an umbrella in the rain on a cobblestone bridge, gouache texture, warm lamplight, puddle reflections, gentle and cozy.

Result: a matter of taste. 2.0 has the thickest gouache brushwork and the closest crop. 2.5 pulled back to show the whole bridge and village. 2.6 has the most storybook detail, with rain drops falling off the umbrella, ripples in the puddles and a chimney smoking in the distance, and the two friends are clearly sharing one umbrella.

Test 5: a precise edit

The source image, made with a different model:

Turn this into a bright sunny morning: fresh white paint on the house, a red front door, blue sky, a garden of sunflowers in front. Keep the shape of the house, every window, the towers and the camera angle exactly the same.

Result: all three passed. Each one kept the two towers, the window layout and the camera angle while changing the paint, the door, the sky and the garden. 2.5 and 2.6 added climbing roses that weren't asked for, a small liberty. The differences between versions are smaller in edits than in new images.

Speed

Times run from pressing Generate to the finished image, on Flixly, at High quality and 1024 × 1024. Each is a single run, so treat them as a rough guide:

	GPT Image 2.0	GPT Image 2.5 Sunburst	GPT Image 2.6 Sunburst
Average of four new images	57 s	46 s	52 s
Edit	63 s	62 s	68 s

Sunburst is the precision version. For speed, use Flare: in our launch examples, GPT Image 2.6 Flare at Medium quality finished in 32 to 39 seconds.

Which one should you use?

GPT Image 2.6 Sunburst for keyframes and recurring characters, prompts with many instructions, posters and layouts with text, and dense illustrations. It was the most consistent across every test.
GPT Image 2.6 Flare for most everyday images, when speed matters more than the last bit of detail.
GPT Image 2.5 if you already have a project built on it. It keeps working, and in these tests it was close to 2.6.
GPT Image 2.0 when you need 2K or 4K output, or a custom size.

How to compare them yourself

Open the Image Generator with GPT Image 2.6 Sunburst, GPT Image 2.5 Sunburst or GPT Image 2.0 selected.
Paste the same prompt into each and pick the same quality and size.
For edits, upload the same image to GPT Image 2.6 Sunburst Edit, GPT Image 2.5 Sunburst Edit and GPT Image 2.0 Edit.
Check the credit price shown before each one, then press Generate. Every result stays in your history, so you can compare them side by side.

Frequently asked questions

Which GPT Image version keeps a character most consistent?

In our test, one reference image and six keyframes for a short film, GPT Image 2.6 Sunburst and 2.5 Sunburst kept the same face, freckles and eyebrow scar in every shot where the face is visible. GPT Image 2.0 kept the outfit but dropped the scar in one shot and drifted to a slimmer face. 2.6 also followed the camera directions most closely.

How do I keep a character consistent across a 2-minute AI video?

Make one clear reference image of the character, then create every keyframe from that same reference with an edit model, such as GPT Image 2.6 Sunburst Edit. In each prompt, name the details that must not change, like the hairstyle, a scar or a logo on the clothes. Story Creator on Flixly builds keyframes from your character references for you, shot by shot.

Is GPT Image 2.6 better than GPT Image 2.5?

In our side-by-side tests on Flixly, GPT Image 2.6 Sunburst was the most consistent: it held a character's face across six keyframes, followed every instruction literally, such as placing a cat exactly next to the blue cup, and added the most fine detail. GPT Image 2.5 was close behind and spelled text just as accurately. The difference is in the details, not a different class of result.

Is GPT Image 2.6 better than GPT Image 2.0?

For most images, yes. 2.6 offers more quality levels, transparent backgrounds and the Flare and Sunburst versions, and it costs less at High quality. GPT Image 2.0 still has one advantage on Flixly: 2K and 4K output with custom sizes.

Which GPT Image version is best for text in images?

All three spelled every line of our recipe card correctly, including the degree sign. GPT Image 2.6 Sunburst gave the cleanest layout. For posters and pages with a lot of small text, use 2.6 Sunburst at High or Maximum quality.

Which GPT Image version is fastest?

At High quality, all three took between 43 and 76 seconds per image in our tests. For speed, use GPT Image 2.6 Flare: at Medium quality it finished in 32 to 39 seconds in our launch examples.

Try all three on Flixly. Originally published on the Flixly blog.