What is ChatGPT Images 2.5?

ChatGPT Images 2.5 is OpenAI’s latest image generation and editing model. It is designed to improve image quality, reference preservation, iterative editing and generation speed.

What is the difference between Flare and Sunburst?

Flare is better suited to fast exploration and higher-volume generation. Sunburst is better suited to detailed edits and situations where preserving an existing asset matters more than speed.

What does “pixel-identical” mean in AI image editing?

Pixel-identical means an area of the edited image contains exactly the same pixel values as the original file, not simply that it looks the same to the human eye. Generative models can recreate an area so closely that you don’t notice a difference while still changing some of the underlying pixels. If an asset must stay technically identical, such as a logo or approved product label, keep the original and composite the new edit into it instead of regenerating the whole asset.

Can ChatGPT Images 2.5 edit an existing image?

Yes. You can use an existing image as input and ask for specific changes while preserving the rest of the composition.

How do I keep the same character or product consistent across multiple scenes in MITO?

Use Elements to define reusable characters, objects and locations once, then bring them back into future scenes instead of rebuilding the same references every time.

Can I use a sketch as a reference for AI image generation?

Yes. A rough sketch or storyboard can be used as a visual reference when composition is easier to show than describe.

Flare vs. Sunburst: Which ChatGPT Images 2.5 Model Should You Use?

CHATGPT IMAGES 2.5

Another week, another AI model launch

The biggest difference this time is that editing finally starts feeling more like… editing.

OpenAI says ChatGPT Images 2.5 improves reference-image preservation, multi-turn editing and generation speed, with latency reduced by up to 50% compared with Images 2.0.

What changes in practice:

Edit what you asked for. Change one thing without accidentally changing five others. The rest of the image stays much more stable.
Keep previous edits intact. A few rounds of feedback no longer make your original image slowly disappear.
Wait less between revisions. Up to 50% lower latency makes the back-and-forth on tiny client requests much faster.

Two models, depending on what you’re doing

You probably don’t need maximum fidelity for every generation.

Sometimes you’re throwing fifteen ideas at the wall. Other times, the client has approved everything except one tiny detail.

Flare — for exploring ideas quickly. Moodboards, colorways, variations and quick creative exploration.
Sunburst — for protecting a nearly-finished asset. Detailed edits, campaign assets and final client revisions.

Think of Flare as “show me more options.”

And Sunburst as “please, for the love of God, don’t touch anything else.”

A few specs worth knowing

If you care less about model names and more about what you can actually get out of them, there are a few useful upgrades too:

More quality levels: alongside low, medium and high, you now get xhigh and max when you need more detail.
Up to 4K output: useful when the image is heading somewhere beyond a moodboard or social post.
Transparent backgrounds: generate transparent PNG or WebP assets directly, especially useful for product shots and compositing.
Built-in provenance: supported generated images can include C2PA metadata and an invisible SynthID watermark.

Basically: more control over how polished the output needs to be, without treating every generation like a final render.

What still isn’t perfect

The editing is much better, but there are still a few things to watch:

Preserved does not always mean untouched: an area can look identical after an edit while still having small pixel-level changes underneath.
Logos and approved brand assets still need care: if something must remain technically identical, keep the original asset locked and composite the edited part back into it instead of regenerating the whole image.
Edit boundaries are not perfectly strict: OpenAI notes that image-edit selections act as guidance, so changes can sometimes affect areas outside the region you selected. See OpenAI’s image editing guide.
Grain and texture can still appear: some early independent tests have reported subtle noise on flat gradients, skies and studio-style backgrounds after generation or repeated edits. This is not an officially documented OpenAI limitation, but it is worth checking before calling an asset final. See an early independent test.

In short: visually consistent is much better. Mathematically identical is still getting there.

Use it inside your MITO workflow

Both models are now available in MITO.

You can combine them with your existing references and Elements to keep characters, products, locations and other visual details consistent across iterations.

And when describing a composition in words becomes painful, use a rough sketch or storyboard as a visual reference instead.

Try ChatGPT Images 2.5 in MITO →