ChatGPT Images 2.5 (GPT-Image-2.5 Sunburst): what the new OpenAI model can do and how to try it in your browser

OpenAI has released a new generation of image generation — GPT-Image-2.5. The family includes two models: Sunburst, focused on sharper details, more natural lighting and greater control across edits, and Flare, built for speed. Both support transparent backgrounds and are available via the API. We have added the flagship model of the family to our site as ChatGPT Images 2.5 — you can generate and edit images right in the browser, no API keys or subscriptions needed: the model page on NeuralSpace.

What is new compared to the previous generation

According to OpenAI, Sunburst draws noticeably sharper details with more natural lighting, and — most importantly — gives you more control when editing: long series of edits on a single frame no longer fall apart. Flare is the fast sibling: it delivers high-quality images over 50% faster.

Sunburst is available on the site right now — it is the quality-and-precision model. If there is demand, Flare will follow.

Five rendering levels — from draft to maximum

The previous models offered three quality levels. The 2.5 generation has five: low, medium, high, plus two upper levels — xhigh and max. The workflow is simple:

• Low — cheap drafts: iterate over compositions and angles quickly.
• Medium — a solid working middle for social media and websites.
• High — a confident final for most tasks.
• Xhigh and Max — when fine texture decides: print, large format, macro details.

The price per image is calculated and shown before you hit generate — no balance surprises.

Series of edits from a single source image

The signature skill of this generation is editing. In OpenAI's official demo, a long series of edits is applied to one starting frame: change the jacket color, replace the background, add eyeglasses, switch the scene to rainy weather, redraw it in pastel or as an architectural watercolor — and every step changes only what was asked.

On the site, editing mode turns on automatically: attach from one to sixteen reference images (up to 50 MB each) and write an instruction. There is no separate toggle — the model understands the mode from the presence of images in the request.

What the ChatGPT app demo shows: sketch, targeted edits and templates

Alongside the model release, OpenAI refreshed the ChatGPT app itself, and hands-on reviews show the character of this generation well. First, sketch-based input: in the app you can draw a rough diagram of a scene (a box for the couch, windows, a dog silhouette) and the model turns the doodle into a full interior — it interprets the sketch even with no text instructions at all. Generation also feels noticeably faster than before.

Second, targeted editing tools on top of the finished frame: circle an area and ask to "put a cat here", leave several comments in one batch ("make this plant dead", "add a rainbow outside", "make the walls gray"), highlight an object with the eraser so the model understands what to remove and fills the gap cleanly. A background remover separates a clear subject from its background in one click.

Third, reference photos. Reviews show the model restoring old snapshots (remove the glare, clean it up, put the kid in a suit — and it is still the very same kid), redesigning real spaces (a gravel backyard becomes a rock garden) and compositing three separate portraits into one photo. Another standout skill is identity preservation: people and animals stay recognizably themselves across long edit series — the image does not deteriorate from iteration to iteration, which is where image models were usually criticized. The app also gained templates — starting points for popular formats: logos, posters, interior design, illustration.

The sketch input and templates are ChatGPT app conveniences and are not part of the API. On our site the same Sunburst model is available through the direct OpenAI API: text-to-image generation, reference-based editing (up to 16 images, 50 MB each — restoration, recoloring, background replacement, restyling), transparent backgrounds and five rendering levels. To restore or rework a photo on the site, simply attach it as a reference and write an instruction.

A separate hands-on case from the review is video thumbnails: the author assembles a catchy YouTube preview through a series of edits (a punchier background, a large subject, a readable look) — the same targeted-edit mechanics, only the goal is "clickable" rather than "pretty". On the site this task works the same way: attach a frame as a reference and add an instruction about the background and the accent.

Precision in the details

The second hallmark is prompt adherence down to small details: how many objects there are, on which side, what the clock reads, how many floors the building has. OpenAI's demo shows frames where the model reproduces several exact conditions from the description at once.

Native transparency out of the box

Both models in the family support native transparency: an object with a full alpha channel is instantly ready for collages, layouts or games — no manual cutouts. The demo shows an object composited onto new backgrounds.

On the site, pick the "Transparent" background mode and the PNG or WebP format (JPEG cannot store transparency — the form will hint at that).

How much it costs

OpenAI's token rates for 2.5 match the previous generation, and on the site the per-image price depends on the rendering level and canvas size — always shown before you hit generate. Drafts on low, finals on high and above. You pay in rubles from your internal balance; no subscription required.

Try it in the browser

The model is already live in the image generation studio: pick "ChatGPT Images 2.5" in the model list, describe the frame and attach references if needed. Open ChatGPT Images 2.5 on NeuralSpace.