GPT Image 2 is OpenAI's image generation and editing model from before the GPT Image 2.5 line; Masonry also runs the newer GPT Image 2.5 Flare and GPT Image 2.5 Sunburst (compared below). OpenAI's model documentation lists text input, image input and output, image generation, image editing, flexible sizes, and high-fidelity image inputs. Its April 2026 launch emphasizes stronger instruction following, layouts, editing, and dense text.
Our verdict: start with GPT Image 2 when an image has to carry exact text or a layout. In our seven-region text test it rendered every character correctly, as did Nano Banana 2 and Seedream 5 Pro. In Masonry it accepts up to 10 reference images and 21 fixed sizes up to 3840 pixels but exposes no seed, so it suits one strong result better than repeatable batches. Below: the controls, one first-hand test, and a check to run on your own brief.
Current GPT Image 2 controls on Masonry
Run masonry models params gpt-image-2 before building a batch. At the time of this update, the route exposes:
| Input | Current contract | Production implication |
|---|---|---|
| Prompt | Required, up to 32,000 characters | Use the shortest brief that states the full acceptance criteria; capacity is not a target. |
| Output size | One of 21 fixed dimensions, up to 3840x2160 or 2160x3840 | Design for the final placement before generating rather than relying on an arbitrary canvas. |
| Reference images | Zero to 10; any reference switches the route to edit mode | Use clean sources and name what must stay unchanged. More references do not guarantee better fidelity. |
| Seed | Not exposed | Do not promise deterministic reruns from a seed. |
| Quality tier | Low, medium, or high; default low | Checked November 1, 2026. Draft at low, then rerun the chosen prompt at high for the final. |
| Mask | Route accepts an optional mask; no CLI flag in v1.1.26 | Checked November 1, 2026. Use it to limit an edit to one region instead of regenerating the frame. |
| Negative prompt | Not exposed | Put the desired visual state in the main prompt. |
The available sizes are 1024x1024, 1536x1024, 1024x1536, 1920x1080, 2560x1440, and 3840x2160. Aspect aliases map 1:1, 3:2, 2:3, and 16:9 to four of those sizes.
Evidence boundary: the poster below is one first-hand output from the exact prompt and current Masonry route described here. It is not a multi-seed benchmark, a comparison with other models, or proof that GPT Image 2 will preserve a real product. Official model capabilities are linked to OpenAI; Masonry-specific controls come from the live route contract checked August 4, 2026.
One first-hand text and product-layout test
We asked the live route for a fictional serum poster with exactly three strings: “NIGHT BLOOM,” “Barrier Serum,” and “30 mL.” The prompt required each string exactly once and prohibited other copy, logos, badges, prices, and claims.
Observed outcome: the candidate rendered all three required strings correctly once, introduced no extra copy, kept a coherent bottle and dropper, and placed the contact shadow to camera-right under the requested camera-left light. The hierarchy remains legible at the 2:3 crop. It also introduced decorative dried flowers and stones around the specified limestone setting; those were not prohibited, but they are a reminder to state an exact prop budget when the layout must stay minimal. Because the bottle is fictional, this run provides no evidence about preserving a real SKU.
Use this pass/fail sheet rather than treating a polished composition as sufficient:
| Check | Pass condition |
|---|---|
| Exact text | “NIGHT BLOOM,” “Barrier Serum,” and “30 mL” each appear once with no wrong character. |
| No invented copy | No extra benefit claim, ingredient, price, badge, brand mark, or legal line appears. |
| Product geometry | Bottle, cap, base, and contact with the surface are physically coherent. |
| Lighting | The bottle highlights and contact shadow agree with the stated camera-left source. |
| Layout | Headline, subheading, bottle, and volume line have a usable hierarchy at the intended crop. |
For a real SKU, add harder checks: compare silhouette, closure, fill level, exact label artwork, color, regulatory copy, and trademark use with the approved source. A generated near-match is still a failure when it misrepresents the product.
Generate and edit from the CLI
A text-only run uses the prompt, model, output size, and destination path:
masonry image "Premium editorial ecommerce poster for a cobalt-blue glass serum bottle. Exact headline: 'NIGHT BLOOM'. Exact subheading: 'Barrier Serum'. Exact small line: '30 mL'. Render each string exactly once. No other text." \ --model gpt-image-2 \ --aspect 2:3 \ --output night-bloom.png
To use the route's edit mode, attach a clean product reference and state the invariants:
masonry image "Place this exact bottle upright on pale limestone. Keep its silhouette, cap, cobalt color, and all label artwork unchanged. Add cool window light from camera-left and one natural contact shadow. Do not add or rewrite text." \ --model gpt-image-2 \ --ref ./approved-bottle.png \ --aspect 2:3 \ --output bottle-editorial.png
Reference-based generation is still generative. Review the output against the source; do not interpret “keep unchanged” as a product lock.
Prompt patterns that are easy to verify
Exact displayed copy
Put each required string in quotes, specify hierarchy, and prohibit other copy:
Headline: “SUMMER SET.” Subheading: “Three daily essentials.” Footer: “50 mL · 30 mL · 15 mL.” Render those strings exactly once. No other words, numbers, logos, prices, or badges.
Reject the output for one wrong character. For regulated, legal, price, ingredient, or fine-print copy, generate the visual without that text and add approved typography deterministically in a design tool.
Product reference edit
Separate what changes from what cannot:
Change only the environment to a pale limestone vanity with cool morning light. Keep the supplied bottle's silhouette, cap, proportions, cobalt color, label placement, and every printed character unchanged. No new props or copy.
If the product still drifts, the fix may be compositing the approved packshot rather than adding more prompt words.
Layout with usable negative space
State the intended placement and crop:
16:9 campaign hero. Product occupies the right 40% of the frame, fully visible, camera at product height. Keep the left 45% quiet and evenly lit for external typesetting. No text in the generated image.
This is more verifiable than asking for a “premium ad” and hoping the composition leaves room for the page.
GPT Image 2 or GPT Image 2.5?
OpenAI now offers two newer GPT Image models in Masonry: GPT Image 2.5 Flare, which OpenAI describes as its fastest for everyday work, and GPT Image 2.5 Sunburst, which it positions as its most capable for generation and precise editing. What we have seen first-hand:
- Text: both 2.5 models were exact on the same seven-region label prompt that GPT Image 2 passed, so text accuracy alone is not a reason to switch.
Here is that label prompt on all three, same wording at 1024×1024, one output each. GPT Image 2 ran on 4 August 2026 (top left in the first grid, beside other models from the same test); the two 2.5 models ran on 31 October 2026.
- Photoreal people: in our six-prompt photorealism test, Sunburst often added things the prompt did not ask for, including real brand logos on clothing in three of six images. Check every garment and prop before you publish.
- Choosing: try Flare when you need quick drafts, Sunburst when an edit has to be precise, and keep GPT Image 2 when your current prompts already pass review.
When to use another model
GPT Image 2 belongs on a shortlist; it is not a default winner for every task. Use the same brief across candidates when:
- photoreal material rendering matters more than displayed copy;
- a route with seed control is required for batch comparisons;
- the selected workflow needs a mask from the CLI, a negative-prompt field, or another input not exposed here;
- cost per accepted output matters more than one provider's headline price;
- identity or product consistency needs to be tested across many assets.
The text-rendering comparison, product-photography model guide, and GPT Image 2 vs FLUX test use task-specific evidence instead of assuming one universal winner.
The bottom line
GPT Image 2 is a current generation-and-editing option with strong official claims around instruction following, layouts, editing, and text. On Masonry, the useful facts are concrete: 21 fixed output sizes up to 3840 pixels, up to 10 references, low, medium, or high quality, an optional mask for edits, and no exposed seed or negative-prompt input in the checked route.
Write an observable brief, generate a bounded number of candidates, and inspect every required character and product detail. The winning model is the one that produces an accepted deliverable for your source, not the one with the strongest launch headline.
