For most product photography, start with Nano Banana 2.1, the successor to the Nano Banana 2 we tested: across our tests Nano Banana 2 was the reliable all-rounder for photoreal scenes and relighting, and it stayed closest to the source product in two of three same-SKU scenes. For the most premium hero shot of a glass, metal, fabric or other material-driven product, Seedream 4.5 won the most of our thirty category tests, at the lowest cost of the photoreal models. When label text has to come out legible, use GPT Image 2; it was also closest to the source when the product was held in a hand.
Those verdicts come from one output per model in each category test, plus 13 same-source outputs, so treat them as a starting shortlist. The question that decides a real listing is whether the model gives back your exact product, and no model kept exact geometry in our same-SKU runs. Run the shortlist on your own SKU before you scale.
How we tested: each of the thirty category tests holds one fictional product brief constant across four models and publishes one output per model. Some original prompts were not preserved and are shown as controlled reconstructions. The same-source results below use one real source image across five models. Neither set measures repeated-run acceptance rates.
Quick answer
- All-rounder for photoreal scenes and relighting: Nano Banana 2 in our tests; run its successor, Nano Banana 2.1, today. Closest to the source on the studio pedestal and the dark reflective set in our same-SKU runs.
- Premium material and macro hero shots, best value: Seedream 4.5. Won the most of our thirty category tests on glass, metal, fabric, fur and glaze. Weak on dense text.
- Legible label text and held-in-hand shots: GPT Image 2. Most reliable text in the category tests; closest to the source in the hand scene. Still composite approved regulated copy and barcodes from source artwork.
- Most polished look, with product drift: Nano Banana Pro and Seedream 5 Pro. Strong craft, but both changed the product more than the models above.
- Score product truth before craft: reject changed geometry, color, finish, labels, marks, quantity or variant before comparing lighting or mood, and measure accepted assets per attempt, not single generations.
Download the blank model benchmark scorecard
Download the four-route product-photo model scorecard. It is deliberately unscored: each row starts at NOT_RUN, so the template cannot smuggle invented performance into your decision. Replace the placeholders, keep the approved source set, scene brief, crop, output size, and four-candidate count fixed, then store every output in the matching evidence folder.
Calculate acceptance rate as accepted candidates divided by total candidates. Calculate total route cost as generation cost, external cost, and loaded review plus correction time. Divide that total by accepted candidates for cost per accepted asset. If a route accepts nothing, mark it failed instead of reporting a misleading zero-dollar result. A rejected candidate can trigger several failure classes, so identity, data, geometry, appearance, rights or marking, and claim counts do not have to sum to the number rejected.
The tested model shortlist
What each model's documentation says, and what our tests can and can't show about it. Masonry retired two of these in November 2026: Nano Banana 2 (replaced by Nano Banana 2.1) and FLUX.2 Pro (replaced by FLUX 3 Image). We have not rerun the corpus on either successor.
| Model used in the corpus | Current documented reason to test it | What the corpus can say | What it cannot say |
|---|---|---|---|
| Nano Banana 2 | Google's current guide calls Gemini 3.1 Flash Image its versatile workhorse, documents 512px through 4K output, and supports multi-reference workflows. | One fictional output per category exposes scene, detail, text, and design choices. | A repeated-run preservation rate or expected acceptance cost. |
| GPT Image 2 | OpenAI documents generation and editing, automatic high-fidelity processing of image inputs, and flexible output sizes up to a 3840px edge. | Some displayed text and structured elements are highly legible, including unsupported product data. | That legible copy is correct, or that the model preserves an uploaded SKU without review. |
| Seedream 4.5 | It is the Seedream version used for every linked category output, so it remains useful as a reproducible corpus baseline in Masonry. | The displayed outputs provide direct evidence of visual composition, material cues, and category-specific drift. | That it “wins” materials, optics, cost, or real-product fidelity; Seedream 5.0 Pro was not tested here. |
| FLUX.2 Pro | Black Forest Labs documents a production endpoint, up to ten references, and a fixed flux-2-pro snapshot for reproducible workflows. | The linked concepts reveal useful geometry, material, marking, and prompt-adherence checks. | That it is the cheapest usable workflow or takes more liberties across repeated SKU tests. |
Primary documentation: Google image generation, OpenAI image generation, and the FLUX.2 overview. Google shut down the Imagen 4 standard, Ultra, and Fast endpoints on August 17, 2026 and points users to Gemini 3.1 Flash Image.
Two outputs that explain the benchmark
These images do not prove that Seedream always makes these errors. They show why a single attractive output cannot be accepted without a source comparison.
The 30-category evidence map
| Product test | What the displayed test helps you inspect | What a real listing must source and verify |
|---|---|---|
| Skincare | Frosted glass, small label, cap, liquid and scene cues | Exact container, formula state, label, quantity, ingredients, claims, warnings, and variant |
| Jewelry | Stone presentation, setting contacts, band, reflection, view | Exact piece or disclosed representative design, stones, setting, metal, marks, condition, scale, and grading data |
| Supplements | Bottle, capsule, label and panel-like structure | Approved formula, Supplement Facts, ingredients, warnings, claims, code, lot area, and package |
| Makeup | Relative shade, finish, bullet, case, cap and invented marks | Formula, shade, color-managed capture, component, labels, swatch protocol, claims, variant, and assortment |
| Food & beverage | Serving scene, material, condensation, garnish and package cues | Exact food or beverage, quantity, ingredients, preparation, package, claims, condition, and serving truth |
| Footwear | Silhouette, multi-material construction, sole and marks | Exact upper, sole, stitching, colorway, size cues, condition, branding, variant, and pair consistency |
| Candles | Vessel, wax, wick, flame, glow and scene | Exact vessel, fill, wick count, label, scent variant, burn state, warnings, and safe-use claims |
| Clothing | Garment silhouette, print, fabric and styling | Exact cut, size, pattern or artwork, construction, material, color, fit, marks, and variant |
| Furniture | Form, room scale, materials, assembly and shadows | Exact dimensions, geometry, joins, hardware, finish, color, condition, configuration, and included parts |
| Electronics | Screen content, body, controls, finish and wear | Exact device, UI, controls, ports, sensors, marks, accessories, specs, compatibility, and safety evidence |
| Handbags | Silhouette, grain, stitching, hardware and color | Exact construction, material, lining, closure, hardware, marks, dimensions, variant, and condition |
| Sunglasses | Frame symmetry, lens appearance, hinges and reflection | Exact frame, lens, tint, coatings, marks, dimensions, fit, included case, and UV or safety claims |
| Glassware | Geometry, rim, stem, refraction, reflection and crop | Exact item or disclosed handmade range, set count, capacity, dimensions, marks, condition, and use claims |
| Flowers | Organic form, petal detail, arrangement and freshness cues | Exact arrangement or disclosed representative range, stem and bloom count, species, color, size, and condition |
| Watches | Dial, hands, indices, sub-dials, case, crown and strap | Exact watch, time or state, dial copy, movement-facing claims, dimensions, materials, marks, condition, and set |
| Perfume | Bottle geometry, glass, liquid, cap, label and reflection | Exact bottle, fill, color, cap, atomizer, label, volume, ingredients or warnings when shown, and variant |
| Packaging / CPG | Structure, panels, copy, codes, count and print appearance | Approved dieline, artwork, identity, quantity, ingredients, allergens, facts, claims, identifiers, and print proof |
| Pet products | Product form, animal interaction, fit and scene | Exact product, size, attachment, materials, animal-fit boundaries, warnings, included items, and claims |
| Toys | Part shapes, assembly cues, materials, marks and visual resemblance | Owned design, part inventory, count, assembly, age grading, warnings, safety evidence, package, and set |
| Textiles & bedding | Weave, drape, pattern, seams and pile | Exact pattern repeat, material, dimensions, construction, color-managed reference, variant, and set count |
| Cookware | Geometry, reflections, handles, lid and scene | Exact pan or set, dimensions, materials, coatings, hardware, marks, included items, condition, and use or safety claims |
| Stationery | Paper, foil, deboss, binding, text and layout | Exact artwork, copy, page or item count, dimensions, stock, finish, binding, personalization, and set |
| Drinkware | Shape, finish, lid, handle, reflection and marks | Exact vessel, capacity, dimensions, lid or straw, seals, material, color, marks, set, and use claims |
| Soap & bath | Bar shape, swirl, texture, cut and styled batch | Exact bar or disclosed batch range, dimensions, weight, formula, ingredients, label, variation, and claims |
| Ceramics | Form, handle, foot, glaze and firing variation | Exact piece or disclosed range, dimensions, capacity, weight, condition, glaze variation, marks, and food or heat claims |
| Art prints | Frame, mat, glass, glare, room scale and artwork placement | Exact owned artwork, crop, color, edition, dimensions, paper, frame, glazing, marks, and included items |
| Earbuds | Bud and case geometry, ports, seams, marks and resemblance | Exact buds, charging case, controls, indicators, accessories, specs, compatibility, safety evidence, and set |
| Houseplants | Species-like traits, foliage, pot, scale and condition | Exact stock or disclosed representative plant, species, size range, pot, condition, count, care, and toxicity claims |
| Knives & cutlery | Blade shape, pattern, bevel, handle and reflection | Exact blade and handle, dimensions, pattern, edge, marks, sheath or set, condition, materials, and safety claims |
| Automotive wheels | Spoke topology, rim, finish, marks and brake or tire context | Exact wheel, dimensions, PCD, bore, offset, load data, finish, marks, fitment, accessories, and safety evidence |
The recurring failure classes are now more useful than a model leaderboard:
- Identity drift: a plausible category object replaces the exact SKU.
- Data drift: text, UI, facts panels, barcodes, dials, warnings, ingredients, or specifications look authoritative without an approved source.
- Geometry drift: parts, prongs, spokes, handles, controls, seams, set count, and repeated structures change.
- Appearance drift: color, finish, texture, condition, natural variation, reflection, and transparency become a more idealized product.
- Rights and marking drift: logos, lettering, familiar configurations, certifications, or decorative marks appear without approval.
- Claim drift: pixels imply fitment, performance, safety, health, compatibility, material, capacity, or included features they cannot prove.
Same-source results: 13 outputs, five models
We also ran current models on one fixed source product in three scenes, with every output published in the same-SKU fidelity test. The short version:
| Scene | Outputs | Closest to the source | Most polished, with drift | Failed the brief |
|---|---|---|---|---|
| Neutral studio pedestal | 4 | Nano Banana 2 | Nano Banana Pro | Qwen Image Edit Plus |
| Dark reflective surface | 6 | Nano Banana 2 (3 of 3 core identity) | Seedream 5 Pro | GPT Image 2 (missed the dark set) |
| Held in a hand | 3 | GPT Image 2 | Nano Banana 2 | Qwen Image Edit Plus |
Every model kept the visible label words. None kept exact geometry, and 0 of 13 were approved as factual primary photography. Samples are one to three per model per scene, so read this as a starting shortlist, not a ranking.
Run your own benchmark
Use the same source set, prompt, ratio, and candidate count for every model, declare what cannot change before generating, review product truth blind before style, and compare cost per accepted asset. The fidelity test's workflow lays out the six steps.
# Originally run on gemini-3.1-flash-image-preview (Nano Banana 2), which Masonry retired in November 2026; gemini-nano-banana-2.1 replaced it. masonry image "Change only the environment to polished warm stone with soft camera-left light. Keep the supplied product's geometry, colors, materials, finish, marks, label, condition, quantity, crop, and perspective unchanged. Add no text, logo, feature, claim, prop, or extra product." \ --model gemini-nano-banana-2.1 \ --ref ./approved-product-three-quarter.png \ --aspect 1:1 masonry job wait <job-id> masonry job download <job-id> --output ./product-scene-candidate.png
When exactness dominates, generate the empty scene and composite the approved packshot. The background route test shows why: a general edit and a structured placement both changed the package, while a source-card route kept it. Fidelity approval only makes an image eligible to test against your current one; the AI product-photo trust test covers that control-versus-candidate plan.
Model notes without winner claims
Nano Banana 2
Masonry retired Nano Banana 2 in November 2026; Nano Banana 2.1 replaced it and keeps 1K to 4K output and up to 14 references. Google's guide positioned Gemini 3.1 Flash Image as a versatile workhorse with text-and-image editing, 1K through 4K output plus 512px, and multi-reference support. Those capabilities make it a sensible pilot candidate. They do not guarantee that ten supplied product views will all be preserved.
GPT Image 2
OpenAI documents generation, image edits, masks, automatic high-fidelity processing of image inputs, and flexible sizes. The category images show why legibility needs a second score: clean text, UI, or panels can still be entirely unsupported by product data.
Seedream 4.5
Seedream 4.5 is the fixed version represented across all thirty linked tests. It often provides useful scene and material directions in the displayed outputs, but the same corpus includes extra products, changed geometry, invented marks, and unsupported copy. Seedream 5.0 Pro exists but is outside this benchmark.
FLUX.2 Pro
Masonry retired FLUX.2 Pro in November 2026; FLUX 3 Image replaced it, with up to 10 references and output up to 4K. Black Forest Labs documents FLUX.2 Pro for production workflows, multi-reference editing, and a fixed endpoint for reproducibility. Reproducibility helps operations; it does not turn a fictional category result into evidence of SKU fidelity.
Bottom line
The thirty tests answer “what should I inspect?” much better than “which model wins?” Their first-hand images expose the category-specific places where visual plausibility outruns product truth. Use the map to build a rejection sheet, benchmark current models on approved sources, measure acceptance rather than showcase quality, and composite the real product when exactness dominates. The same-SKU product-fidelity test applies one exact source and fixed prompts across five current models in three scenes, including glass and reflective surfaces and a product held in a hand. The complete ecommerce image-set test shows the production handoff on one controlled source, including the accepted files and the geometry drift that kept them out of the factual-primary slot.
To turn a selected model into a repeatable production brief, use the 12 ecommerce product-photography prompts; each prompt separates immutable product truth from the scene and includes a merchant acceptance gate.
Before generating a gallery, turn the unanswered purchase questions into an ecommerce product photography shot list; its seven-slot manifest separates factual capture, controlled compositing, reviewed AI scenes, and rows that must stay blocked until product evidence exists.
Once one SKU passes that gate, use the three-SKU batch product-photography workflow to carry the approved recipe into a manifest, asynchronous jobs, separate product-truth and set-consistency review, and cost-per-accepted-image accounting before scaling the catalog.
Run the same controlled source through Masonry's AI product photography studio, or automate the candidate set and file naming with the Masonry CLI. The decision should come from your accepted assets, not this page's favorite model.
Once a pilot supplies a real acceptance rate, move the attempts, reviewer time, correction time, credits, and external spend into the AI product-photography cost calculator. It compares unlike production routes on the same accepted deliverable and translates project cost into a conservative break-even order threshold.
If the model comparison is only one part of a larger merchant job, use the AI for ecommerce workflow map to route catalog, PDP, acquisition, lifecycle, evidence, and wholesale work by its authority record and commercial finish line.
