Same Prompt, Three AI Image Generators: A Controlled 2026 Test

The short answer

We sent three unchanged English prompts to Nano Banana Pro, GPT Image 2, and Midjourney V8.2 on September 3, 2026. Each model got one portrait brief, one exact-text poster, and one three-panel character sheet. We accepted the first returned image instead of rerolling for a prettier result.

The useful finding is not a universal winner. It is a routing rule:

For the wider product and corpus context, read our 2026 AI image generator comparison. That article measures where thousands of gallery prompts were routed; this article measures what happened when the inputs were actually held constant.

Method: what we held constant

The run ID is 20260903t073722z-514b0ccedd. The checked-in manifest hash is 514b0cceddd25b65aff20462573dae0f5b7e19a2f0efcdd37c60c10f591783f7. Nine of nine planned jobs completed.

There is one unavoidable asymmetry worth making explicit: the Midjourney response exposed four candidate URLs for each job, while the other two routes exposed one. The runner automatically kept the first Midjourney URL; we did not inspect the other three and choose a winner. Raw provider sizes also differed before normalization, so this test is about composition, text, and visible instruction following—not a microscopic sharpness comparison.

Observed end-to-end job times ranged from 40.5 to 56.2 seconds, including provider polling. With only three calls per route and different serving mechanics, those timings are recorded for reproduction, not used to make a speed claim.

If you want to build your own test brief, the complete prompt-engineering guide explains how to separate subject, composition, light, and exclusions before the first run.

Test 1: a photoreal editorial portrait

Exact prompt

Create a vertical 3:4 photoreal editorial portrait of a fictional adult woman in her late twenties, seated beside a large north-facing window in a quiet apartment. She wears a plain charcoal knit top, looks directly into the camera with a calm, self-possessed expression, and has natural skin texture with fine facial detail. Use soft overcast daylight, gentle shadow falloff, a 50 mm documentary perspective, eye-level framing, restrained neutral colors, and subtle fine grain. Keep the setting believable and uncluttered. No visible words, logos, branded objects, celebrity likeness, fantasy elements, beauty-filter skin, or decorative border.

All three outputs show an adult woman seated beside a window, in a charcoal knit top, looking directly at the camera with a calm expression. All three also avoid visible words, logos, and borders. On those auditable pass/fail checks, this sample is a tie.

The difference is editorial taste. Nano Banana Pro pulled back far enough to make the quiet apartment part of the story and left the most everyday skin variation. GPT Image moved closer and sharpened the face and garment. Midjourney produced the most polished casting, shallowest-feeling background, and cleanest beauty-editorial finish. None of those is automatically “better.” If your layout needs room for copy, the wider Nano Banana result may be more useful; if the face is the asset, the tighter GPT Image or Midjourney framing may be preferable.

Most importantly, a single attractive face does not measure repeatability. For portrait constraints and reference-led work, pair this result with our consistent-character guide and Nano Banana vs Midjourney comparison.

Urban Still Shadow Crowd Flow

Nano Banana Pro

Prompt▾

Ultra-realistic cinematic street portrait of a young woman standing still in a crowded city street, sharp focus on her face with calm, intense expression. Long-exposure effect with people moving around her creating strong directional motion blur, streaked crowd movement while the subject remains perfectly still. Natural soft daylight, shallow depth of field, creamy bokeh, realistic skin texture, subtle freckles, neutral makeup, dark winter coat and scarf. Emotional, introspective mood, urban storytelling photography, DSLR quality, 85mm lens look, f/1.8, high dynamic range, 8K, professional color grading.

Copy

A real gallery portrait prompt that pins motion, light, and camera behaviour. It is useful writing evidence, but not part of the controlled run above.Open in LocalBanana

Controlled Gaze Under Dominant Flash

Nano Banana Pro

Prompt▾

Use reference image.
Preserve identity and facial structure strictly.

A slim Asian woman standing still, body deliberately composed rather than casual.
Her posture feels arranged and intentional, not relaxed.
She faces the camera directly, shoulders stable, center of gravity controlled.

Her expression is calm and restrained — not playful, not overly sweet.
A controlled, subtle smile, with emotional distance.
Her gaze is steady and aware, fixed toward the camera, creating quiet dominance rather than friendliness.

Hands & Props

Right hand holding a hanging cluster of golden trumpet flowers, positioned deliberately as a visual accent

Left hand holding a larger bouquet of golden trumpet flowers, lowered slightly

Flowers function as props only, never overpowering the subject

The woman remains the absolute visual focal point at all times

Hair

Long hair, slightly messy layered style

Hair gently lifted by wind, with a few loose strands crossing the face

Chic, slightly sexy, but controlled — never messy or cute

Outfit

White vintage-style puff-sleeve blouse

Large puffed sleeves

Layered ruffle cuffs

Square neckline

Drawstrings at the chest forming soft gathers

Slightly long length covering the hips

Front slit visible but restrained

Light blue jeans

Colorful beaded necklace as a subtle accent

Makeup

Fair skin tone

Douyin + Korean beauty inspired

Long curled eyelashes

Soft pink blush on cheeks and nose tip

Glossy pink-orange lips with juicy shine

Makeup feels polished and deliberate, not cute

Nails

White French tip nails

Subtle Christmas-themed nail art, low contrast

Environment

Standing directly in front of a fully blooming Golden Trumpet Tree (Thong Urai)

The tree is dense with bright golden flowers, forming a saturated backdrop

Some flower stems partially overlap the top edge of the frame, creating a soft foreground blur

Background exists to frame the subject, not to compete with her

Lighting (CRITICAL)

Direct flash is the dominant key light

Flash visibly overpowers ambient light

Skin appears very bright with slight yellow flash tone

Clear, hard-edged shadow cast behind the subject

Natural sunlight exists only as weak ambient fill

Lighting creates strong separation between subject and background

Photography Style

Compact camera aesthetic

Fujifilm Pro 400H film look

Vintage lens character

Subtle film grain

Ultra-sharp subject clarity

Bright exposure with aggressive subject emphasis

8K resolution

The image feels intentional, staged, and directed — not casual or spontaneous

Copy

A reference-led portrait brief from the gallery. Unlike the text-only test, its identity anchor comes from an input image.Open in LocalBanana

Test 2: an exact-text editorial poster

Exact prompt

Create a vertical 3:4 contemporary editorial poster on a warm off-white paper field. Set exactly the two-line headline "MAKE IDEAS" on line one and "VISIBLE" on line two, preserving spelling, capitalization, and word order. Use bold black grotesque lettering, a small cobalt-blue square, one thin vermilion rule, generous negative space, crisp alignment, and subtle printed-paper grain. The quoted headline must be the only readable text. Do not add a logo, signature, date, mockup frame, extra letters, or brand mark.

This is where “the text is correct” turns out to be too weak a criterion.

GPT Image passed all five visible checks. Nano Banana Pro preserved the exact copy and hierarchy but lost layout points by clipping the blue square at the left edge. Midjourney rendered every letter correctly—useful progress for a model often treated as typography-hostile—but it redesigned the hierarchy. For a mood board, that interpretation may be delightful. For a paid poster with an approved line break, it is a production failure.

This sample supports a narrow conclusion: exact characters and exact layout are different tests. Spellcheck the output, then separately check line breaks, countable graphic elements, margins, and forbidden additions. Our AI text-rendering benchmark expands this first poster into twelve controlled typography outputs.

GPT Image

Clean Modern YouTube Thumbnail

Nano Banana Pro

Premium Poster for Dan Dan Noodles

GPT Image

Futuristic Earbuds Ad

For more reusable starting points, browse GPT Image prompts and Nano Banana prompts before inserting your final copy.

Test 3: one courier across three panels

Exact prompt

Create one vertical 3:4 character-consistency sheet divided into three equal horizontal panels. Every panel must show the same fictional adult bicycle courier: age thirty, oval face, short wavy black hair, small scar through the left eyebrow, mustard rain jacket, navy trousers, and a plain silver helmet with no markings. Panel one is a front-facing waist-up portrait, panel two is a left-facing side profile holding the helmet, and panel three is a full-body view beside a simple unbranded bicycle. Keep facial identity, hair, clothing colors, and body proportions consistent across all three panels. Use clean overcast daylight and a restrained pale-gray studio background. No captions, words, logos, celebrity likeness, or extra people.

Nano Banana Pro followed the document structure most closely: three equal horizontal bands, front portrait, left-facing profile with helmet, then full body beside the bicycle. The face, hair, jacket, trousers, and helmet remain recognizably connected across the sheet. The tiny eyebrow scar is not reliably visible, so even the strongest result misses one identity anchor.

GPT Image also delivered three equal horizontal panels and the requested view sequence. Identity and wardrobe are coherent, but it introduced a black shoulder bag that was never requested, and the eyebrow scar is again not reliably present. Midjourney kept the mustard-and-navy courier concept and produced attractive, reasonably consistent illustration, yet replaced the specified horizontal sheet with an asymmetric comic-style collage. Its first pose is not the strict front-facing waist-up view requested.

There is also a prompt lesson hiding in Midjourney's output: we specified light and background but never explicitly said “photorealistic” in this third brief. The illustrated rendering is a legitimate use of the remaining freedom. When medium matters, lock it as a separate constraint instead of assuming the model will inherit it from a previous task.

Nano Banana Pro

One Image Generates 9 Different Shots

Nano Banana Pro

Pixar-Style 6-Panel Expression Grid

GPT Image

Cat-Eared Student Council Character Reference

Cinematic Photo Storyboard

Nano Banana Pro

Prompt▾

A 3x3 cinematic storyboard contact sheet consisting of 9 distinct panels arranged in a grid. The sequence features a young woman with platinum blonde hair in a frozen alpine winter setting.

The panels display various angles and shots:

Close-ups: Focusing on her rosy cheeks, blue-grey eyes, and snowflakes on her eyelashes.

Medium shots: Showing her wrapped in a black wool coat and blue knit scarf, holding a bouquet of dried white flowers.

Wide shots: Capturing her standing alone on the frozen lake with towering snowy mountains in the background.

The lighting is consistent moody blue-hour twilight across all frames. High-quality film photography aesthetic, photorealistic, 8k resolution, coherent character and color grading.

Copy

A gallery storyboard whose panels carry narrative order. It shows why panel roles should be named, not left as a generic request for a grid.Open in LocalBanana

The multi-panel image guide goes deeper on panel grammar, shot order, and attribute locks.

What this changes about model choice

This test makes three model-choice rules more precise:

1. For portraits, choose by art direction after basic compliance. All three cleared the visible brief, so the useful question is whether you want environmental documentary, polished realism, or beauty-editorial restraint.
2. For typography, score hierarchy separately from spelling. A poster can contain every correct letter and still be wrong.
3. For character sheets, specify the document before the character. Panel count, orientation, crop per panel, medium, and forbidden accessories belong in the hard-constraint block.

Do not generalize the result beyond the named routes and date. Model versions change, random variation is real, and three prompts cover only three production shapes. The defensible workflow is to use a comparison like this to choose two finalists, then run the exact asset you need in both.

You can copy one of the prompts above into the LocalBanana generator and compare a fresh run. If you want a style-led alternative, the Midjourney prompt library is more useful than pretending this small test has settled every creative task.

FAQ

Which AI image generator won this test?

No model won all three tasks. All three passed the portrait's visible hard constraints. Nano Banana Pro and GPT Image followed the poster layout more closely, while Nano Banana Pro followed the three-panel character brief most closely. That is a task-routing result, not an overall ranking.

Did you use exactly the same prompt for every model?

Yes. Within each task, the English prompt was byte-for-byte identical across the three routes. We did not translate, shorten, add Midjourney flags by hand, or write model-specific variants. The only provider-level differences were the recorded model routes and their native parameters.

Were the best images cherry-picked?

No. The runner accepted the first image URL returned by each route and made no rerolls. Midjourney exposed four candidate URLs while the other routes exposed one; the runner kept the first URL automatically rather than choosing among them.

Does this prove Nano Banana Pro is better than GPT Image 2 or Midjourney V8.2?

No. It proves only what is visible in these nine outputs from September 3, 2026. Estimating a reliable win rate would require many seeds per task, more task categories, blinded scoring, and repeated runs as versions change.

How should I run my own fair comparison?

Write the acceptance checks before generating. Freeze the exact prompt, input image, ratio, model version, and selection policy. Run every route once before rerolling, inspect hard constraints first, and only then judge aesthetics. Save the date and outputs so the conclusion remains auditable.