ImageBench

ImageBench V1 —

192 evaluations across 6 categories

Benchmark V1 verdicts are produced by VLM judges and can contain mistakes. Treat PASS/FAIL labels as machine-assisted assessments, and inspect the images yourself. Learn more about the methodology.

Generation Details

Source-backed model context, size, cost, and request settings for this ImageBench V1 run.

local/krea-2-turbo-no-filter

Local

Krea 2 Turbo (no filter) is the distilled Krea 2 Turbo checkpoint run with a diff-patch LoRA that disables the model's built-in content filter, so it completes prompts the stock model would refuse — benchmarked here for comparison against stock Krea 2 Turbo.

Maker
Krea AI
Family
Krea 2 Open-Source
Model Size
12B
high
Cost
local run; no API price
not_applicable
Run Target
gx10/krea2-turbo-lora
Effective Request
response_format: b64_json · size: 1024x1024 · num_inference_steps: 8 · guidance_scale: 0
152
Pass
40
Fail
79%
Pass Rate
71.2s
Avg Latency
70.4s
Min Latency
71.5s
Max Latency
Text Rendering67%Spatial Reasoning84%Human realism88%Truthfulness70%Professional Studio93%Graphical design54%Latency0%

All 192 generations

Text Rendering

Spatial Reasoning

Human realism

Truthfulness

Professional Studio

Graphical design

Text Rendering 67%

Typography StyleClick to expand100%

Typography Style measures whether local/krea-2-turbo-no-filter preserves requested lettering styles, font mood, and text texture such as typewriter ink or neon signage.

Easy 100%
The word 'CHAPTER ONE' typed on aged paper with a vintage tyPASS
The word 'CHAPTER ONE' typed on aged paper with a vintage typewriter font, complete with slightly uneven ink

Evaluator (Qwen 3 VL)

Text reads “CHAPTER ONE” correctly. Font mimics vintage typewriter style with uneven, slightly smudged ink edges and consistent letterforms. Background shows aged paper texture. The style convincingly simulates typewritten text on old paper with intentional ink imperfections as requested. VERDICT: PASS

The phrase 'TODAY'S SPECIAL' written in white chalk on a darPASS
The phrase 'TODAY'S SPECIAL' written in white chalk on a dark green chalkboard with chalk dust

Evaluator (Qwen 3 VL)

Text reads "TODAY'S SPECIAL" correctly. Letters show convincing chalk texture, smudges, and uneven edges on dark green board. Chalk dust effect is visible. Medium matches prompt precisely. VERDICT: PASS

The word 'OPEN' displayed on a red LED sign with glowing pixPASS
The word 'OPEN' displayed on a red LED sign with glowing pixel-style letters

Evaluator (Qwen 3 VL)

The word "OPEN" is correctly spelled and rendered in a glowing, pixel-style LED format with distinct red dots forming each letter. The style convincingly mimics a classic LED sign with visible pixelation and ambient glow against a dark background. All visual elements align with the prompt’s description. VERDICT: PASS

Writing accuracyClick to expand58%

Writing accuracy measures whether local/krea-2-turbo-no-filter renders the exact requested words, numbers, labels, and short phrases without spelling or layout errors.

Easy 100%
A single large word 'HELLO' centered on a white backgroundPASS
A single large word 'HELLO' centered on a white background

Evaluator (Qwen 3 VL)

The word "HELLO" is fully spelled correctly and is clearly readable in bold black letters on a white background. All letters are intact and legible. No misspellings, missing words, or illegible parts are present. The text matches the intended specification exactly. VERDICT: PASS

The word 'ADVENTURE' in big bold letters centered on a plainPASS
The word 'ADVENTURE' in big bold letters centered on a plain cream background

Evaluator (Qwen 3 VL)

The word "ADVENTURE" is spelled correctly and fully readable in bold, centered text on a cream background. All letters are intact and clearly rendered. No misspellings or illegible parts detected. The design matches the intended specification precisely. VERDICT: PASS

The word 'SERENITY' written large and centered on a solid liPASS
The word 'SERENITY' written large and centered on a solid light blue background

Evaluator (Qwen 3 VL)

The word "SERENITY" is fully spelled correctly and is large, centered, and clearly readable against the solid light blue background. No misspellings, missing words, or illegible parts are present. All visual elements match the intended specification. VERDICT: PASS

Medium 33%
The sentence 'The quick brown fox jumps high' in clean blackPASS
The sentence 'The quick brown fox jumps high' in clean black text on a white background

Evaluator (Qwen 3 VL)

All words are spelled correctly and fully readable: "The", "quick", "brown", "fox", "jumps", "high". Text is clean black on white background. No misspellings or illegible parts. Matches intended text exactly. VERDICT: PASS

'Every sunset brings a new dawn ahead' written neatly on a pFAIL
'Every sunset brings a new dawn ahead' written neatly on a pale yellow background

Evaluator (Qwen 3 VL)

The word "sunset" is misspelled as "srigs". All other words are correctly spelled and fully readable. The intended phrase "Every sunset brings a new dawn ahead" is not accurately rendered. VERDICT: FAIL

'Stars shine brightest in the dark night' displayed on a cleFAIL
'Stars shine brightest in the dark night' displayed on a clean off-white background

Evaluator (Qwen 3 VL)

The text reads "Stars shine brightest in darknight" — "darknight" is incorrectly merged without a space. "darknight" should be "dark night". All other words are spelled correctly and fully readable. The intended phrase is not accurately rendered. VERDICT: FAIL

Hard 100%
A poster with headline 'SUMMER SALE' in large bold text, bodPASS
A poster with headline 'SUMMER SALE' in large bold text, body text 'Up to 50% off all items this weekend only' in medium size, and fine print 'Terms and conditions apply. See store for details.' at the bottom in small text

Evaluator (Qwen 3 VL)

All text matches the intended message exactly. "SUMMER SALE", "Up to 50% off all items this weekend only", and "Terms and conditions apply. See store for details." are all spelled correctly and fully readable. No misspellings or illegible parts detected. VERDICT: PASS

A flyer with large title 'GRAND OPENING', subtitle 'Join us PASS
A flyer with large title 'GRAND OPENING', subtitle 'Join us for food, music, and fun' in medium text, and small disclaimer 'RSVP required. Limited seating available.' at the bottom

Evaluator (Qwen 3 VL)

All text matches the intended message exactly. "GRAND OPENING" is correct. Subtitle "Join us for food, music, and fun" is fully readable. Bottom disclaimer "RSVP required. Limited seating available." is accurate and legible. No misspellings or missing words detected. VERDICT: PASS

An event banner with headline 'ANNUAL GALA 2025' at the top PASS
An event banner with headline 'ANNUAL GALA 2025' at the top in large serif font, description 'An evening of fine dining and live jazz' in medium text, and footnote 'Black tie optional. Doors open at 6 PM.' in small text

Evaluator (Qwen 3 VL)

All text matches the intended content exactly: "ANNUAL GALA 2025", "An evening of fine dining and live jazz", and "Black tie optional. Doors open at 6 PM." Every word is spelled correctly and fully readable, with no missing or illegible parts. Font styles are consistent with the description. VERDICT: PASS

Extreme 0%
A vintage movie poster for 'THE LAST VOYAGE' featuring a tagFAIL
A vintage movie poster for 'THE LAST VOYAGE' featuring a tagline 'One ship. One chance. No turning back.' with credits block reading 'Directed by James Harlow. Starring Elena Voss, Marcus Chen, and Sofia Reyes. Music by Thomas Grant. A Paramount Pict

Evaluator (Qwen 3 VL)

Text contains multiple errors: “VO YA GE” instead of “VOYAGE”; “MARCHS CHEN” (should be “Marcus Chen”); “NIK ANA VOSIC” (should be “Elena Voss”); “THARMAS GRANT” (should be “Thomas Grant”); “JOIE WOR” (should be “Jodie Wor”); “MOSE JEN VUKE” (should be “Mose Jen Vuke”); “SOUNDTRACK” misrendered. Many names and credits are illegible or garbled. VERDICT: FAIL

A magazine cover titled 'NATIONAL EXPLORER' with cover linesFAIL
A magazine cover titled 'NATIONAL EXPLORER' with cover lines 'The Hidden Temples of Cambodia — page 34', 'Interview: Dr. Maria Santos on Climate Action', 'Top 10 Trails You Must Hike This Year', and a barcode area with 'Issue 247 | March 2025 | $6.99

Evaluator (Qwen 3 VL)

“Cambania” is misspelled (should be “Cambodia”). All other text matches the intended content exactly, including the barcode details. The misspelling is a clear error affecting accuracy. VERDICT: FAIL

A product label for 'GOLDEN HARVEST ORGANIC HONEY' with subtFAIL
A product label for 'GOLDEN HARVEST ORGANIC HONEY' with subtitle 'Raw & Unfiltered', weight '12 oz (340g)', description 'Pure wildflower honey harvested from sustainable apiaries in the Pacific Northwest. No additives or preservatives.', and small te

Evaluator (Qwen 3 VL)

Text contains multiple errors: "Unfltetred" (misspelled), "feific" (should be "Pacific"), "Northelits" (should be "Northwest"), "addifities" (should be "additives"), "preserviaties" (should be "preservatives"). Weight "340g" is incorrect (should be 340g, but 340g is correct). "Product of USA" is correct. VERDICT: FAIL

Spatial Reasoning 84%

Attributes BindingClick to expand100%

Attributes Binding measures whether local/krea-2-turbo-no-filter attaches the right colors, materials, and properties to the correct requested objects.

Easy 100%
A red ball and a blue cube sitting side by side on a white sPASS
A red ball and a blue cube sitting side by side on a white surface

Evaluator (Qwen 3.5 122B)

The image shows two objects on a white surface. On the left is a red sphere (ball). On the right is a blue cube. Both objects are correctly colored and shaped as specified. They are positioned side by side. No attributes are swapped — red is bound to the ball, blue to the cube. Shapes and colors match the prompt exactly. VERDICT: PASS

A green apple and an orange pumpkin on a wooden cutting boarPASS
A green apple and an orange pumpkin on a wooden cutting board

Evaluator (Qwen 3.5 122B)

The image shows a green apple and an orange pumpkin on a wooden cutting board. The apple is correctly green, round, and has a stem. The pumpkin is correctly orange, round, and has a stem. All attributes (color, shape) are correctly bound to the respective objects with no swaps. VERDICT: PASS

A yellow taxi and a black limousine parked next to each othePASS
A yellow taxi and a black limousine parked next to each other on a street

Evaluator (Qwen 3.5 122B)

The image shows a yellow taxi in the foreground and a black limousine behind it, both parked on a street. The taxi is correctly colored yellow and has the typical sedan shape of a NYC cab. The limousine is black, elongated, and clearly a stretch vehicle. All attributes (color, size, shape) are correctly bound to each object with no swaps. VERDICT: PASS

Medium 100%
A large red circle, a small blue triangle, and a medium greePASS
A large red circle, a small blue triangle, and a medium green star arranged on a white canvas

Evaluator (Qwen 3.5 122B)

The image contains a large red circle as the background. On top of it, there is a small blue triangle on the left and a medium green star on the right. All attributes (color, size, shape) are correctly assigned to each object with no swaps. The white canvas is implied by the background surrounding the red circle. VERDICT: PASS

A tall thin white candle, a short fat red candle, and a mediPASS
A tall thin white candle, a short fat red candle, and a medium spiral yellow candle on a shelf

Evaluator (Qwen 3.5 122B)

The image shows three candles on a shelf: 1. Left: Tall, thin, white candle — matches description. 2. Center: Short, fat, red candle — matches description. 3. Right: Medium-height, spiral-shaped, yellow candle — matches description. All attributes (color, size, shape) are correctly bound to each object with no swaps. VERDICT: PASS

A big brown horse, a small white rabbit, and a medium-sized PASS
A big brown horse, a small white rabbit, and a medium-sized black cat standing in a meadow

Evaluator (Qwen 3.5 122B)

The image shows a big brown horse, a small white rabbit, and a medium-sized black cat in a meadow. All attributes match the prompt: the horse is large and brown, the rabbit is small and white, and the cat is medium-sized and black. No attribute swaps are present. The scene composition aligns with the requested description. VERDICT: PASS

Hard 100%
A pink fire truck, a blue banana, and a green sun in a surrePASS
A pink fire truck, a blue banana, and a green sun in a surreal landscape

Evaluator (Qwen 3.5 122B)

The image contains: - A pink fire truck (correct color, correct object) - A blue banana (correct color, correct object, oversized but still a banana) - A green sun (correct color, correct object, stylized with spikes) All attributes are correctly bound to their respective objects. No swaps or misattributions. The surreal scale is intentional per prompt. VERDICT: PASS

A purple carrot, a red tree with red leaves, and a white watPASS
A purple carrot, a red tree with red leaves, and a white watermelon sliced open

Evaluator (Qwen 3.5 122B)

The image shows: - A red tree with red leaves — correct. - A purple carrot with purple leafy top — correct. - A watermelon sliced open, with green rind, white rind layer, and pink flesh with black seeds — matches “white watermelon sliced open” if “white” refers to the rind layer (common in stylized art). All attributes are correctly bound; no swaps. Style is illustrative, not photorealistic, but prompt compliance is met. VERDICT: PASS

An orange elephant, a yellow penguin, and a silver strawberrPASS
An orange elephant, a yellow penguin, and a silver strawberry arranged on a table

Evaluator (Qwen 3.5 122B)

The image shows three objects on a wooden surface: 1. Orange elephant – correct color and shape. 2. Yellow penguin – correct color and shape. 3. Silver strawberry – correct color and shape, with green leaves. All attributes (color, shape) are correctly bound to the right objects. No swaps or mismatches observed. VERDICT: PASS

CompositionalityClick to expand100%

Compositionality measures whether local/krea-2-turbo-no-filter combines subjects, actions, outfits, props, and scene details into one coherent requested image.

Easy 100%
A tabby cat wearing oversized red sunglassesPASS
A tabby cat wearing oversized red sunglasses

Evaluator (Qwen 3.5 122B)

The image contains all described elements: 1. Tabby cat - Present (clear tabby markings on fur) 2. Oversized red sunglasses - Present (large red frames covering eyes) 3. Coherent combination - Present (glasses fit naturally on cat's face) All elements are clearly visible and properly integrated into a single, coherent image. VERDICT: PASS

A golden retriever wearing a tiny cowboy hatPASS
A golden retriever wearing a tiny cowboy hat

Evaluator (Qwen 3.5 122B)

The image shows a golden retriever with a small brown cowboy hat on its head. The hat has a braided band and sits naturally on the dog’s head. The dog is smiling, tongue out, in a grassy outdoor setting. All prompt elements — golden retriever, tiny cowboy hat, unusual combination — are present and coherently combined. VERDICT: PASS

A penguin holding a colorful umbrellaPASS
A penguin holding a colorful umbrella

Evaluator (Qwen 3.5 122B)

The image shows a penguin standing in snow under a blue sky with white dots (possibly snowflakes). The penguin is holding an umbrella with multiple bright colors — red, orange, yellow, green, purple, and blue — arranged in rainbow-like segments. The umbrella’s handle is orange and curved, held by the penguin’s flipper. All described elements — penguin, colorful umbrella, and their coherent combination — are clearly present and visually integrated. VERDICT: PASS

Medium 100%
A medieval knight in full armor sitting at a desk typing on PASS
A medieval knight in full armor sitting at a desk typing on a modern laptop

Evaluator (Qwen 3.5 122B)

The image shows a medieval knight in full armor sitting at a wooden desk, typing on a modern laptop. All described elements are present and coherently combined: - Medieval knight in full armor: Present - Sitting at a desk: Present - Typing on a modern laptop: Present The scene is well-integrated, with the knight’s hands positioned naturally on the laptop keyboard. VERDICT: PASS

A Roman gladiator taking a selfie with a smartphone in the CPASS
A Roman gladiator taking a selfie with a smartphone in the Colosseum

Evaluator (Qwen 3.5 122B)

The image contains all required elements: 1. Roman gladiator - Present (wearing authentic-looking armor, helmet with red crest, and red tunic) 2. Selfie action - Present (holding phone up in selfie pose) 3. Smartphone - Present (modern black smartphone with triple camera array) 4. Colosseum - Present (ancient Roman amphitheater structure visible in background) All elements are coherently combined in a single scene with proper lighting and perspective. The anachronistic combination is intentiona

An astronaut in a spacesuit riding a bicycle through a parkPASS
An astronaut in a spacesuit riding a bicycle through a park

Evaluator (Qwen 3.5 122B)

The image shows an astronaut in a full white spacesuit with helmet, patches (including U.S. flag), and life-support pack, riding a blue bicycle on a paved path. The background is a sunlit park with trees, grass, and dappled light — all consistent with the prompt. All elements are present and coherently combined: astronaut, spacesuit, bicycle, park setting. No contradictions or missing components. VERDICT: PASS

Hard 100%
An octopus wearing a top hat and monocle playing chess on thPASS
An octopus wearing a top hat and monocle playing chess on the surface of the moon with Earth visible in the background

Evaluator (Qwen 3.5 122B)

The image contains all described elements: - Octopus: Present, central figure - Top hat: Present, worn by octopus - Monocle: Present, on octopus's eye - Chess: Present, board with pieces in foreground - Moon surface: Present, gray rocky terrain - Earth in background: Present, visible in upper portion All elements are coherently combined in a surreal but visually consistent composition. VERDICT: PASS

A dinosaur in a business suit giving a PowerPoint presentatiPASS
A dinosaur in a business suit giving a PowerPoint presentation in a modern office while drinking coffee

Evaluator (Qwen 3.5 122B)

The image contains all described elements: 1. Dinosaur head (T-Rex style) - Present 2. Business suit - Present (blue suit with tie) 3. PowerPoint presentation - Present (on screen behind, though misspelled as "PowenPbnt") 4. Modern office setting - Present (desk, laptop, window) 5. Drinking coffee - Present (holding white coffee cup) All core elements are coherently combined in a single scene. The dinosaur is anthropomorphized as a businessman giving a presentation while holding coffee. VERDIC

A robot dressed as a pirate sailing a paper boat on a lake oPASS
A robot dressed as a pirate sailing a paper boat on a lake of lava while juggling three kittens

Evaluator (Qwen 3.5 122B)

The image contains: - Robot dressed as a pirate: Present (wearing pirate hat, coat, skull emblem) - Paper boat: Present (robot is seated in a brown paper boat) - Lake of lava: Present (glowing molten surface beneath the boat) - Three kittens: Present (one black, two tabby — all floating or perched around the robot) - Juggling: Not accurately depicted — kittens are not being juggled; they’re floating or standing statically. Core concept is visually represented but “juggling” is misinterpreted. S

CountingClick to expand78%

Counting measures whether local/krea-2-turbo-no-filter creates the exact number of requested objects without adding or missing items.

Easy 100%
Exactly 3 red apples arranged on a wooden tablePASS
Exactly 3 red apples arranged on a wooden table

Evaluator (Qwen 3.5 122B)

The image displays exactly three red apples with yellow streaks, each with a visible stem, arranged on a wooden surface. The count matches the prompt’s request for “exactly 3 red apples.” The setting is consistent with a wooden table. No extra or missing objects are present. VERDICT: PASS

Exactly 5 yellow rubber ducks sitting in a row on a bathroomPASS
Exactly 5 yellow rubber ducks sitting in a row on a bathroom shelf

Evaluator (Qwen 3.5 122B)

The image shows exactly five yellow rubber ducks arranged in a row on a white bathroom shelf. The background consists of tiled walls with a cracked-glaze pattern. All ducks are identical in appearance and orientation, facing forward. The count matches the prompt’s request precisely: five ducks, yellow, rubber-like, on a shelf, in a row. No extra or missing objects. VERDICT: PASS

Exactly 4 white candles standing on a dark surfacePASS
Exactly 4 white candles standing on a dark surface

Evaluator (Qwen 3.5 122B)

The image displays four white candles standing upright on a dark surface against a black background. Each candle is unlit, with visible wicks. The count of candles is exactly four, matching the prompt’s request. All objects are correctly rendered and positioned as described. VERDICT: PASS

Medium 100%
2 orange cats and 3 black dogs sitting together on a grassy PASS
2 orange cats and 3 black dogs sitting together on a grassy lawn

Evaluator (Qwen 3.5 122B)

The image shows exactly 2 orange cats in the front and 3 black dogs behind them, all sitting on a grassy lawn. The count matches the prompt’s request precisely: 2 cats and 3 dogs. No extra or missing animals are present. Composition is accurate to the description. VERDICT: PASS

4 red roses and 2 white daisies in a glass vase on a tablePASS
4 red roses and 2 white daisies in a glass vase on a table

Evaluator (Qwen 3.5 122B)

The image shows 4 red roses and 2 white daisies arranged in a clear glass vase on a light-colored surface (likely a table). The counts match the prompt exactly: 4 roses, 2 daisies, 1 vase, on a table. All requested elements are present and correctly counted. VERDICT: PASS

1 blue butterfly and 3 yellow butterflies resting on a gardePASS
1 blue butterfly and 3 yellow butterflies resting on a garden fence

Evaluator (Qwen 3.5 122B)

The image shows exactly 1 blue butterfly and 3 yellow butterflies resting on a wooden garden fence. The count matches the prompt’s request precisely: one blue, three yellow. All butterflies are positioned on or near the fence posts and rails, consistent with “resting on a garden fence.” No extra or missing butterflies are present. VERDICT: PASS

Hard 33%
Exactly 9 goldfish swimming in a large round fishbowlPASS
Exactly 9 goldfish swimming in a large round fishbowl

Evaluator (Qwen 3.5 122B)

The image shows a round fishbowl containing goldfish. Counting them: there are 9 distinct goldfish visible — 8 clearly in focus and one slightly blurred in the background near the bottom center. All appear to be swimming. The count matches the prompt’s request for “exactly 9 goldfish.” The bowl is large and round as described. VERDICT: PASS

A fruit bowl containing exactly 3 bananas, 4 oranges, and 2 FAIL
A fruit bowl containing exactly 3 bananas, 4 oranges, and 2 apples

Evaluator (Qwen 3.5 122B)

The image shows a fruit bowl with 3 bananas, 3 oranges, and 1 apple. The prompt requested 3 bananas (correct), 4 oranges (incorrect — only 3 visible), and 2 apples (incorrect — only 1 visible). Since the counts for oranges and apples do not match the request, the core criteria is not met. VERDICT: FAIL

Exactly 11 colorful balloons floating against a clear blue sFAIL
Exactly 11 colorful balloons floating against a clear blue sky

Evaluator (Qwen 3.5 122B)

The image shows a cluster of colorful balloons against a blue sky. Counting them: 1 yellow (top), 1 light blue, 1 pink, 1 orange (center), 1 red, 1 dark blue (front), 1 yellow (bottom right), 1 green, and 1 orange (left). That’s 9 balloons total. The prompt requested exactly 11. The count does not match. VERDICT: FAIL

NegationClick to expand44%

Negation measures whether local/krea-2-turbo-no-filter respects what should be absent from the image, not only what should be present.

Easy 67%
A tropical beach scene with no peoplePASS
A tropical beach scene with no people

Evaluator (Qwen 3.5 122B)

The image depicts a serene tropical beach scene featuring two palm trees in the foreground, golden sand, and turquoise ocean waters under a blue sky with scattered clouds. There are no people visible anywhere in the frame — no figures on the beach, in the water, or in the distance. The exclusion criterion (“no people”) is fully satisfied. VERDICT: PASS

A cat lying on a couch without a collarFAIL
A cat lying on a couch without a collar

Evaluator (Qwen 3.5 122B)

The image shows a cat lying on a couch, but it is wearing a red collar with a gold tag. Since the prompt explicitly excluded “a collar,” and one is clearly present, the excluded element is not absent. VERDICT: FAIL

A classroom with desks and a chalkboard but no studentsPASS
A classroom with desks and a chalkboard but no students

Evaluator (Qwen 3.5 122B)

The image shows an empty classroom with rows of wooden desks and chairs facing a green chalkboard. There are no students visible in the room. The scene is quiet and unoccupied, matching the prompt’s exclusion criteria. All elements align with the description: desks, chalkboard, no students. VERDICT: PASS

Medium 33%
A sandy beach with palm trees, seashells, and a beach umbrelPASS
A sandy beach with palm trees, seashells, and a beach umbrella but no water or ocean visible

Evaluator (Qwen 3.5 122B)

The image shows a sandy beach in the foreground with a pile of seashells. In the midground, there is a white beach umbrella and several palm trees with green foliage. The background consists of more trees and a clear blue sky. There is no visible water, ocean, or sea anywhere in the frame — the horizon is formed entirely by vegetation and sky. The excluded element (water/ocean) is truly absent. VERDICT: PASS

An office workspace with a desk, chair, bookshelf, and lamp FAIL
An office workspace with a desk, chair, bookshelf, and lamp but no computers or screens

Evaluator (Qwen 3.5 122B)

The image clearly shows a computer monitor on the desk, along with a keyboard and mouse — all of which are computer-related elements. The prompt explicitly excluded “computers or screens,” yet a screen (monitor) is prominently present. Therefore, the excluded element is not absent. VERDICT: FAIL

A kitchen with pots, pans, a stove, and a cutting board but FAIL
A kitchen with pots, pans, a stove, and a cutting board but no food

Evaluator (Qwen 3.5 122B)

The image shows a kitchen scene with pots, pans, a stove, and a cutting board — as expected. However, there is clearly food present: shredded orange carrots on the cutting board, and cooked food (possibly pasta or stew) in two of the pans on the stove. Since the prompt explicitly excluded “no food,” and food is visibly present, the exclusion criterion is violated. VERDICT: FAIL

Hard 33%
A pepperoni pizza with tomato sauce, basil, and crust but abFAIL
A pepperoni pizza with tomato sauce, basil, and crust but absolutely no cheese

Evaluator (Qwen 3.5 122B)

The image shows a pepperoni pizza with visible melted cheese covering the surface beneath the toppings. The prompt explicitly excluded cheese ("absolutely no cheese"), but cheese is clearly present in the image — it’s melted, golden, and covers most of the pizza base. Therefore, the excluded element is not absent. VERDICT: FAIL

A car body with windows, doors, and headlights but no wheelsPASS
A car body with windows, doors, and headlights but no wheels

Evaluator (Qwen 3.5 122B)

The image shows a car body with windows, doors, and headlights. The wheels are indeed absent — the wheel wells are empty, exposing the inner structure where tires would normally be mounted. This matches the exclusion criteria specified in the prompt. No wheels are visible anywhere in the frame. VERDICT: PASS

A human face with eyes, nose, and mouth but no eyebrowsFAIL
A human face with eyes, nose, and mouth but no eyebrows

Evaluator (Qwen 3.5 122B)

The image shows a close-up of a human face with eyes, nose, and mouth area visible. However, eyebrows are clearly present above both eyes — they are natural-looking, with individual hairs and defined arches. Since the prompt explicitly excluded eyebrows, and they are visibly present in the image, the exclusion criterion is violated. VERDICT: FAIL

Relative PositionClick to expand100%

Relative Position measures whether local/krea-2-turbo-no-filter places objects in the requested spatial relationship, such as above, below, inside, or next to another object.

Easy 100%
A cat sitting on top of a cardboard boxPASS
A cat sitting on top of a cardboard box

Evaluator (Qwen 3.5 122B)

The image shows a cat sitting directly on top of a cardboard box. The cat is centered on the box’s upper surface, with its paws resting on the box and its body elevated above it. The box is positioned in the corner of a room, against two walls. All spatial relationships described — “on top of” — are accurately represented. VERDICT: PASS

A red ball underneath a wooden chairPASS
A red ball underneath a wooden chair

Evaluator (Qwen 3.5 122B)

The image shows a red ball positioned directly beneath the seat of a wooden chair, resting on the floor between the chair’s legs. The spatial relationship “underneath” is accurately depicted — the ball is clearly below the chair structure and not beside or above it. All described positional relationships are correct. VERDICT: PASS

A coffee mug next to an open book on a deskPASS
A coffee mug next to an open book on a desk

Evaluator (Qwen 3.5 122B)

The image shows a coffee mug and an open book on a wooden surface (desk). The mug is positioned to the left of the book, slightly behind it, with both resting on the desk. The spatial relationships described in the prompt — “next to” and “on a desk” — are accurately represented. No incorrect positional terms (like “under” or “above”) are violated. VERDICT: PASS

Medium 100%
A bird perched on a branch, the branch extending from a treePASS
A bird perched on a branch, the branch extending from a tree next to a park bench

Evaluator (Qwen 3.5 122B)

The image shows a bird perched on a branch that extends from a tree trunk on the right side of the frame. Below and to the left of the branch is a park bench situated on a path. The spatial relationships described — bird on branch, branch extending from tree, tree next to bench — are all accurately represented in the image. VERDICT: PASS

A cat sitting on a pillow, the pillow placed on a wooden chaPASS
A cat sitting on a pillow, the pillow placed on a wooden chair

Evaluator (Qwen 3.5 122B)

The image shows a cat lying on a pillow, which is placed on a wooden chair. The spatial relationships described in the prompt are accurately represented: the cat is on the pillow, and the pillow is on the chair. All positional relationships are correct. VERDICT: PASS

A candle on top of a stack of books, the books next to a potPASS
A candle on top of a stack of books, the books next to a potted plant

Evaluator (Qwen 3.5 122B)

The image shows a lit candle in a glass holder placed directly on top of a stack of three books. To the left of the book stack is a potted plant with green leaves in a terracotta pot. All specified spatial relationships — “candle on top of books” and “books next to potted plant” — are accurately depicted. The arrangement matches the prompt’s description precisely. VERDICT: PASS

Hard 100%
Five chess pieces on a board: a king in the center, a queen PASS
Five chess pieces on a board: a king in the center, a queen to its left, a bishop to its right, a rook above the king, and a knight below the king

Evaluator (Qwen 3.5 122B)

The image shows five black chess pieces on a checkered board. The king is centered. To its left is the queen. To its right is the bishop. Above the king is the rook. Below the king is the knight. All spatial relationships described in the prompt are accurately represented in the image. VERDICT: PASS

A desk scene: laptop in the center, coffee mug to the left, PASS
A desk scene: laptop in the center, coffee mug to the left, phone to the right, lamp above, and notebook below

Evaluator (Qwen 3.5 122B)

The image shows a desk scene with a laptop centered, a coffee mug to its left, and a phone to its right — all matching the prompt. The lamp is positioned above and to the right of the laptop, casting light downward, which satisfies “lamp above.” The notebook lies directly below the laptop on the desk surface, fulfilling “notebook below.” All specified spatial relationships are accurately represented. VERDICT: PASS

Five animals in a field: a horse on the far left, a cow to tPASS
Five animals in a field: a horse on the far left, a cow to the right of the horse, a sheep in the center, a goat to the right of the sheep, and a dog on the far right

Evaluator (Qwen 3.5 122B)

The image shows five animals arranged in a field. From left to right: a brown horse is on the far left; next to it (to its right) is a brown-and-white cow; in the center is a fluffy sheep; to the right of the sheep is a white goat with curved horns; and on the far right sits a tricolor dog. All specified spatial relationships — “on the far left,” “to the right of,” “in the center” — are accurately represented. VERDICT: PASS

Extreme 100%
A landscape with a red barn in the foreground at large scalePASS
A landscape with a red barn in the foreground at large scale, a windmill in the midground at medium scale, and snow-capped mountains in the background at small scale, all with consistent depth perspective

Evaluator (Qwen 3.5 122B)

The image shows a red barn in the foreground on the right, a windmill to its left in the midground, and snow-capped mountains in the background. The spatial arrangement matches the prompt: barn (foreground, large), windmill (midground, medium), mountains (background, small). Depth perspective is consistent. All positional relationships are correctly represented. VERDICT: PASS

A beach scene with a sandcastle in the foreground, a surfer PASS
A beach scene with a sandcastle in the foreground, a surfer on the waves in the midground, and a cruise ship on the horizon in the background, sizes decreasing with distance

Evaluator (Qwen 3.5 122B)

The image correctly depicts a beach scene with a sandcastle in the foreground, a surfer riding waves in the midground, and a cruise ship on the horizon in the background. The sizes of the objects decrease appropriately with distance, maintaining proper spatial relationships as described. All positional relationships are accurate. VERDICT: PASS

A city park with a park bench and pigeons in the foreground,PASS
A city park with a park bench and pigeons in the foreground, a fountain in the midground, and skyscrapers in the background, each layer progressively smaller

Evaluator (Qwen 3.5 122B)

The image shows a park bench in the foreground with pigeons perched on it and on the ground around it. A fountain is visible in the midground, centered behind the bench. Skyscrapers rise in the background, appearing progressively smaller due to perspective. All spatial relationships described — foreground (bench/pigeons), midground (fountain), background (skyscrapers) — are accurately represented. No positional errors detected. VERDICT: PASS

Scale & ProportionsClick to expand78%

Scale & Proportions measures whether local/krea-2-turbo-no-filter keeps people, vehicles, buildings, and everyday objects at believable relative sizes.

Easy 67%
A person standing next to a yellow school bus, showing realiPASS
A person standing next to a yellow school bus, showing realistic relative scale

Evaluator (Qwen 3.5 122B)

The person’s height relative to the bus appears realistic — roughly 1/3 to 1/4 of the bus’s height, which is consistent with real-world proportions. The bus’s windows, door, and wheel are scaled appropriately for a standard school bus. No obvious distortions or size inconsistencies are visible. The perspective and shadows also support correct spatial relationships. VERDICT: PASS

A ladybug sitting on a large green leaf, shown at realistic PASS
A ladybug sitting on a large green leaf, shown at realistic proportions

Evaluator (Qwen 3.5 122B)

The ladybug appears appropriately sized relative to the leaf it is resting on. The leaf’s veins, serrated edges, and fine hairs are rendered at a scale consistent with macro photography of a real leaf. The ladybug’s body segments, legs, and spots are proportionally accurate for a typical seven-spotted ladybug. No elements appear unnaturally enlarged or shrunk. VERDICT: PASS

A child holding a basketball, both at correct relative sizesFAIL
A child holding a basketball, both at correct relative sizes

Evaluator (Qwen 3.5 122B)

The image shows a child holding a basketball. The ball appears disproportionately large relative to the child’s torso and hands — it nearly spans the width of their chest and is held with both hands in a way that suggests it’s too big for a typical child. In reality, a standard basketball (size 7) is about 29.5 inches in circumference; even a youth-sized ball (size 6 or 5) would not appear this oversized on a child. The proportions are inconsistent with real-world scale. VERDICT: FAIL

Medium 100%
A tiny person standing on the rim of a coffee cup, looking dPASS
A tiny person standing on the rim of a coffee cup, looking down into it

Evaluator (Qwen 3.5 122B)

The image shows a miniature person standing on the rim of a coffee cup, which aligns with the prompt’s description of size relationships. The person is appropriately scaled relative to the cup — tiny enough to appear as if they could stand on its edge, yet detailed enough to be clearly visible. The proportions are consistent and visually coherent. VERDICT: PASS

A giant tabby cat walking between city skyscrapers like a kaPASS
A giant tabby cat walking between city skyscrapers like a kaiju

Evaluator (Qwen 3.5 122B)

The image shows a tabby cat that is significantly larger than the surrounding skyscrapers, consistent with the "giant" and "kaiju" description. The cat’s paws are on the street level, towering over cars and buildings. The perspective and scale are intentionally exaggerated to match the prompt’s requirement for a giant cat among city structures. All size relationships align with the described concept. VERDICT: PASS

A miniature house sitting on the palm of someone's handPASS
A miniature house sitting on the palm of someone's hand

Evaluator (Qwen 3.5 122B)

The image shows a small house model resting on an open human palm. The house is appropriately scaled to fit comfortably within the hand, with its width spanning roughly the breadth of the palm and its height proportionate to the fingers. The perspective and depth of field support the miniature scale. No anatomical or proportional inconsistencies are visible. VERDICT: PASS

Hard 67%
A group photo of an elephant, a horse, a dog, a cat, and a mFAIL
A group photo of an elephant, a horse, a dog, a cat, and a mouse, all standing in a line with correct real-world proportional sizes

Evaluator (Qwen 3.5 122B)

The image shows an elephant, a horse, and two cats — but no dog or mouse as specified in the prompt. Additionally, while the elephant and horse are proportionally large relative to the cats, the absence of required animals (dog, mouse) means the core criteria of “correct real-world proportional sizes” for all listed species is not met. The composition also lacks a true “line” arrangement. VERDICT: FAIL

A dinner table scene with a plate, fork, knife, wine glass, PASS
A dinner table scene with a plate, fork, knife, wine glass, salt shaker, and peppercorn, all at realistic relative sizes

Evaluator (Qwen 3.5 122B)

The image shows a table setting with a plate, fork, knife, wine glass, salt shaker, and peppercorn shaker. The relative sizes appear realistic: the plate is appropriately large compared to the cutlery, the wine glass is proportionate to the plate, and the shakers are smaller than the plate but larger than the cutlery handles. All objects maintain consistent and believable scale relationships typical of a real dining setup. VERDICT: PASS

A farm scene with a barn, tractor, farmer, cow, chicken, andPASS
A farm scene with a barn, tractor, farmer, cow, chicken, and a fence post, all at correct proportional scale

Evaluator (Qwen 3.5 122B)

The image shows a farm scene with a red barn, tractor, farmer, cow, chicken, and fence post. The cow is large relative to the farmer, which is realistic. The tractor is appropriately sized compared to the barn and farmer. The chicken is small in front of the cow, and the fence post in the foreground appears correctly scaled for its proximity. All objects maintain plausible proportional relationships. VERDICT: PASS

Human realism 88%

Faces & ExpressionsClick to expand83%

Faces & Expressions measures whether local/krea-2-turbo-no-filter creates realistic faces with the requested age, emotion, expression, and identity cues.

Easy 100%
A close-up portrait of a young woman with a warm natural smiPASS
A close-up portrait of a young woman with a warm natural smile

Evaluator (Qwen 3 VL)

Face is symmetric with natural features; eyes, nose, and mouth are proportionate. Warm, genuine smile is clearly readable with crinkled eyes and relaxed cheeks. No noticeable distortions. Lighting and skin texture appear authentic. Matches prompt well. VERDICT: PASS

A portrait of a middle-aged man with a calm, serious expressPASS
A portrait of a middle-aged man with a calm, serious expression

Evaluator (Qwen 3 VL)

Face is symmetric with natural, correctly proportioned features. Expression conveys calm seriousness with subtle brow lines and neutral mouth. No visible distortions or artifacts. Lighting and texture appear realistic. Meets all criteria for the prompt. VERDICT: PASS

A headshot of a teenager with a relaxed, neutral facePASS
A headshot of a teenager with a relaxed, neutral face

Evaluator (Qwen 3 VL)

The face is symmetric with correctly proportioned features. Eyes, nose, and mouth are aligned naturally. The expression is relaxed and neutral, with no discernible distortions. Skin texture and lighting appear realistic. The subject appears to be a teenager. All requested criteria are met. VERDICT: PASS

Medium 67%
A close-up of a person's face showing clear disgust, nose wrFAIL
A close-up of a person's face showing clear disgust, nose wrinkled and lip curled

Evaluator (Qwen 3 VL)

Face is asymmetric with distorted features: eyes squinted unevenly, nose slightly crooked, and lips curled asymmetrically. Skin texture appears overly wrinkled and unnatural. Disgust is clearly conveyed via wrinkled nose and curled lips, but anatomical distortions compromise realism. VERDICT: FAIL

A portrait capturing genuine surprise — raised eyebrows, widPASS
A portrait capturing genuine surprise — raised eyebrows, wide eyes, slightly open mouth

Evaluator (Qwen 3 VL)

Face is symmetric with correctly rendered features. Eyes are wide, eyebrows raised, and mouth slightly open — clearly conveying genuine surprise. No significant distortions or anatomical errors. Expression is vivid and emotionally readable. VERDICT: PASS

A face showing quiet melancholy — downcast eyes, slightly drPASS
A face showing quiet melancholy — downcast eyes, slightly drawn mouth, distant gaze

Evaluator (Qwen 3 VL)

Face is symmetric with natural, correctly rendered features. Eyes are downcast, lips slightly drawn, and gaze distant — clearly conveying quiet melancholy. No visible distortions. Lighting and texture are realistic. Emotion is unmistakably readable and aligned with the prompt. VERDICT: PASS

Hard 100%
An elderly woman in her 80s with deep wrinkles and white haiPASS
An elderly woman in her 80s with deep wrinkles and white hair, smiling warmly with kind eyes

Evaluator (Qwen 3 VL)

The face is symmetric with natural, aged features: deep wrinkles, white hair, and warm, kind eyes. The smile is clearly readable and genuine, conveying warmth. No distortions are present; details like skin texture and lighting are realistic. The image accurately fulfills the prompt’s requirements. VERDICT: PASS

A 5-year-old child with round cheeks and large eyes, crying PASS
A 5-year-old child with round cheeks and large eyes, crying with tears streaming down their face

Evaluator (Qwen 3 VL)

The child’s face is symmetric with round cheeks and large, expressive eyes. Tears stream visibly down both cheeks, clearly conveying crying. Features are proportionate and well-defined, with no noticeable distortions. The emotion is unmistakably sad and tearful, matching the prompt. VERDICT: PASS

An elderly man in his 70s with age spots and thinning gray hPASS
An elderly man in his 70s with age spots and thinning gray hair, looking skeptically over reading glasses

Evaluator (Qwen 3 VL)

Face is symmetric with natural wrinkles, age spots, and thinning gray hair. Reading glasses are present. Skeptical expression is clearly readable via furrowed brow and downturned mouth. No significant distortions. Features align well with prompt. VERDICT: PASS

Extreme 67%
A group of three friends at a table: one laughing with head PASS
A group of three friends at a table: one laughing with head tilted back, one looking shocked with wide eyes, and one rolling their eyes with a smirk

Evaluator (Qwen 3 VL)

Faces are symmetric with correct anatomical features. Emotions are clearly readable: left person laughs with head back, center looks shocked with wide eyes and hands to face, right person smirks with rolled eyes. No distortions or unnatural artifacts. All three expressions match the prompt accurately. VERDICT: PASS

A family photo with four people: a father beaming with pridePASS
A family photo with four people: a father beaming with pride, a mother smiling gently, a teenager looking bored, and a child grinning excitedly

Evaluator (Qwen 3 VL)

Faces show natural symmetry and correct anatomical features. Emotions are clearly readable: father beams, mother smiles gently, teenager looks bored, child grins excitedly. No significant distortions or artifacts. All four individuals match the prompt’s emotional descriptions accurately. VERDICT: PASS

Three coworkers in a meeting: one looking frustrated with fuFAIL
Three coworkers in a meeting: one looking frustrated with furrowed brows, one nodding with a pleased expression, and one looking confused with a tilted head

Evaluator (Qwen 3 VL)

Faces are symmetric with correct features. The left woman shows frustration (furrowed brows). The man in center has a neutral, focused expression, not pleased. The right woman appears confused (tilted head), but her expression is ambiguous. The "pleased" emotion is missing. Facial distortions are minimal. VERDICT: FAIL

Full BodyClick to expand100%

Full Body measures whether local/krea-2-turbo-no-filter renders full-body people with natural anatomy, clothing, pose, and proportions.

Easy 100%
A woman standing upright in a relaxed pose, arms at her sidePASS
A woman standing upright in a relaxed pose, arms at her sides, wearing jeans and a white t-shirt

Evaluator (Qwen 3 VL)

The woman stands upright with arms at her sides, wearing a white t-shirt and jeans as described. Limb count and proportions are anatomically correct. The pose is clearly recognizable as relaxed and upright. No distortions are visible. All elements match the prompt accurately. VERDICT: PASS

A man standing straight facing the camera, hands in pockets,PASS
A man standing straight facing the camera, hands in pockets, normal proportions

Evaluator (Qwen 3 VL)

The man stands straight, facing forward, with hands in pockets. Limb count and proportions are anatomically correct. The pose is clearly recognizable as requested. No distortions are visible. All elements match the prompt precisely. VERDICT: PASS

A person standing in a neutral pose in a park, full body visPASS
A person standing in a neutral pose in a park, full body visible from head to feet

Evaluator (Qwen 3 VL)

The figure shows a full-body view in a park, standing neutrally with arms at sides. Limb count and proportions appear anatomically correct. Pose is recognizable as standing still. No major distortions are visible. Clothing and background details are coherent. VERDICT: PASS

Medium 100%
A woman mid-stride running through a park, hair and clothes PASS
A woman mid-stride running through a park, hair and clothes showing motion

Evaluator (Qwen 3 VL)

The woman’s limbs and proportions are anatomically correct. Her running pose is dynamic and recognizable, with arms swinging and legs mid-stride. Hair and clothing show motion blur, matching the prompt. No distortions are evident. VERDICT: PASS

A man captured mid-jump over a puddle, body in the air with PASS
A man captured mid-jump over a puddle, body in the air with bent knees

Evaluator (Qwen 3 VL)

The man’s limbs are correctly counted and proportioned. His pose—bent knees, mid-air jump over a puddle with visible splash—is anatomically plausible and matches the prompt. No distortions are evident. The action is clearly recognizable as jumping over water. VERDICT: PASS

A dancer in a dynamic spin, dress flowing outward with one lPASS
A dancer in a dynamic spin, dress flowing outward with one leg extended

Evaluator (Qwen 3 VL)

The dancer’s limbs are correctly proportioned and count is accurate. The pose—dynamic spin with one leg extended and dress flowing—is anatomically plausible and recognizable. No distortions are evident; musculature, joints, and motion are natural. The action matches the prompt precisely. VERDICT: PASS

Hard 100%
A person in a yoga tree pose — standing on one leg with the PASS
A person in a yoga tree pose — standing on one leg with the other foot pressed to the inner thigh, arms raised overhead

Evaluator (Qwen 3 VL)

The pose is recognizable as tree pose: one leg stands firmly, the other foot rests on the inner thigh, and arms are raised overhead. Limb count and proportions are anatomically correct. No distortions are visible. The pose is executed with proper alignment and balance. VERDICT: PASS

A rock climber clinging to a cliff face with arms and legs ePASS
A rock climber clinging to a cliff face with arms and legs extended to different holds

Evaluator (Qwen 3 VL)

The climber has two arms and two legs, with proportions and limb placement consistent with human anatomy. Her pose—arms extended to holds, legs positioned for balance—is recognizable as a standard climbing stance. No significant distortions are visible. The action matches the prompt precisely. VERDICT: PASS

A cellist seated with correct posture, legs around the instrPASS
A cellist seated with correct posture, legs around the instrument, bow arm extended

Evaluator (Qwen 3 VL)

The cellist’s posture and limb count are anatomically correct. The instrument rests between legs, bow arm extended, and hands positioned for playing. Proportions are natural, with no visible distortions. The pose accurately reflects standard cello playing posture. All elements of the prompt are faithfully rendered. VERDICT: PASS

Extreme 100%
Two tango dancers in a close embrace, the man dipping the woPASS
Two tango dancers in a close embrace, the man dipping the woman backward with intertwined legs

Evaluator (Qwen 3 VL)

The dancers’ limbs are correctly counted and proportioned. The woman’s legs are intertwined with the man’s, and her body is arched backward in a classic tango dip. The pose is anatomically plausible and recognizable as a tango embrace. No significant distortions are visible. VERDICT: PASS

Two soccer players mid-tackle, one sliding and the other jumPASS
Two soccer players mid-tackle, one sliding and the other jumping over with the ball at their feet

Evaluator (Qwen 3 VL)

Both players show correct limb count and proportions. The sliding player’s pose is anatomically plausible, and the jumping player’s posture is dynamic and realistic. The ball is at the jumping player’s feet, matching the prompt. No significant distortions are visible. The action is clearly recognizable as a mid-tackle scenario. VERDICT: PASS

Two gymnasts performing a synchronized handstand, side by siPASS
Two gymnasts performing a synchronized handstand, side by side with identical body alignment

Evaluator (Qwen 3 VL)

Both gymnasts show correct limb count and proportions. Their synchronized handstand pose is anatomically accurate and recognizable. Limbs are straight, feet together, wrists properly positioned. No distortions; bodies are symmetrical and aligned as described. The action is clearly a synchronized handstand. VERDICT: PASS

HandsClick to expand75%

Hands measures whether local/krea-2-turbo-no-filter draws anatomically plausible hands, fingers, and gestures.

Easy 33%
A person standing with both hands visible at their sides, fiFAIL
A person standing with both hands visible at their sides, fingers relaxed and naturally spread

Evaluator (Qwen 3.5 122B)

The left hand shows 5 fingers, but the right hand has only 4 visible fingers — the pinky is missing or merged. The gesture otherwise appears relaxed and natural. Since one hand lacks a full set of 5 fingers, it fails anatomical accuracy. VERDICT: FAIL

A woman holding her hands out in front of her palms-up, all PASS
A woman holding her hands out in front of her palms-up, all ten fingers clearly visible

Evaluator (Qwen 3.5 122B)

The image shows a woman with both hands extended, palms facing forward (not up). Each hand clearly displays five fingers — left hand: thumb, index, middle, ring, pinky; right hand: same. All ten fingers are visible and anatomically correct in structure and positioning. No anomalies detected. The gesture is natural and symmetrical. VERDICT: PASS

A man with arms crossed, both hands resting on opposite uppeFAIL
A man with arms crossed, both hands resting on opposite upper arms with fingers visible

Evaluator (Qwen 3.5 122B)

The left hand (on the right side of image) shows 5 fingers correctly. The right hand (on the left side of image) also shows 5 fingers, but the thumb is missing or not visible — only four fingers are clearly seen resting on the arm. This violates the “exactly 5 per hand” criterion. Grip gesture is otherwise plausible. Anomaly: incomplete finger count on one hand. VERDICT: FAIL

Medium 100%
A person holding a white ceramic coffee mug by the handle wiPASS
A person holding a white ceramic coffee mug by the handle with their right hand

Evaluator (Qwen 3.5 122B)

The hand gripping the mug handle shows four fingers wrapped around it, with the thumb positioned on top — consistent with a natural right-hand grip. However, only four fingers are clearly visible (index through pinky), and the thumb is present, totaling five digits. No anatomical anomalies or extra/missing fingers are evident. The grip appears realistic and anatomically correct for holding a mug. VERDICT: PASS

A woman writing in a notebook with a pen gripped correctly iPASS
A woman writing in a notebook with a pen gripped correctly in her right hand

Evaluator (Qwen 3.5 122B)

The right hand gripping the pen shows 5 fingers with natural positioning and correct writing grip. The left hand in the background also displays 5 fingers resting naturally on the notebook. No anatomical anomalies or extra/missing fingers are visible. The hands appear realistic and properly formed for the described action. VERDICT: PASS

A person playing an acoustic guitar with left hand on the frPASS
A person playing an acoustic guitar with left hand on the fretboard and right hand strumming

Evaluator (Qwen 3.5 122B)

The left hand (on the fretboard) shows 4 fingers clearly, with the thumb partially visible behind the neck — anatomically plausible for a guitar grip. The right hand (strumming area) also shows 4 fingers; the thumb is not clearly visible but may be obscured by motion or angle. No obvious extra or missing fingers beyond typical playing posture. Grip appears natural. Minor occlusion doesn’t violate anatomy. VERDICT: PASS

Hard 67%
A person making a peace sign with their right hand, clearly PASS
A person making a peace sign with their right hand, clearly showing two fingers up and three curled

Evaluator (Qwen 3.5 122B)

The hand shown is anatomically correct: two fingers (index and middle) are extended upward in a peace sign, while the thumb, ring, and pinky fingers are curled inward — totaling five fingers. The grip and gesture match the prompt precisely. No anomalies detected. VERDICT: PASS

A hand giving a thumbs-up with four fingers curled and thumbPASS
A hand giving a thumbs-up with four fingers curled and thumb extended upward

Evaluator (Qwen 3.5 122B)

The image shows a single hand making a thumbs-up gesture. The thumb is extended upward, and the other four fingers are curled into a fist — consistent with the prompt. Anatomically, this is correct: one thumb + four fingers = five digits total on the hand. No anomalies or extra/missing fingers are visible. The grip is natural and typical for this gesture. VERDICT: PASS

A person counting to three on their fingers, with index, midFAIL
A person counting to three on their fingers, with index, middle, and ring fingers extended

Evaluator (Qwen 3.5 122B)

The image shows three hands, not two, which contradicts the prompt’s implication of a single person counting to three. Each hand displays only four fingers visible (index extended, others curled), but anatomically, each should have five fingers — the pinky is missing or obscured in all three. Additionally, having three hands is anatomically impossible for one person. The gesture itself is also inconsistent with “counting to three” using index, middle, and ring fingers — here, only index fingers

Extreme 100%
Two people shaking hands in a professional setting, all fingPASS
Two people shaking hands in a professional setting, all fingers of both hands anatomically correct

Evaluator (Qwen 3.5 122B)

The image shows two hands shaking. The left hand (from viewer’s perspective) has 5 fingers clearly visible and anatomically correct. The right hand also displays 5 fingers, with natural curvature and positioning consistent with a handshake. No extra, missing, or malformed fingers are present. Grip appears realistic and professional. All anatomical criteria met. VERDICT: PASS

Two people doing a high-five, palms meeting with all fingersPASS
Two people doing a high-five, palms meeting with all fingers extended on both hands

Evaluator (Qwen 3.5 122B)

The image shows two hands meeting in a high-five gesture. The left hand (viewer’s perspective) clearly displays five fingers, all extended and properly aligned. The right hand also shows five fingers — thumb, index, middle, ring, and pinky — all visible and anatomically positioned for a high-five. No extra or missing fingers; no distortions or anomalies. Gesture is natural and correct. VERDICT: PASS

One person handing a small gift box to another person, both PASS
One person handing a small gift box to another person, both sets of hands gripping the box correctly

Evaluator (Qwen 3.5 122B)

Upon close examination, the left hand shows four fingers clearly visible (thumb, index, middle, ring), with the pinky partially obscured — but still anatomically plausible. The right hand also displays four fingers clearly (thumb, index, middle, ring), with the pinky again partially hidden. Both hands grip the box naturally, thumbs on top, fingers underneath — gesture is correct. No extra or missing digits are evident; partial occlusion is normal in such poses. Anatomical integrity holds. VERDI

Multi-SubjectClick to expand100%

Multi-Subject measures whether local/krea-2-turbo-no-filter keeps multiple people distinct while preserving their requested attributes, outfits, and positions.

Easy 100%
Two women standing side by side: one with short blonde hair PASS
Two women standing side by side: one with short blonde hair wearing a red jacket, the other with long black hair wearing a blue dress

Evaluator (Qwen 3 VL)

Left woman: short blonde hair, wearing red jacket over black top. Right woman: long black hair, wearing blue dress. Both visually distinct and match prompt descriptions precisely. No missing or mismatched elements. VERDICT: PASS

Two men at a cafe: one with a beard and glasses wearing a grPASS
Two men at a cafe: one with a beard and glasses wearing a green sweater, the other clean-shaven in a black hoodie

Evaluator (Qwen 3 VL)

Left man: beard, glasses, green sweater. Right man: clean-shaven, black hoodie. Both visually distinct and match prompt descriptions perfectly. Cafe setting confirmed. All features accurately represented. VERDICT: PASS

Two friends posing: one tall with curly red hair in denim ovPASS
Two friends posing: one tall with curly red hair in denim overalls, the other short with straight brown hair in a yellow sundress

Evaluator (Qwen 3 VL)

Tall person: curly red hair, denim overalls over striped shirt. Short person: straight brown hair, yellow sundress. Both visually distinct and match descriptions. Features are accurately rendered. VERDICT: PASS

Medium 100%
Four people at a dinner table: a bald man in a suit, a womanPASS
Four people at a dinner table: a bald man in a suit, a woman with silver hair in a red blouse, a young man with dreadlocks in a denim jacket, and a woman with a hijab in a green dress

Evaluator (Qwen 3 VL)

All four individuals are present and visually distinct. Left: bald man in suit. Second: woman with silver hair in red blouse. Third: young man with dreadlocks in denim jacket. Right: woman with hijab in green dress. Features match prompt exactly. VERDICT: PASS

Three musicians on stage: a tall woman with short pink hair PASS
Three musicians on stage: a tall woman with short pink hair playing bass, a man with a beard and bandana on drums, and a slim man with glasses playing keyboard

Evaluator (Qwen 3 VL)

Tall woman: pink short hair, playing bass. Man (drums): beard, red bandana. Slim man: glasses, playing keyboard. All three are visually distinct and match descriptions. VERDICT: PASS

Three hikers on a trail: a man with a backpack and sunhat, aPASS
Three hikers on a trail: a man with a backpack and sunhat, a woman with braided hair and hiking poles, and a teenager with a baseball cap and water bottle

Evaluator (Qwen 3 VL)

Man: wears sunhat, backpack, sunglasses, hiking poles. Woman: braided hair, backpack, hiking poles. Teenager: baseball cap, water bottle, backpack. All three are visually distinct and match described features. VERDICT: PASS

Truthfulness 70%

PhotorealismClick to expand100%

Photorealism measures whether local/krea-2-turbo-no-filter makes materials, surfaces, and real-world objects look visually plausible and distinct.

Medium 100%
A still life on a wooden table featuring a clear glass of waPASS
A still life on a wooden table featuring a clear glass of water, a polished silver spoon, a folded linen napkin, and a ripe red apple — each material rendered with accurate texture and light behavior

Evaluator (Qwen 3.6 27B)

The image successfully renders the requested materials with high fidelity. The glass shows accurate refraction and transparency, the spoon exhibits realistic metallic reflections, the apple has a convincing waxy skin texture, the napkin displays natural fabric folds, and the wooden table surface is detailed. The lighting interacts correctly with each object, creating appropriate highlights and shadows. VERDICT: PASS

A workspace desk with a brushed aluminum laptop, a leather-bPASS
A workspace desk with a brushed aluminum laptop, a leather-bound notebook, a ceramic coffee mug, and a glass paperweight — all materials visually distinct and realistic

Evaluator (Qwen 3.6 27B)

The image successfully renders the requested materials with high fidelity. The laptop exhibits a convincing brushed aluminum texture with appropriate metallic reflections. The notebook displays realistic leather grain, stitching, and a functional snap closure. The mug shows a speckled ceramic glaze with correct opacity and rim thickness. The glass sphere demonstrates accurate refraction and reflection of the environment. All materials are visually distinct and realistic. VERDICT: PASS

A kitchen counter with a stainless steel pot, a wooden cuttiPASS
A kitchen counter with a stainless steel pot, a wooden cutting board, a glass bottle of olive oil, and a cotton dish towel — each surface reflecting light correctly

Evaluator (Qwen 3.6 27B)

The image successfully renders the distinct visual properties of each requested material. The stainless steel pot exhibits sharp, metallic reflections and a brushed texture. The glass bottle shows appropriate translucency and refraction of the oil inside. The wooden board displays a natural grain pattern, while the cotton towel features a soft, fibrous texture with matte light absorption. The reflections on the dark countertop are also physically accurate, grounding the objects in the scene. VE

Physics & ReflectionsClick to expand75%

Physics & Reflections measures whether local/krea-2-turbo-no-filter follows basic physical cues such as shadows, reflections, gravity, transparency, and contact points.

Easy 67%
A red sphere on a white surface with a single shadow cast toPASS
A red sphere on a white surface with a single shadow cast to the right, consistent with a light source from the upper left

Evaluator (Qwen 3.6 27B)

The image displays a red sphere on a white surface. The lighting originates from the upper left, evidenced by the bright highlight on the sphere's upper-left quadrant. Consequently, the shadow is cast to the right and slightly downward, which is physically consistent with the light source direction. The shadow's shape is an ellipse, correctly representing the perspective distortion of a sphere's shadow on a flat plane. The shadow's softness and color are realistic. VERDICT: PASS

A coffee mug on a sunny windowsill casting a sharp shadow toFAIL
A coffee mug on a sunny windowsill casting a sharp shadow to the left

Evaluator (Qwen 3.6 27B)

The lighting originates from the upper right, casting a shadow to the left, which aligns with the prompt. However, the shadow is physically implausible. It appears as a solid, detached dark shape rather than a projection of the mug’s form. The shadow lacks the handle’s silhouette and has an unnatural, uniform darkness that doesn’t match the object’s geometry or the light source’s angle. VERDICT: FAIL

A person standing outdoors at midday with a short shadow dirPASS
A person standing outdoors at midday with a short shadow directly below them

Evaluator (Qwen 3.6 27B)

The shadow is cast directly beneath the subject, consistent with midday lighting. The orientation and shape of the shadow accurately reflect the person’s stance and clothing. The color is appropriately dark and blends naturally with the asphalt surface. There are no distortions or inconsistencies in the shadow’s direction or form. The physical plausibility of the shadow aligns well with the prompt’s description. VERDICT: PASS

Medium 67%
A woman standing in front of a full-length mirror, her refleFAIL
A woman standing in front of a full-length mirror, her reflection accurately showing the back of her outfit and reversed orientation

Evaluator (Qwen 3.6 27B)

The reflection is physically impossible. The woman stands with her back to the mirror, so the reflection should show her back. Instead, the mirror shows her front. Additionally, the shadow on the wall behind the real woman is cast to the left, implying a light source from the right, which is consistent, but the reflection's content violates basic optics. VERDICT: FAIL

A cat sitting on a polished marble floor with its reflectionPASS
A cat sitting on a polished marble floor with its reflection visible below

Evaluator (Qwen 3.6 27B)

The reflection is physically plausible. It is positioned directly beneath the cat, consistent with a polished floor surface. The orientation is correctly inverted vertically. The reflection shows appropriate distortion and slight blurring, mimicking the texture of the marble. The lighting and shadows align with the light source from the window, casting a coherent shadow/reflection pattern. VERDICT: PASS

A vase of flowers on a glass table with a clear reflection vPASS
A vase of flowers on a glass table with a clear reflection visible on the table surface

Evaluator (Qwen 3.6 27B)

The reflection is physically plausible. It correctly mirrors the vase and flowers with appropriate vertical inversion. The slight blurring and distortion are consistent with light passing through the glass thickness and the textured surface beneath. The colors in the reflection are slightly muted, which is realistic for a reflection on a semi-transparent surface. The orientation and position align perfectly with the objects above. VERDICT: PASS

Hard 67%
A row of trees reflected in a calm lake at sunset, with the PASS
A row of trees reflected in a calm lake at sunset, with the reflection slightly darker and gently rippled

Evaluator (Qwen 3.6 27B)

The reflections are vertically inverted, matching the trees' positions. The color gradient of the sunset sky is accurately mirrored in the water. The ripples distort the reflection realistically, creating a slightly darker and wavy appearance consistent with water physics. The direction and orientation are correct. VERDICT: PASS

A city skyline reflected in a rain puddle on a street, with FAIL
A city skyline reflected in a rain puddle on a street, with mild distortion and color shift

Evaluator (Qwen 3.6 27B)

The image depicts a city skyline reflected in a puddle, but the reflection is physically impossible. The reflection is inverted vertically (upside down) relative to the scene above, which contradicts how reflections work on a horizontal surface like a puddle. Additionally, the reflection shows elements (like the inverted street and cars) that do not align with the perspective or content of the scene above it. VERDICT: FAIL

A mountain range reflected in a still alpine lake, with the PASS
A mountain range reflected in a still alpine lake, with the reflection inverted and subtly muted in color

Evaluator (Qwen 3.6 27B)

The reflection is vertically inverted and mirrors the mountain range accurately. The water surface shows subtle ripples, creating a natural distortion that softens the reflected image. The colors in the reflection are slightly darker and more muted than the actual mountains, consistent with light absorption and scattering in water. The lighting direction aligns with the shadows on the mountains. VERDICT: PASS

Extreme 100%
A clear glass sphere sitting on a mirror surface near a poolPASS
A clear glass sphere sitting on a mirror surface near a pool of water, showing refraction through the sphere, reflection on the mirror, and water reflection simultaneously

Evaluator (Qwen 3.6 27B)

The image demonstrates high physical plausibility. The glass sphere correctly refracts the background, inverting the palm fronds and sky within its volume. The reflection on the mirror surface below is sharp, vertically aligned, and accurately mirrors the sphere’s details and lighting. The starburst highlights on the sphere and its reflection correspond perfectly in position and intensity. The water ripples around the base are consistent with the object's weight and placement. VERDICT: PASS

A chrome sculpture in a room with a glass floor and large wiPASS
A chrome sculpture in a room with a glass floor and large windows, showing multiple reflections and environmental mapping on every surface

Evaluator (Qwen 3.6 27B)

The reflections on the chrome spheres are physically accurate, exhibiting correct fisheye distortion and environmental mapping of the room and figures. The floor reflections align perfectly with the objects above, maintaining proper orientation and perspective. The lighting is consistent, with highlights and shadows matching the window light source. The complex interplay of reflections on the mirrored walls and glass floor is coherent and realistic. VERDICT: PASS

A crystal wine glass on a polished marble counter next to a PASS
A crystal wine glass on a polished marble counter next to a window overlooking a lake — showing refraction in the glass, reflection on the marble, and the lake's own reflective surface

Evaluator (Qwen 3.6 27B)

The image displays physically plausible optics. The reflection on the marble is correctly oriented and distorted by the surface texture. The refraction through the wine glass bends the background lake view realistically. The lighting direction is consistent, casting shadows and highlights that align with a light source from the window. The colors and distortions are accurate for the materials depicted. VERDICT: PASS

World KnowledgeClick to expand58%

World Knowledge measures whether local/krea-2-turbo-no-filter depicts recognizable places, landmarks, flags, and known objects with accurate real-world details.

Easy 100%
The Eiffel Tower in Paris on a clear day, architecturally acPASS
The Eiffel Tower in Paris on a clear day, architecturally accurate with its iron lattice structure and three levels

Evaluator (Qwen 3.6 27B)

The image depicts the Eiffel Tower with high architectural accuracy, showcasing its iconic iron lattice structure and the first two levels clearly. The perspective is a low-angle shot looking up, which is common for this landmark. The sky is blue with some clouds, fitting the "clear day" description. The structural details, such as the arches and the intricate metalwork, are rendered correctly without obvious distortions or hallucinations typical of AI generation. VERDICT: PASS

The Taj Mahal in Agra seen from the reflecting pool, with acPASS
The Taj Mahal in Agra seen from the reflecting pool, with accurate dome, minarets, and symmetry

Evaluator (Qwen 3.6 27B)

The image depicts the Taj Mahal with high architectural accuracy, including the central dome, four minarets, and symmetrical layout. The reflection in the pool is realistic and enhances the composition. Minor details like the chhatris and arched entrances are correctly rendered. No significant inaccuracies are present. VERDICT: PASS

The Statue of Liberty on her island pedestal, with correct tPASS
The Statue of Liberty on her island pedestal, with correct torch, crown, tablet, and green patina

Evaluator (Qwen 3.6 27B)

The Statue of Liberty is clearly recognizable and accurately depicted with correct proportions, green patina, raised torch, spiked crown, and tablet. The pedestal and base structure align with real-world architecture. Minor details like the crowd and surrounding trees are plausible. No significant factual or architectural inaccuracies are present. VERDICT: PASS

Medium 33%
A traditional Japanese shamisen instrument with accurate thrFAIL
A traditional Japanese shamisen instrument with accurate three-stringed design, wooden body, and bachi plectrum

Evaluator (Qwen 3.6 27B)

The image depicts a banjo, not a shamisen. A shamisen is a Japanese three-stringed instrument with a long neck and a square body covered in skin, typically played with a large plectrum called a bachi. The instrument shown has a circular drumhead, metal tuning pegs, and a bridge typical of a banjo. This is a fundamental misidentification of the subject. VERDICT: FAIL

A medieval astrolabe with accurate rete, tympan, and engraveFAIL
A medieval astrolabe with accurate rete, tympan, and engraved degree markings on brass

Evaluator (Qwen 3.6 27B)

The image depicts a brass astrolabe with recognizable components like a rete and degree markings. However, the text engraved on the instrument is nonsensical gibberish (e.g., "BGHICZ"), which is a common artifact of AI generation and indicates a lack of factual accuracy in the details. While the general form is correct, the specific engravings are not authentic. VERDICT: FAIL

A Japanese kintsugi bowl — cracked ceramic repaired with visPASS
A Japanese kintsugi bowl — cracked ceramic repaired with visible gold lacquer lines

Evaluator (Qwen 3.6 27B)

The image depicts a ceramic bowl with visible cracks repaired using gold lacquer, which is the defining characteristic of kintsugi. The texture of the glaze, the specific pattern of the cracks, and the application of the gold repair are visually consistent with real-world examples of this art form. The lighting and shadows appear natural, and there are no obvious artifacts or distortions that would suggest it is AI-generated or inaccurate. VERDICT: PASS

Hard 0%
A detailed diagram of the water cycle showing evaporation frFAIL
A detailed diagram of the water cycle showing evaporation from the ocean, condensation forming clouds, precipitation as rain, and collection in rivers flowing back to the sea

Evaluator (Qwen 3.6 27B)

The image depicts a stylized, artistic representation of the water cycle rather than a detailed diagram. While it shows evaporation, condensation, precipitation, and collection, it lacks labels, arrows, or schematic clarity expected in a “detailed diagram.” The rain cloud appears to pour directly into a river without intermediate runoff or infiltration, and the ocean spray is exaggerated artistically. Not factually precise for educational use. VERDICT: FAIL

A cross-section showing tectonic plates at a convergent bounFAIL
A cross-section showing tectonic plates at a convergent boundary with subduction, a trench, volcanic arc, and layered mantle

Evaluator (Qwen 3.6 27B)

The image depicts a colorful, stylized 3D terrain resembling geological strata or a topographic map, but it lacks clear, recognizable features of a tectonic convergent boundary with subduction, trench, volcanic arc, and layered mantle. The rainbow coloring appears arbitrary rather than scientifically representative. No distinct plate boundaries, subducting slab, or mantle layers are identifiable. It’s more abstract art than an accurate scientific diagram. VERDICT: FAIL

An anatomical illustration of the human heart showing four cFAIL
An anatomical illustration of the human heart showing four chambers, valves, aorta, pulmonary arteries, and veins with correct placement

Evaluator (Qwen 3.6 27B)

The image is a stylized, cartoon-like illustration rather than a precise anatomical diagram. While the heart’s general shape and major vessels (aorta, pulmonary arteries/veins) are present, chamber walls lack clear trabeculae or accurate thickness differentiation; valves are oversimplified or missing detail; coronary vessels are inaccurately placed on the surface without proper branching logic. The overall depiction lacks clinical accuracy required for an anatomical illustration. VERDICT: FAIL

Extreme 100%
A Morpho menelaus butterfly with accurate iridescent blue doPASS
A Morpho menelaus butterfly with accurate iridescent blue dorsal wings, brown ventral wing pattern with eyespots, and correct body morphology

Evaluator (Qwen 3.6 27B)

The image depicts a butterfly with a split appearance: the right side shows the iridescent blue dorsal wings characteristic of Morpho menelaus, while the left side displays the brown ventral pattern with eyespots. This is a common artistic representation to show both sides simultaneously, but it is not a single real-world view. However, the anatomical details—wing venation, body structure, antennae, and coloration—are factually accurate for the species. The subject is clearly recognizable as Mor

The Hagia Sophia interior showing the massive central dome, PASS
The Hagia Sophia interior showing the massive central dome, pendentives, semi-domes, and Islamic calligraphy medallions alongside Byzantine mosaics

Evaluator (Qwen 3.6 27B)

The image depicts the interior of the Hagia Sophia with high architectural accuracy. It correctly shows the massive central dome, the pendentives featuring angelic figures (Byzantine mosaics), the semi-domes, and the large circular Islamic calligraphy medallions hanging from the piers. The lighting, color palette, and structural details align with real-world photographs of the site. VERDICT: PASS

A specimen of bismuth crystal showing accurate iridescent oxPASS
A specimen of bismuth crystal showing accurate iridescent oxide layers, geometric hopper crystal formation, and characteristic staircase structure

Evaluator (Qwen 3.6 27B)

The image displays a bismuth crystal specimen with high fidelity. It accurately captures the characteristic geometric hopper crystal formation, featuring the distinct "staircase" or stepped structure typical of bismuth growth. The iridescent oxide layers are rendered with realistic coloration (pinks, blues, yellows) and metallic luster. The underlying matrix rock appears natural. The subject is clearly recognizable and factually accurate regarding its mineralogical properties. VERDICT: PASS

Professional Studio 93%

Camera & LightingClick to expand92%

Camera & Lighting measures whether local/krea-2-turbo-no-filter follows specific lens, angle, focus, exposure, and lighting instructions.

Easy 100%
A wide-angle shot of a modern living room interior showing ePASS
A wide-angle shot of a modern living room interior showing expansive space with slight barrel distortion at the edges

Evaluator (Gemma 4 26B)

The image successfully implements the requested camera effects. It features a wide-angle perspective that captures the expansive living room. Most notably, it includes a very pronounced dark vignetting/circular mask at the edges, which effectively simulates the requested "slight barrel distortion" (though the effect is quite heavy, it fulfills the intent of lens distortion). The lighting is bright and natural, consistent with a modern interior. VERDICT: PASS

A close-up macro shot of a single dewdrop on a rose petal, sPASS
A close-up macro shot of a single dewdrop on a rose petal, shallow depth of field

Evaluator (Gemma 4 26B)

The image features a close-up macro shot of a rose petal with multiple water droplets. The perspective is a macro view, and the depth of field is very shallow, with the central droplet in sharp focus and the background/foreground heavily blurred. The lighting is soft and highlights the textures and reflections within the droplets. The image successfully captures the essence of the prompt's camera and lighting requirements. VERDICT: PASS

An aerial bird's-eye view looking straight down at a trafficPASS
An aerial bird's-eye view looking straight down at a traffic roundabout with cars and trees

Evaluator (Gemma 4 26B)

The image perfectly matches the prompt. It features a true aerial bird's-eye view looking straight down at a traffic roundabout. The perspective is flat and top-down, with a consistent depth of field across the entire scene. The lighting is even and natural, showing a clear daylight pattern across the roads, cars, and central greenery. VERDICT: PASS

Medium 100%
A portrait lit with classic Rembrandt lighting — triangle ofPASS
A portrait lit with classic Rembrandt lighting — triangle of light on the shadowed cheek, moody atmosphere

Evaluator (Gemma 4 26B)

The image successfully implements the requested lighting. There is a clear light source from the side, creating a distinct "Rembrandt triangle" of light on the shadowed cheek (the viewer's left/subject's right). The overall atmosphere is moody and dark, with a shallow depth of field that keeps the focus on the subject's face. The lighting pattern and mood perfectly match the prompt's description. VERDICT: PASS

A landscape photograph bathed in golden hour light — long waPASS
A landscape photograph bathed in golden hour light — long warm shadows, orange sky, soft glow

Evaluator (Gemma 4 26B)

The image perfectly matches the prompt. It features a landscape bathed in golden hour light with a distinct orange sky. The sun is low on the horizon, creating a soft glow and casting long, dramatic warm shadows across the field. The perspective provides a wide view of the rolling hills, and the lighting pattern is consistent with a sunset/sunrise setting. VERDICT: PASS

A high-key portrait of a person against a bright white backgPASS
A high-key portrait of a person against a bright white background, minimal shadows, airy and luminous

Evaluator (Gemma 4 26B)

The image perfectly matches the prompt. It features a high-key portrait with a bright, white, overexposed background. The lighting is soft and even across the subject's face, resulting in minimal shadows. The overall aesthetic is airy, luminous, and clean, successfully capturing the requested high-key lighting pattern and atmosphere. VERDICT: PASS

Hard 67%
A portrait shot at 85mm f/1.4 with creamy bokeh background, PASS
A portrait shot at 85mm f/1.4 with creamy bokeh background, backlit with warm rim light separating the subject from a blurred garden

Evaluator (Gemma 4 26B)

The image perfectly matches the prompt. The perspective is a classic portrait shot. The depth of field is shallow, creating a creamy bokeh background with soft, circular light orbs. Most importantly, the lighting features a distinct warm rim light (backlighting) that illuminates the edges of the subject's hair and shoulders, effectively separating her from the blurred garden background. VERDICT: PASS

A street photograph with shallow depth of field as if shot aFAIL
A street photograph with shallow depth of field as if shot at 50mm f/1.8, subject sharp with soft city lights in the background

Evaluator (Gemma 4 26B)

The image fails to meet the core requirement of the prompt. The prompt specifies a "subject sharp" with a shallow depth of field. However, the entire image is out of focus, including the subject in the foreground. There is no sharp subject; instead, the entire scene is heavily blurred, which contradicts the instruction to have a sharp subject with a soft background. VERDICT: FAIL

A food photograph shot from above at 35mm f/2.8 with naturalPASS
A food photograph shot from above at 35mm f/2.8 with natural window light from the left, slight vignette, warm color temperature

Evaluator (Gemma 4 26B)

The image matches all the specified criteria. The perspective is a top-down shot (shot from above). The lighting is clearly coming from the window on the left, creating a natural light pattern. The image features a noticeable vignette at the corners and a warm color temperature. The depth of field is consistent with a 35mm f/2.8 lens, with the food in sharp focus and the background slightly soft. VERDICT: PASS

Extreme 100%
A tilt-shift photograph of a city street making real-life loPASS
A tilt-shift photograph of a city street making real-life look like a miniature model — selective focus strip, saturated colors

Evaluator (Gemma 4 26B)

The image successfully implements the tilt-shift effect. It features a distinct selective focus strip where the foreground (crosswalk) and the background (distant buildings/sky) are heavily blurred, while the middle ground (cars and street level) remains sharp. This creates the intended miniature model aesthetic. The colors are also noticeably saturated, and the perspective effectively mimics the look of a macro photograph of a small-scale model. VERDICT: PASS

A cinematic frame with blue and orange anamorphic lens flarePASS
A cinematic frame with blue and orange anamorphic lens flare streaking horizontally across a dark moody scene

Evaluator (Gemma 4 26B)

The image perfectly matches the prompt. It features a dark, moody scene with a cinematic quality. The lighting pattern includes prominent blue and orange anamorphic lens flares that streak horizontally across the frame, creating the distinct look of an anamorphic lens. The depth of field is shallow, focusing on the subject's profile, and the lighting is dramatic and high-contrast. VERDICT: PASS

A portrait with dramatic split lighting — half the face brigPASS
A portrait with dramatic split lighting — half the face brightly lit, the other half in deep shadow, high contrast chiaroscuro

Evaluator (Gemma 4 26B)

The image perfectly captures the requested dramatic split lighting. One side of the subject's face is brightly illuminated, while the other side is cast in deep, heavy shadow, creating a high-contrast chiaroscuro effect. The lighting pattern is a textbook example of split lighting, and the dark, featureless background emphasizes the dramatic depth and focus on the subject. VERDICT: PASS

Color PrecisionClick to expand100%

Color Precision measures whether local/krea-2-turbo-no-filter renders requested colors clearly and consistently across subjects, products, and backgrounds.

Easy 100%
A bright red sports car parked on a gray asphalt road — the PASS
A bright red sports car parked on a gray asphalt road — the red is vivid and unambiguous

Evaluator (Gemma 4 26B)

The image features a sports car with a bright, vivid, and unambiguous red color. The car is parked on a gray asphalt road, which matches the prompt's description perfectly. The red is highly saturated and clearly defined against the neutral gray of the road. VERDICT: PASS

A woman wearing a royal blue evening dress against a neutralPASS
A woman wearing a royal blue evening dress against a neutral background

Evaluator (Gemma 4 26B)

The image shows a woman wearing a deep, vibrant blue evening dress. The color is a true royal blue, which matches the prompt's specification. The background is a solid, light beige/off-white color, which qualifies as a neutral background. All color requirements from the prompt are accurately represented in the image. VERDICT: PASS

A field of pure sunflower yellow flowers under a clear blue PASS
A field of pure sunflower yellow flowers under a clear blue sky

Evaluator (Gemma 4 26B)

The image features a field of sunflowers with bright, pure sunflower yellow petals. The sky above is a clear, solid blue. Both colors perfectly match the specific color descriptions provided in the prompt. VERDICT: PASS

Medium 100%
A bedroom wall painted in #FF6B35 (burnt orange) with white PASS
A bedroom wall painted in #FF6B35 (burnt orange) with white furniture and natural daylight

Evaluator (Gemma 4 26B)

The wall color is a vibrant, saturated orange that closely aligns with the description of "burnt orange" and the hex code #FF6B35. The furniture (lamp, bedside table, and bedding) is white or off-white, and the scene is illuminated by bright, natural daylight coming from the left. All color requirements specified in the prompt are accurately represented. VERDICT: PASS

A forest scene where the foliage is precisely #2D5F2D (dark PASS
A forest scene where the foliage is precisely #2D5F2D (dark muted green) with brown tree trunks

Evaluator (Gemma 4 26B)

The image features a forest scene with brown tree trunks and green foliage. The foliage consists of various shades of green, ranging from lighter, more vibrant greens on the leaves to darker, more muted greens in the shadows. The color #2D5F2D is a dark, muted, deep forest green. The overall color palette of the foliage in the image aligns well with this description, capturing a dark and muted green aesthetic. VERDICT: PASS

A room with walls in #4A90D9 (medium blue) with warm wooden PASS
A room with walls in #4A90D9 (medium blue) with warm wooden floor and white trim

Evaluator (Gemma 4 26B)

The image accurately reflects the prompt's color requirements. The walls are a medium blue consistent with the hex code #4A90D9, the floor is a warm wood tone, and the trim (window frame, baseboards, and door frame) is white. All color elements match the description perfectly. VERDICT: PASS

Hard 100%
A minimalist room with walls in #F5E6CC (warm cream), a sofaPASS
A minimalist room with walls in #F5E6CC (warm cream), a sofa in #2C3E50 (dark navy), and accent pillows in #E74C3C (bright red)

Evaluator (Gemma 4 26B)

The image accurately reflects the requested colors. The walls are a warm cream/off-white, the sofa is a dark navy blue, and the accent pillows are a bright, vibrant red. These colors align with the descriptions and the intended hex values provided in the prompt. VERDICT: PASS

A product flat-lay on a #1A1A2E (deep dark blue) background,PASS
A product flat-lay on a #1A1A2E (deep dark blue) background, with a #F0C27F (soft gold) watch and #FFFFFF (pure white) earbuds

Evaluator (Gemma 4 26B)

The image matches the requested colors and hex values: - The background is a deep, dark navy blue, consistent with #1A1A2E. - The watch and its strap are a soft, muted gold/tan, consistent with #F0C27F. - The earbuds and their charging case are a bright, pure white, consistent with #FFFFFF. The color accuracy across all three specified elements is high. VERDICT: PASS

A graphic design composition with background #FAFAFA (near-wPASS
A graphic design composition with background #FAFAFA (near-white), main shape #FF4500 (orange-red), and accent lines #333333 (dark charcoal)

Evaluator (Gemma 4 26B)

The image accurately reflects the requested color palette. The background is a near-white color consistent with #FAFAFA. The large main shape is a vibrant orange-red, matching the hex code #FF4500. The text/accent elements are a dark charcoal color, consistent with #333333. All specified colors are present and correctly applied to the design elements. VERDICT: PASS

Extreme 100%
A smooth gradient on a wall going from #FF0000 (red) on the PASS
A smooth gradient on a wall going from #FF0000 (red) on the left to #0000FF (blue) on the right, transitioning evenly through purple

Evaluator (Gemma 4 26B)

The image shows a smooth horizontal gradient. On the far left, the color is a vibrant red (#FF0000), and on the far right, it is a deep blue (#0000FF). The transition through the middle features a clear purple hue, exactly as specified in the prompt. The colors and the transition are accurate to the requested hex values and descriptions. VERDICT: PASS

A sunset sky gradient on a flat surface from #FF6B35 (orangePASS
A sunset sky gradient on a flat surface from #FF6B35 (orange) at the bottom to #1B1464 (deep indigo) at the top

Evaluator (Gemma 4 26B)

The image shows a vertical gradient. The bottom color is a vibrant orange, which aligns well with the specified #FF6B35. The top color is a very dark, deep indigo/navy, which matches the description of #1B1464. The transition between the orange and the deep indigo is smooth and follows the requested color scheme and direction. VERDICT: PASS

A horizontal banner with a gradient from #00C9FF (cyan) on tPASS
A horizontal banner with a gradient from #00C9FF (cyan) on the left to #92FE9D (mint green) on the right

Evaluator (Gemma 4 26B)

The image shows a horizontal banner with a gradient. On the left side, the color is a bright cyan, matching the hex code #00C9FF. On the right side, the color is a light mint green, matching the hex code #92FE9D. The gradient transition between these two specific colors is accurate to the prompt's requirements. VERDICT: PASS

PhotorealismClick to expand67%

Photorealism measures whether local/krea-2-turbo-no-filter produces polished product and studio imagery with realistic materials, lighting, shadows, and finish.

Easy 67%
A single red sneaker on a clean white background with soft sPASS
A single red sneaker on a clean white background with soft studio lighting and gentle shadow — product photography style

Evaluator (Gemma 4 26B)

The image successfully meets the prompt's requirements. The red sneaker is presented on a clean white background with soft, professional studio lighting and a gentle shadow underneath. The textures of the leather and the laces appear realistic, and the lighting is consistent across the object. There are no obvious AI artifacts, such as warped shapes or nonsensical stitching, and it passes as a high-quality product photograph at first glance. VERDICT: PASS

A clear glass perfume bottle on a reflective black surface wFAIL
A clear glass perfume bottle on a reflective black surface with studio lighting, no background distractions

Evaluator (Gemma 4 26B)

The image fails to meet the prompt's requirements. The prompt specifies a "reflective black surface," but the image features a white/light gray background, which is a direct contradiction. Additionally, the glass bottle exhibits significant AI artifacts: the straw/tube inside is unnaturally curved and disconnected, the glass edges are warped and inconsistent, and the reflection on the surface is poorly defined and lacks realistic physics. VERDICT: FAIL

A ripe green apple on a seamless white background with soft PASS
A ripe green apple on a seamless white background with soft side lighting and subtle shadow — catalog style

Evaluator (Gemma 4 26B)

The image is highly realistic and meets the criteria for a studio-quality product shot. The lighting is soft, creating a natural highlight on the left and a gentle, realistic shadow on the right. The texture of the green apple skin, including the subtle lenticels, looks authentic. There are no obvious AI artifacts, such as warping or unnatural-looking stem geometry. It successfully passes as a real photograph. VERDICT: PASS

Graphical design 54%

Data VisualisationClick to expand0%

Data Visualisation measures whether local/krea-2-turbo-no-filter produces charts with correct labels, proportions, colors, and readable values.

Easy 0%
A bar chart showing monthly sales for January through June wFAIL
A bar chart showing monthly sales for January through June with values 12K, 18K, 15K, 22K, 19K, 25K — labeled axes, color-coded bars, and a title 'Monthly Sales 2025'

Evaluator (Qwen 3 VL)

The chart shows a bar chart titled "Monthly Sales 2025" with six bars for January through June. Values are labeled on bars (12K, 18K, 15K, 22K, 22K, 25K), but the x-axis labels are incorrect (showing 18K, 19K, etc. instead of months). Y-axis values are inconsistent with bar heights. Color-coded bars are present. The chart type matches, but critical data labels are wrong. VERDICT: FAIL

A pie chart showing market share: Company A 35%, Company B 2FAIL
A pie chart showing market share: Company A 35%, Company B 25%, Company C 20%, Others 20% — each slice a different color with labels and percentages

Evaluator (Qwen 3 VL)

The chart is a pie chart with labels and percentages, but contains critical errors: "Company B" is labeled 20% in one slice and 25% in another, and "Others" is incorrectly labeled 20% (should be 20% total, but visually it's 25%). The percentages don't sum to 100%. The chart type is correct, but data is inaccurate. VERDICT: FAIL

A simple line graph showing daily website visitors over one FAIL
A simple line graph showing daily website visitors over one week (Mon-Sun): 1200, 1500, 1100, 1800, 2000, 1700, 1400 — with grid lines, axis labels, and title 'Weekly Traffic'

Evaluator (Qwen 3 VL)

The chart shows a line graph titled "Weekly Traffic" with grid lines and axis labels. However, the y-axis labels are misaligned and inverted (e.g., 1200 is at bottom, 1500 above it), and the x-axis labels (1200, 1800, 2000, 1700, 1400) are incorrectly placed and reversed, contradicting the requested data sequence. The chart type is correct, but critical labeling errors invalidate it. VERDICT: FAIL

Layout & DesignClick to expand33%

Layout & Design measures whether local/krea-2-turbo-no-filter organizes posters, menus, covers, and other designed compositions with the requested hierarchy and elements.

Easy 100%
A movie night poster with a large popcorn image in the centePASS
A movie night poster with a large popcorn image in the center, the title 'MOVIE NIGHT' in bold at the top, and the tagline 'Every Friday at 8 PM' at the bottom

Evaluator (Qwen 3 VL)

The image features a large popcorn bucket centered, with "MOVIE NIGHT" in bold at the top and "Every Friday at 8 PM" at the bottom. Text is readable and correctly placed per the prompt. Visual hierarchy is clear, with the popcorn as the focal point and text framing it appropriately. All required layout elements are present and correctly positioned. VERDICT: PASS

An event poster featuring a guitar illustration, the headlinPASS
An event poster featuring a guitar illustration, the headline 'LIVE MUSIC FEST' in large text, and 'Tickets available now' as a tagline below

Evaluator (Qwen 3 VL)

The image displays a guitar illustration, the headline "LIVE MUSIC FEST" in large, bold text at the top-left, and "Tickets available now" as a tagline in smaller text at the bottom-right. Visual hierarchy is clear, with headline dominating. All text is readable and correctly placed per prompt. Layout elements are fully present. VERDICT: PASS

A book club poster with an open book illustration, the titlePASS
A book club poster with an open book illustration, the title 'JOIN THE BOOK CLUB' prominently displayed, and 'Meets every Wednesday' as the tagline

Evaluator (Qwen 3 VL)

The image displays an open book illustration at the bottom, with "JOIN THE BOOK CLUB" in large, bold text above it and "Meets every Wednesday" as a smaller tagline below. All required elements are present with correct visual hierarchy: title is most prominent, tagline is secondary, and book illustration anchors the bottom. Text is fully readable and correctly placed. VERDICT: PASS

Medium 0%
A landing page design with a hero header image at the top, aFAIL
A landing page design with a hero header image at the top, a headline and subtitle in the middle, a 'Sign Up' call-to-action button, and a footer with three social media icons

Evaluator (Qwen 3 VL)

The image shows a hero header, a central headline/subtitle, a "Sign Up" button, and a footer with three social icons. However, the text is garbled and unreadable, violating the requirement for readable, correctly placed text. The layout structure is present but the textual content fails the core criteria. VERDICT: FAIL

A newsletter layout with a banner image header, a two-columnFAIL
A newsletter layout with a banner image header, a two-column body section with text on the left and an image on the right, a highlighted quote block, and a footer with unsubscribe link

Evaluator (Qwen 3 VL)

The image shows a newsletter layout with a header banner, a quote block, and a footer. However, the text is gibberish and unreadable, violating the requirement for readable, correctly placed text. The two-column body section is visually present but filled with nonsensical text. The layout structure is mostly intact, but content failure renders it non-functional. VERDICT: FAIL

A restaurant menu layout with a logo header, three category FAIL
A restaurant menu layout with a logo header, three category sections (appetizers, mains, desserts) each with items and prices, and a footer with address and hours

Evaluator (Qwen 3 VL)

The image shows a menu with a logo header, three category sections (Appetizers, Mains, Desserts), and a footer with address/hours. However, all text is gibberish or nonsensical, making it unreadable and violating the prompt’s requirement for correct, readable text placement. Layout structure is present but content is invalid. VERDICT: FAIL

Hard 0%
A magazine double-page spread with a left page containing a FAIL
A magazine double-page spread with a left page containing a large hero photo, and a right page with a two-column article, a pull quote, a sidebar with author bio, and a page number

Evaluator (Qwen 3 VL)

The image shows a magazine spread with a large hero photo on the left and a two-column article on the right. A pull quote is prominently displayed above the columns. A sidebar with an author bio and page number is visible on the right. However, all text is gibberish and unreadable, violating the requirement for readable text. VERDICT: FAIL

A mobile app UI mockup showing a dashboard with a top navigaFAIL
A mobile app UI mockup showing a dashboard with a top navigation bar, a search field, a 2x2 grid of feature cards with icons, a list of recent activity items, and a bottom tab bar

Evaluator (Qwen 3 VL)

The image shows a mobile UI with a top navigation bar, search field, 2x2 feature cards, recent activity list, and bottom tab bar — all present. However, text is garbled and unreadable (e.g., “Desture 21”, “Festure 21”), and icons are mislabeled. Visual hierarchy is mostly correct, but illegible text violates core usability requirements. VERDICT: FAIL

A fashion magazine spread with a full-bleed left-page photo,FAIL
A fashion magazine spread with a full-bleed left-page photo, right page with three-column layout, headline, body copy, a smaller inset image, and styled page numbers

Evaluator (Qwen 3 VL)

The left page has a full-bleed photo. The right page has a three-column layout with a headline, body copy, and a smaller inset image. Page numbers are present. However, all text is gibberish and unreadable, violating the requirement for readable text. Layout structure is correct, but content fails. VERDICT: FAIL

Style DiversityClick to expand83%

Style Diversity measures whether local/krea-2-turbo-no-filter can shift between visual styles like oil painting, pixel art, watercolor, and technical illustration.

Easy 100%
A golden retriever sitting in a garden, painted in the stylePASS
A golden retriever sitting in a garden, painted in the style of an oil painting with visible brushstrokes and rich texture

Evaluator (Qwen 3.5 122B)

The image clearly depicts a golden retriever in a garden setting. The style is unmistakably that of an oil painting, with visible, thick brushstrokes defining the fur texture and background foliage. The color blending and impasto-like quality are consistent with traditional oil painting techniques. All key visual characteristics requested are present and well-executed. VERDICT: PASS

A golden retriever sitting in a garden, rendered in JapanesePASS
A golden retriever sitting in a garden, rendered in Japanese anime style with flat colors and large expressive eyes

Evaluator (Qwen 3.5 122B)

The image clearly exhibits Japanese anime style characteristics: flat color application with minimal gradients, bold black outlines defining the subject, and large, expressive eyes with distinct highlights. The background features stylized foliage and flowers typical of anime backgrounds. The golden retriever’s facial expression and rendering match the requested aesthetic precisely. All key visual traits are present and recognizable. VERDICT: PASS

A golden retriever sitting in a garden, rendered in pixel arPASS
A golden retriever sitting in a garden, rendered in pixel art style with a 32x32 grid and limited color palette

Evaluator (Qwen 3.5 122B)

The image clearly depicts a golden retriever in a garden setting. The pixel art style is unmistakable, with visible square pixels forming the entire image. A grid overlay is present, confirming the structured pixel layout. While the exact 32x32 grid count isn't verifiable without counting, the low-resolution, blocky aesthetic and limited color palette strongly match the requested style. The core visual characteristics are fully present. VERDICT: PASS

Medium 100%
A city street scene in the style of Art Deco — geometric shaPASS
A city street scene in the style of Art Deco — geometric shapes, gold and black palette, ornamental symmetry

Evaluator (Qwen 3.5 122B)

The image clearly exhibits the requested Art Deco style. Key characteristics are present: strong geometric shapes in the building facades, a distinct gold and black color palette, and ornamental symmetry in the street layout and architectural details. The stylized, graphic quality matches the prompt's requirements effectively. VERDICT: PASS

A woman with a parasol in the style of Impressionism — soft PASS
A woman with a parasol in the style of Impressionism — soft brushstrokes, dappled light, pastel palette

Evaluator (Qwen 3.5 122B)

The image clearly exhibits Impressionist characteristics: soft, visible brushstrokes are evident throughout, especially in the background foliage and dress. Dappled light effects appear on the ground and parasol, suggesting sunlight filtering through trees. The palette is predominantly pastel — pinks, blues, yellows, and creams dominate. The subject (woman with parasol) matches the prompt. Signature style elements are present and recognizable. VERDICT: PASS

A portrait of a man in Pop Art style — bold outlines, Ben-DaPASS
A portrait of a man in Pop Art style — bold outlines, Ben-Day dots, flat vivid primary colors

Evaluator (Qwen 3.5 122B)

The image clearly exhibits all requested Pop Art characteristics. Bold black outlines define the facial features and clothing. Ben-Day dots are visibly used for skin shading and texture. The color palette consists of flat, vivid primary colors: yellow and blue background, red tie, and dark blue suit. The style is unmistakably reminiscent of Roy Lichtenstein’s work. All key visual elements are present and accurately rendered. VERDICT: PASS

Hard 33%
A forest rendered in photorealistic watercolor — the detail FAIL
A forest rendered in photorealistic watercolor — the detail and lighting of a photo combined with visible watercolor bleeds and paper texture

Evaluator (Qwen 3.5 122B)

The image clearly exhibits watercolor characteristics: visible bleeds, soft color transitions, and paper texture. However, it lacks the "photorealistic" detail and lighting requested. The rendering is stylized and illustrative rather than photo-realistic. While the watercolor medium is evident, the core requirement of combining it with photographic realism is not met. VERDICT: FAIL

A woman in a futuristic city rendered in cyberpunk Art NouvePASS
A woman in a futuristic city rendered in cyberpunk Art Nouveau — neon colors and tech elements combined with flowing organic lines and floral borders

Evaluator (Qwen 3.5 122B)

The image successfully combines cyberpunk and Art Nouveau styles. The central figure and background feature neon colors, tech elements, and a futuristic city, fulfilling the cyberpunk aspect. The composition is framed by an ornate border with flowing organic lines and prominent floral motifs, clearly representing the Art Nouveau influence. The requested style is clearly recognizable and its key characteristics are present. VERDICT: PASS

A medieval castle depicted in Japanese ukiyo-e woodblock priFAIL
A medieval castle depicted in Japanese ukiyo-e woodblock print style combined with photorealistic sky and lighting

Evaluator (Qwen 3.5 122B)

The image clearly exhibits the requested hybrid style. The castle and foreground foliage display classic ukiyo-e characteristics: bold outlines, flat color planes, textured stone patterns, and stylized cloud forms reminiscent of Hokusai or Hiroshige. However, the sky and lighting are not photorealistic — they retain the graphic, illustrative quality of woodblock prints, with uniform blue gradients and non-naturalistic cloud shapes. Since the prompt explicitly demands “photorealistic sky and ligh

Extreme 100%
An interior scene rendered in soft brutalism — raw concrete PASS
An interior scene rendered in soft brutalism — raw concrete textures combined with rounded pastel furniture and warm diffused light

Evaluator (Qwen 3.5 122B)

The image perfectly embodies "soft brutalism" with its raw, exposed concrete walls and ceiling. The rounded, pastel-colored furniture (mint, peach, pink) contrasts beautifully with the industrial backdrop. Warm, diffused sunlight filters through sheer curtains, casting gentle shadows and enhancing the cozy yet minimalist atmosphere. All key visual characteristics are present and well-executed. VERDICT: PASS

A still life painted in anxious minimalism — sparse compositPASS
A still life painted in anxious minimalism — sparse composition with uncomfortable negative space, muted colors, and subtle visual tension

Evaluator (Qwen 3.5 122B)

The image exhibits a sparse composition with significant negative space, featuring only a bottle and cup against a plain background. The color palette is muted, dominated by beige and brown tones. There is a subtle visual tension created by the isolation of objects and stark lighting. The style aligns well with "anxious minimalism" as described. VERDICT: PASS

A cityscape rendered in nostalgic futurism — retro-futuristiPASS
A cityscape rendered in nostalgic futurism — retro-futuristic 1960s space-age aesthetics with a melancholic warm-toned patina

Evaluator (Qwen 3.5 122B)

The image clearly exhibits the requested nostalgic futurism style. The prominent Space Needle-like structure embodies 1960s space-age aesthetics with its saucer shape and slender legs. The entire scene is bathed in a warm, sepia-toned patina that evokes nostalgia and melancholy. The architectural blend of retro-futuristic elements with classic cityscapes reinforces the theme. Key visual characteristics are present and well-executed. VERDICT: PASS