Head to head
Esc

Models · slot A

to navigate to pick

FLUX.2 [klein] 4B Black Forest Labs Wan 2.5 (Preview) Alibaba

Settled by community votes across 19 shared challenges, with an AI judge weighing in on each.

FLUX.2 [klein] 4B

22.3 arena score

#32 of 62 in Text-to-Image

Skill signature · Text-to-Image

Wan 2.5 (Preview)

23.4 arena score

#26 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.2 [klein] 4B

0.0%

win rate

Ties

0.0%

Wan 2.5 (Preview)

100.0%

win rate

0.0% 0.0% ties 100.0%
Shared challenges 19

Challenge by challenge

The strongest take from each model on every shared challenge, with the AI judge's read.

Geometric Composition

Text-to-Image

“A glass cube on a wooden table. Inside the cube is a small blue sphere. On top of the cube sits a red book. A green plant is behind the cube, partially visible through the glass. Soft window light from the left.”

FLUX.2 [klein] 4B
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [klein] 4B

  • + Excellent structural geometry of the glass cube.
  • + Realistic surface texture on the book and table.
  • + Accurate refraction and reflection of the sphere on the bottom of the glass.
  • The blue sphere is quite small compared to the prompt's likely intent.
  • The plant in the background is very out of focus.

Wan 2.5 (Preview)

  • + Beautiful lighting and atmosphere with visible dust motes.
  • + Strong composition with vibrant colors.
  • + Excellent adherence to the 'partially visible through the glass' instruction for the plant.
  • The glass cube has physically impossible geometry where the top edge meets the book.
  • The sphere appears to be floating or improperly grounded within the cube.

Verdict: Both models followed the prompt instructions perfectly regarding object placement and color. FLUX.2 [klein] 4B produced a more physically realistic and cleaner image, while Wan 2.5 (Preview) created a more atmospheric scene but struggled with the structural integrity of the glass cube's edges.

Man and Car in California

Editing
Edit instruction

“Make a photo of the man driving the car down the California coastline”

Source
FLUX.2 [klein] 4B
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [klein] 4B

  • + Excellent preservation of the man's facial features and specific hairstyle from the source.
  • + High car fidelity including the specific plaid pattern of the man's coat.
  • + Realistic motion blur and integrated lighting for a driving scene.
  • The driver appears to be leaning quite far out of the window for a photo, which looks slightly unnatural.
  • The coastline background has some minor tiling artifacts in the water waves.

Wan 2.5 (Preview)

  • + Beautiful composition with iconic California-style palm trees.
  • + Good preservation of the car's geometry and reflections.
  • The man's face is very small and loses almost all likeness to the source image.
  • The man appears to be wearing a dark scarf/shirt that doesn't match the source wardrobe.
  • The hand on the steering wheel looks slightly distorted.

Verdict: FLUX.2 [klein] 4B is the clear winner because it successfully preserves the identity and specific clothing of the man from the source image while placing him in the new environment. Wan 2.5 (Preview) creates a nice scenic view but fails to maintain the man's likeness, effectively replacing him with a generic figure.

Candid Street Photography

Text-to-Image

“A candid street photo of an elderly Japanese man repairing a red bicycle in light rain, reflections on wet pavement, shallow depth of field, 50mm lens, natural skin texture, imperfect framing, motion blur from passing cars, cinematic but realistic, no stylization.”

FLUX.2 [klein] 4B
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [klein] 4B

  • + Excellent depiction of heavy rain and wet surface reflections
  • + Dynamic and atmospheric composition with realistic car headlights
  • + Captures the 'candid' and 'imperfect framing' requested in the prompt
  • Major structural defects in the bicycle frame and wheel alignment
  • The man is positioned as if sitting on an invisible seat or a non-existent part of the bike

Wan 2.5 (Preview)

  • + Extremely realistic skin texture and facial details
  • + Accurate depiction of a man actually performing a repair with tools
  • + Strong adherence to the 50mm shallow depth of field request
  • The cars in the background are static rather than showing 'motion blur'
  • The bicycle geometry is slightly warped, specifically the pedals and stand

Verdict: Wan 2.5 (Preview) is the clear winner for its superior anatomical and technical realism, particularly in the subject's face and hands, and for correctly showing the 'repair' action with tools. While FLUX.2 [klein] 4B handles the environmental rain and lighting effects beautifully, it fails significantly on the structural integrity of the bicycle and the physical logic of the man's pose.

Fantasy Warrior

Text-to-Image

“Close portrait of a battle-worn paladin in ornate engraved plate armor, hair braided with small beads, faint scars and dirt on the skin, warm torchlight reflecting off metal, shallow depth of field, bokeh sparks, lifelike eyes, highly detailed texture on leather straps and cloth underlayer.”

FLUX.2 [klein] 4B
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [klein] 4B

  • + Features very clear and intricate engraving on the plate armor
  • + Highly realistic skin texture with subtle scarring
  • + Excellent lighting balance that highlights the metal grain
  • The braids and beads are a bit thin and simple compared to the prompt
  • Composition is a very standard, symmetrical head-on shot

Wan 2.5 (Preview)

  • + Excellent interpretation of 'braided with small beads' with high-contrast metallic beads
  • + Superior texture on leather straps and frayed cloth underlayers
  • + More cinematic composition with better use of bokeh sparks and depth of field
  • The facial features look a bit soft and youthful for a 'battle-worn' paladin
  • The engraving on the armor is less sharp than the competitor

Verdict: Both models followed the prompt well, but Wan 2.5 (Preview) produced a more cinematic and detailed result in terms of materials, specifically the leather straps, frayed cloth, and the beads in the hair. While FLUX.2 [klein] 4B had sharper armor engravings and a more rugged face, Wan 2.5 (Preview) provided a more visually interesting composition with better adherence to the specific 'beads' and 'cloth underlayer' requirements.

Modern Clean Menu

Text-to-Image

“Modern minimalist restaurant menu design, white background with colorful food photos in grid, sections for appetizers/pizza/mains, bold sans-serif fonts, vibrant accents, clean professional layout for casual dining.”

FLUX.2 [klein] 4B
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [klein] 4B

  • + Excellent photo quality with realistic lighting and appetizing textures
  • + Clean, high-end editorial feel better suited for professional dining
  • + Good grid alignment and professional distribution of white space
  • Text rendering is mostly gibberish or heavily distorted symbols
  • The 'Mains' category is repeated as 'Mdains' and 'Mdans'

Wan 2.5 (Preview)

  • + Excellent structural adherence to Appetizers/Pizza/Mains sections
  • + Clear layout that mimics a real casual dining menu
  • + Text is more legible, though spelling errors are present
  • Food photos lack variety, with most dishes looking like identical salads/starters
  • Visual aesthetic is slightly more generic and less stylish than the competitor

Verdict: Both models followed the prompt well, but Wan 2.5 (Preview) followed the specific requested categories (Appetizers, Pizza, Mains) much more accurately. While FLUX.2 [klein] 4B produced more artistic and high-quality food photography, its text generation was poor and it failed to logically separate the food categories.

Magic Burger Explosion: Fiery Photorealism Challenge

Text-to-Image

“Ad for 'Magic Burger'. Dynamic, exploded burger with all components (bun, patty, cheese, lettuce, tomato, sauce) suspended in mid-air. Emphasize photorealistic detail and a sense of motion. Dark, fiery background with glowing embers. Integrate text: 'MAGIC BURGER' as a prominent title, 'LIMITED TIME ONLY' as a secondary message, and '€6.99' in a starburst, all rendered with a fiery, glowing effect.”

FLUX.2 [klein] 4B
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [klein] 4B

  • + Strong, high-resolution textures on the bun and patty
  • + Accurate rendering of the secondary text and price tag
  • + Effective glowing starburst effect
  • Serious distortion and spelling errors in the main 'MAGIC BURGER' title
  • Fails the 'exploded' request as the burger components are mostly stacked

Wan 2.5 (Preview)

  • + Excellent adherence to the 'exploded' view requirement with suspended components
  • + Perfect spelling and creative fiery font for the main title
  • + High-quality sense of motion with flying droplets and steam
  • Composition feels slightly more cluttered than Image A

Verdict: Wan 2.5 (Preview) significantly outperformed FLUX.2 [klein] 4B by correctly interpreting the 'exploded' layout and accurately spelling the main title. While FLUX.2 had impressive texture detail, its failure to space the ingredients and the garbled text made it ineffective for the prompt requirements.

Chalkboard Menu

Text-to-Image

“Handwritten-style chalkboard menu in a cozy café, all text rendered in the exact same realistic chalk handwriting style with natural variations in letter size, slight slant, and chalk texture — no printed or digital fonts anywhere on the board. Title at the top in elegant cursive chalk handwriting: ‘TODAY’S SPECIALS – APRIL 30, 2026’. Below it, three menu items also in the same handwritten chalk style: ‘Truffle Mushroom Risotto – $24’, ‘Grilled Octopus with Lemon & Herbs – $28’, ‘Brown Butter Chocolate Chip Cookies – $9’. At the very bottom, smaller text in the identical handwritten chalk style (slightly smaller but still clearly legible with the same handwriting characteristics): ‘All items made fresh daily • Ask about our gluten-free options’. Warm ambient café lighting, visible chalk dust and smudges, realistic handwriting imperfections, no clean printed text anywhere.”

FLUX.2 [klein] 4B
Wan 2.5 (Preview)
0% wins 0% ties 100% wins

AI Judge Analysis

FLUX.2 [klein] 4B

  • + Successfully renders a cursive title as requested.
  • + Realistic chalk texture with visible smudges and faint dust.
  • + Good lighting on the chalkboard surface.
  • Numerous spelling errors including 'Truffel Musheram', 'Ootrpous', and 'Brawn Buter'.
  • Poor spacing in the word 'SPECIALS' causing a large gap.
  • The font style shifts significantly between the header and the body text.

Wan 2.5 (Preview)

  • + Excellent spelling across all items, including complex words like 'Mushroom' and 'Octopus'.
  • + Better composition with a background that suggests a cozy café environment.
  • + Consistent handwriting style that looks hand-lettered while remaining perfectly legible.
  • The 'Brown Butter Chocolate Chip' line is slightly repetitive with 'Cookies' appearing on a new line with the price duplicated.
  • Missed the 'elegant cursive' requirement for the title, opting for all-caps sans-serif.

Verdict: Wan 2.5 (Preview) is the clear winner due to its superior spelling and presentation, successfully rendering the complex menu items with high accuracy. While FLUX.2 [klein] 4B attempted the cursive style requested in the prompt, it failed significantly on text coherence and spelling, making the menu difficult to read.

The Reversed Rodeo

Text-to-Image

“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”

FLUX.2 [klein] 4B
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [klein] 4B

  • + Excellent detail on the space suit and facial features within the helmet.
  • + Accurate representation of horse anatomy and leather tack.
  • + Clean, high-resolution background with a logical shadow on the planet surface.
  • Static composition feels less 'cinematic' than typical action shots.
  • The horse lacks some of the dynamic energy requested for a surreal prompt.

Wan 2.5 (Preview)

  • + Highly cinematic and dynamic composition with a sense of motion.
  • + Vibrant colors and beautiful nebulae in the background enhance the surreal theme.
  • + Successful lighting interaction between the cosmic elements and the horse's coat.
  • The astronaut's glove and hand positioning are slightly malformed.
  • The horse's mane and tail exhibit some unnatural digital smearing.

Verdict: Both models followed the specific prompt (astronaut on horse) and ignored the 'horse on top' distractor/clarification effectively. FLUX.2 [klein] 4B produces a much sharper, more realistic image with superior fine details on the characters, whereas Wan 2.5 (Preview) captures a better 'cinematic' and 'surreal' aesthetic through movement and color.

Outfit Transfer Challenge

Editing
Edit instruction

“Use Image 1 as the base person. Dress them in the exact elaborate outfit from Image 2 (including all layers, accessories, jewelry, and shoes). Carefully adapt the clothing to the body shape and pose in Image 1 while maintaining realistic fabric behavior, correct proportions, and perfect lighting/shadow matching. Keep the person’s exact face, hair, and background completely unchanged.”

Source
FLUX.2 [klein] 4B
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [klein] 4B

  • + Excellent preservation of the subject's unique identity, including hair and vitiligo patterns.
  • + Successfully transfers the coat, scarf, and jewelry while maintaining the original background.
  • + Correctly adapts the clothing to the subject's specific lean and pose.
  • The coat appears black instead of the dark navy seen in Image 2.
  • Added thick gold chains that were not present in the reference outfit.

Wan 2.5 (Preview)

  • + Perfectly replicates the specific colors and textures of the navy peacoat and scarf.
  • + Includes the sunglasses and watch from the reference image.
  • Completely failed to preserve the source person, replacing the subject's face, hair, and skin with the man from Image 2.
  • Ignored the instruction to keep the person's exact face and hair unchanged.

Verdict: FLUX.2 [klein] 4B followed the complex editing instructions much better by maintaining the identity and unique skin patterns of the person in Image 1 while applying the new clothes. Wan 2.5 (Preview) failed the core task of identity preservation, essentially just pasting the man from Image 2 into the background of Image 1.

The Capybara Taxi Driver

Text-to-Image

“Photorealistic scene inside a yellow New York taxi at night. A capybara is driving, wearing a yellow taxi driver cap and a dark jacket. It has a calm, professional expression and both front paws on the steering wheel. In the back seat sits a human businesswoman in a coat, looking at her phone with a completely normal, bored expression (as if this is just another normal ride). Through the windows you can see the streets of Manhattan at night with blurred lights. Realistic taxi interior, photorealistic, detailed fur and fabric, 35mm lens, night lighting with reflections, shallow depth of field.”

FLUX.2 [klein] 4B
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [klein] 4B

  • + Excellent interior perspective from the front seat
  • + High degree of realism in skin and fur textures
  • + Perfect portrayal of the bored passenger expression
  • The car interior feels more like a small vintage compact than a New York yellow cab

Wan 2.5 (Preview)

  • + Stronger 'New York Taxi' aesthetic with the exterior signage and lights
  • + Great composition showing the capybara squarely in the driver's seat
  • + Good adherence to outfit details like the driver's cap
  • The paws on the steering wheel look somewhat distorted and unnatural
  • The passenger's face is slightly less clear and detailed compared to Model A

Verdict: Both models captured the surreal prompt very well, but FLUX.2 [klein] 4B wins on sheer photorealistic quality and the natural interaction between the subjects. While Wan 2.5 (Preview) did a better job establishing the 'Taxi' exterior, its execution of the capybara's paws and the overall lighting feels slightly more like a composite image than a single cohesive photograph.

The Halloween Invitation

Text-to-Image

“Vintage gothic Halloween party invitation. Dark parchment poster, spooky border with webs and thorns, central glowing jack-o-lantern, bats, twisted trees, moody night sky. Add elegant gothic title text saying "Halloween Party Invitation", a small scroll banner saying "You are invited to a night of frights", and event details at the bottom: Date: 30.10.2026 Time: 7pm Location: The Arches, NYC Spooky but polished, cinematic lighting, square format.”

FLUX.2 [klein] 4B
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [klein] 4B

  • + Strong composition with a balanced thorny/web border
  • + Highly atmospheric and moody lighting
  • + Consistent gothic aesthetic across all elements
  • Several spelling errors in the title text
  • Missing '7pm' and typo in the date line
  • Word 'Location' is misspelled as 'Loeton'

Wan 2.5 (Preview)

  • + Perfect text rendering for all requested strings
  • + High-detail jack-o-lantern with a fiery inner glow
  • + Excellent color contrast between the parchment and the night sky
  • The transition from the circular sky to the parchment looks a bit like a sticker
  • Small bats have slightly distorted silhouettes

Verdict: While FLUX.2 [klein] 4B captures a more cohesive 'vintage' mood with better lighting, it fails significantly on text rendering and required information. Wan 2.5 (Preview) provides a much higher level of utility by rendering all requested text perfectly while maintaining high-quality visual assets and adhering to every prompt requirement.

Bald man challenge

Image Editing
Edit instruction

“Give the person a full, thick head of natural hair with realistic texture, density, and a natural hairline. Preserve facial features and lighting.”

Before After
FLUX.2 [klein] 4B
Before After
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [klein] 4B

  • + Excellent preservation of the original face, glasses, and background
  • + Natural, messy hair texture that matches the rugged setting
  • + Very realistic integration with the existing sideburns and beard

Wan 2.5 (Preview)

  • + Good preservation of the original jacket and environment
  • + Realistic hair color and thick density
  • Subtly altered the eyes and face shape, making the person look slightly different from the source
  • The hairline feels slightly artificial and stylized compared to the source's realism

Verdict: FLUX.2 [klein] 4B successfully added a realistic head of hair while perfectly preserving the identity of the person in the source image. Wan 2.5 (Preview) also performed well but introduced subtle changes to the facial features, resulting in a slight loss of identity.

Isometric Miniature Diorama Scenes

Text-to-Image

“Create a clear, 45° top-down isometric miniature 3D cartoon scene of Japan's signature dish: sushi, with soft refined textures, realistic PBR materials, gentle lighting, on a small raised diorama base with minimal garnish and plate. Solid light blue background. At top-center: 'JAPAN' in large bold text, 'SUSHI' below it, small flag icon. Perfectly centered, ultra-clean, high-clarity, square format.”

FLUX.2 [klein] 4B
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [klein] 4B

  • + Excellent realistic textures on the salmon and tray
  • + Accurate 45-degree isometric perspective
  • + High clarity and sharp rendering
  • Misspelled text as 'SUSH' instead of 'SUSHI'
  • The flag icon is incorrect/generic rather than the Japanese flag
  • Lacks the 'miniature 3D cartoon' aesthetic requested, appearing more like a photo of a toy

Wan 2.5 (Preview)

  • + Perfectly follows text instructions including 'JAPAN' and 'SUSHI'
  • + Accurately renders the Japanese flag icon
  • + Captures the 'miniature 3D cartoon' style with soft, rounded 3D shapes and a diorama base
  • The lighting is a bit more diffused than the high-clarity PBR requested
  • The perspective is slightly flatter than a true 45-degree isometric view

Verdict: Wan 2.5 (Preview) is the clear winner as it successfully rendered all requested text and symbols correctly, whereas FLUX.2 misspelled a basic word and failed to produce the correct flag. Additionally, Wan 2.5 better captured the specific '3D cartoon' and 'diorama base' stylistic prompts.

Over-the-top cartoon caricature

Editing
Edit instruction

“Create a caricature of me and my job. Make it exaggerated and humorous, incorporating my profession as a tv show anchor and my love for dogs and hockey.”

Source
FLUX.2 [klein] 4B
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [klein] 4B

  • + Excellent caricature style with great exaggerated facial features.
  • + Includes dogs and a very clear TV news anchor setting.
  • + The facial features maintain a recognizable link to the source image's smile.
  • Completely misses the 'hockey' requirement.
  • Gibberish text on the background screens reduces professionalism.

Wan 2.5 (Preview)

  • + Successfully incorporates all elements: tv anchor, dogs, and hockey.
  • + The character wears the same denim shirt as the source image.
  • + Includes creative details like the dog in a hockey jersey.
  • The caricature face style is slightly more generic and less sophisticated than model A.
  • Composition is a bit cluttered with the hockey stick and floating screen.

Verdict: Both models do a great job of creating a caricature while preserving the subject's likeliness. FLUX.2 [klein] 4B produces a much more polished illustration and captures the caricature essence better, but it fails to include the requested hockey theme. Wan 2.5 (Preview) is the preferred choice because it successfully integrates 'tv anchor', 'dogs', and 'hockey' into a single cohesive image, even managing to keep the subject's original outfit.

Adorable Baby Animals in Sunny Meadow

Text-to-Image

“Hyper-photorealistic scene of fluffy baby animals—a golden retriever puppy, tabby kitten, baby bunny, and red fox kit—with big expressive eyes and ultra-detailed soft fur, playfully chasing butterflies and tumbling together in a lush wildflower meadow, warm golden sunrise light with god rays and dew sparkles, joyful wholesome vibe, 8K masterpiece.”

FLUX.2 [klein] 4B
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [klein] 4B

  • + Excellent lighting and god rays that blend naturally into the scene
  • + High detail in the fox and puppy fur textures
  • + Pleasant, balanced composition with soft foreground bokeh
  • Missed the baby bunny entirely
  • Includes two kittens instead of one
  • Puppy and fox anatomies are slightly stiff and look static

Wan 2.5 (Preview)

  • + Successfully included all four requested animals (dog, cat, bunny, fox)
  • + Captured a much better sense of movement and 'tumbling' as requested
  • + Detailed dew drops and floating seeds add to the atmosphere
  • The fox's eyes appear overly saturated and slightly digital/artificial
  • The cat's tail anatomy looks a bit unnatural
  • Background lighting is slightly more overexposed than Model A

Verdict: While FLUX.2 [klein] 4B produces a slightly more polished and photographic finish, it failed the prompt by omitting the bunny and doubling the kittens. Wan 2.5 (Preview) followed the prompt perfectly, capturing all four specific animals with a dynamic sense of motion that matches the 'playfully chasing' and 'tumbling' description.

Studio Ghibli Anime Style

Editing
Edit instruction

“Transform this photo into a Studio Ghibli–inspired illustration. Use soft pastel colors, hand-painted textures, gentle lighting, dreamy backgrounds, and a warm, nostalgic mood”

Source
FLUX.2 [klein] 4B
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [klein] 4B

  • + Perfectly captures the soft, warm pastel aesthetic requested in the prompt.
  • + Excellent preservation of the original pose and composition of the meme.
  • + The hand-painted watercolor texture feels very authentic to Ghibli concept art.
  • The character expression on the right is too happy/serene, losing the original 'indignant' emotion of the meme.

Wan 2.5 (Preview)

  • + Retains the character expressions much better than Model A, keeping the original meme context intact.
  • + Excellent character design that looks very close to modern Ghibli or high-quality anime.
  • + Strong preservation of the source image backgrounds and lighting.
  • Colors are slightly more saturated than the requested 'soft pastel' palette.
  • The random floating leaves feel like a generic anime filter addition rather than a stylistic shift.

Verdict: Both models did an exceptional job of stylizing the famous 'distracted boyfriend' meme. FLUX.2 [klein] 4B followed the stylistic prompts for soft colors and hand-painted textures more closely, creating a beautiful nostalgic mood, but it lost the grumpy expression on the woman to the right. Wan 2.5 (Preview) maintained the perfect emotional context of the scene and clean line art, but it feels slightly more like a general anime filter rather than a painted Ghibli illustration.

Golden Hour Stroll

Image Editing
Edit instruction

“Add dynamic motion to this photo: make hair blow in the wind, add leaves flying, energetic and lively feel.”

Before After
FLUX.2 [klein] 4B
Before After
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [klein] 4B

  • + Excellent adherence to the 'leaves flying' prompt with realistic texture and color.
  • + Maintains character likeness and background details almost perfectly.
  • + Great hair dynamics that feel consistent with the environment.
  • The leash handle has been slightly altered/distorted compared to the source.
  • Some leaves have minor digital artifacts upon closer inspection.

Wan 2.5 (Preview)

  • + Successfully adds realistic blowing hair dynamics.
  • + Preserves the original image quality and characters very well.
  • The flying leaves appear as simplistic green shapes that look like digital stickers rather than real leaves.
  • A slight blur is added to the dog which wasn't in the original.

Verdict: Both models successfully added motion to the hair while preserving the identity of the person and dog. However, FLUX.2 [klein] 4B is the clear winner because it rendered the flying leaves with realistic brown textures and depth, whereas Wan 2.5 (Preview) produced bright green, flat shapes that looked out of place in the scene.

Vintage Cafe Logo

Text-to-Image

“Vintage minimalist restaurant logo for "Caffè Florian", retro cloche dome with steam and "Est. 1720" banner, classic typography, warm brown and cream tones, subtle texture on light background, vector emblem style.”

FLUX.2 [klein] 4B
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [klein] 4B

  • + Strong minimalism and vector-like quality
  • + Correct accent mark on the word Caffè
  • + Subtle, clean paper texture
  • Failed to spell the name correctly (FLAXTION instead of Florian)
  • Redundant 'Est. 1720' text appearing twice
  • Slightly clumsy banner design

Wan 2.5 (Preview)

  • + Perfect text rendering for both the name and the date
  • + Excellent composition with a professional banner design
  • + Beautiful vintage aesthetic with paper texture and border
  • The steam is a bit thick compared to the minimalist request
  • Slightly less 'minimalist' than a pure vector logo due to shading

Verdict: Wan 2.5 (Preview) produced a superior result by correctly spelling the restaurant name and integrating all prompt elements into a cohesive, professional logo layout. FLUX.2 [klein] 4B followed the minimalist vector style well but failed significantly on text accuracy and logic by repeating the date and misspelling 'Florian'.

Apollo 11: Journey to Tranquility

Text-to-Image

“Create a clean, modern vector infographic poster about the Apollo 11 mission. NASA-inspired palette (navy, white, muted red, light gray). Flat-vector style, crisp lines, consistent iconography, subtle gradients only. Steps (stop at landing): 1. Launch (Saturn Vicon) 2. Earth Orbit (Earth + orbit ring icon) 3. Translunar (trajectory arc icon) 4. Lunar Orbit (Moon + orbit ring icon) 5. Descent (lunar module descending icon) 6. Landing (lunar module on the surface icon) Small supporting elements (minimal text): • Crew strip: three silhouette icons with only last names: Armstrong, Aldrin, Collins. • Landing site marker: Moon pin labeled "Tranquility" only. Layout constraints: generous margins, large readable labels, clean background with subtle stars. Vector-only, print-poster look, high resolution.”

FLUX.2 [klein] 4B
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [klein] 4B

  • + Successfully used a light, airy palette that feels like a clean poster.
  • + Included the requested crew names at the bottom.
  • Text is largely gibberish or misspelled (e.g., 'APLLO', 'Oborot').
  • Failed to follow the specific 6-step logical flow, showing two Earths instead.
  • Vector style is inconsistent and slightly messy in the iconography.

Wan 2.5 (Preview)

  • + Excellent text rendering with no spelling errors in the labels.
  • + Strong logical flow following the requested mission steps from Earth to the Moon.
  • + Higher visual quality with crisp lines and a consistent professional vector style.
  • The layout is a bit crowded in the center.
  • Added an extra shuttle-like craft for the descent stage that wasn't part of the Saturn V stack.

Verdict: Wan 2.5 (Preview) produced a superior infographic that follows the logical steps of the Apollo mission and renders clear, readable text. FLUX.2 [klein] 4B failed significantly on the typography and provided a confusing layout with redundant icons and gibberish labels.

Next steps

Explore each model