Head to head
Esc

Models · slot A

to navigate to pick

Wan 2.5 (Preview) Alibaba Wan 2.7 Pro Alibaba

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

Wan 2.5 (Preview)

23.4 arena score

#27 of 62 in Text-to-Image

Skill signature · Text-to-Image

Wan 2.7 Pro

21.0 arena score

#37 of 62 in Text-to-Image

Vote tally

Where the votes landed

Wan 2.5 (Preview)

0%

win rate

Ties

0%

Wan 2.7 Pro

0%

win rate

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.”

Wan 2.5 (Preview)
Wan 2.7 Pro

AI Judge Analysis

Wan 2.5 (Preview)

  • + Excellent photographic quality with realistic dust particles in the light
  • + Vivid color saturation and strong use of depth of field
  • + Accurate representation of glass thickness and internal reflections
  • The sphere is quite large, pushing the definition of 'small' relative to the cube

Wan 2.7 Pro

  • + Better adherence to the 'small' scale of the sphere
  • + Visible window frame logically explains the lighting source provided in the prompt
  • + High detail on the wooden table texture and the fern foliage
  • The cube geometry looks slightly warped on the left vertical edge
  • The book edges appear a bit too perfectly sharp compared to the weathered table

Verdict: Both models followed the prompt instructions perfectly, including the complex spatial relationships of objects. Wan 2.5 (Preview) produced a more aesthetically pleasing, vibrant image with soft lighting, while Wan 2.7 Pro provided a more grounded, realistic scene with better relative scaling of the sphere and the inclusion of a literal window. Wan 2.5 (Preview) is slightly preferred for its superior artistic composition and lighting effects.

Man and Car in California

Editing
Edit instruction

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

Source
Wan 2.5 (Preview)
Wan 2.7 Pro

AI Judge Analysis

Wan 2.5 (Preview)

  • + Successfully preserved the identity and hairstyle of the man from the source image.
  • + Excellent preservation of the specific Rolls-Royce car model and details.
  • + Dynamic composition with effective motion blur on the wheels and road.
  • The man appears slightly small in the seat compared to the scale of the car.

Wan 2.7 Pro

  • + Beautiful scenic background and lighting for a California coastline setting.
  • + The car model is well-preserved with clear, sharp details.
  • Failed to preserve the man's identity, replacing him with a different person.
  • The steering wheel is Missing or misaligned with the driver's hands.

Verdict: Wan 2.5 (Preview) is the winner because it successfully integrated both source images by placing the correct man in the correct car. Wan 2.7 Pro provided a high-quality environment but failed the core editing task by replacing the man with a generic subject.

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.”

Wan 2.5 (Preview)
Wan 2.7 Pro

AI Judge Analysis

Wan 2.5 (Preview)

  • + Excellent shallow depth of field and bokeh
  • + Superior rendering of rain droplets and pavement reflections
  • + Highly realistic skin textures and hand details
  • Missed the request for motion blur on passing cars
  • Framing feels balanced rather than the requested 'imperfect' look

Wan 2.7 Pro

  • + Natural, candid positioning of the subject
  • + Captures an authentic Japanese urban background
  • + Good focus on the subject with realistic lighting
  • The bicycle frame has structural inconsistencies (floating pedal, disconnected seat post)
  • Lacks the requested 50mm shallow depth of field
  • Missing motion blur and noticeable rain effects

Verdict: Wan 2.5 (Preview) produced a significantly more cinematic and high-quality image with impressive detail in the skin and environmental effects like rain. While Wan 2.7 Pro captured a more 'candid' feel, it suffered from structural errors in the bicycle and failed to deliver the photographic specifics like shallow depth of field and visible rain.

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.”

Wan 2.5 (Preview)
Wan 2.7 Pro

AI Judge Analysis

Wan 2.5 (Preview)

  • + Excellent intricate engraving on the pauldrons
  • + High-contrast torchlight lighting creates a moody atmosphere
  • + Superior micro-textures on the frayed cloth underlayer
  • The beads in the hair look more like metallic studs or sequins than traditional beads
  • Skin texture appears a bit smooth despite the dirt

Wan 2.7 Pro

  • + Very lifelike skin texture with realistic fine wrinkles and pores
  • + Accurate depiction of hair beads and braided style
  • + Better execution of 'shallow depth of field' with natural bokeh sparks
  • The leather straps show some minor clipping/merging with the plate armor
  • Lighting is slightly flatter compared to the dramatic shadows in Image A

Verdict: Both models followed the prompt exceptionally well, but Wan 2.7 Pro is the winner due to its superior skin texture and more natural integration of the braided beads. While Wan 2.5 (Preview) offered more impressive engraving details on the armor, Wan 2.7 Pro feels more like a lived-in, cinematic portrait with a more convincing shallow depth of field.

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.”

Wan 2.5 (Preview)
Wan 2.7 Pro

AI Judge Analysis

Wan 2.5 (Preview)

  • + Excellent photographic quality for the food items
  • + Clear organized grid with distinct sections as requested
  • + Clean and bright white background
  • Poor typography with significant spelling errors
  • Limited food variety as many images look repetitive

Wan 2.7 Pro

  • + Highly realistic text and professional menu layout
  • + Wide variety of diverse food photos
  • + Sophisticated minimalist design with functional details like QR codes and social icons
  • The grid is slightly asymmetrical at the bottom
  • Text gets a bit messy in the very small product descriptions

Verdict: Wan 2.7 Pro is the clear winner as it produces a more functional and realistic menu design with legible English text and a logical layout. While Wan 2.5 (Preview) has high-quality image assets, its inability to render sensible text and its repetitive food varieties make it less useful for a professional design task.

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.”

Wan 2.5 (Preview)
Wan 2.7 Pro

AI judge analysis unavailable for this challenge.

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.”

Wan 2.5 (Preview)
Wan 2.7 Pro

AI Judge Analysis

Wan 2.5 (Preview)

  • + Excellent chalk texture including realistic dust smears and smudges.
  • + Text is dynamic with varying sizes and slants consistent with physical handwriting.
  • + Clear focus on the foreground board with a nice depth-of-field effect for the café background.
  • Failed to render the full text for 'Brown Butter Chocolate Chip Cookies', splitting it awkwardly.
  • The cursive elegant style requested for the title is not fully realized, appearing more like print.

Wan 2.7 Pro

  • + Successfully rendered all requested menu text perfectly without truncation.
  • + Composition is centered and balanced, making the menu very easy to read.
  • + Text variations and chalk texture are clean and consistent across the whole board.
  • The handwriting style looks slightly more like a digital font family than the organic, slanted handwriting seen in Model A.
  • The 'elegant cursive' for the title is quite simplified.

Verdict: Wan 2.7 Pro is the clear winner for prompt adherence, as it successfully completed the long text strings for the menu items that Wan 2.5 (Preview) cut off. While Wan 2.5 (Preview) featured a more realistic chalk smudge texture and organic handwriting slant, its failure to generate the full requested text makes it less useful for this specific task.

The Reversed Rodeo

Text-to-Image

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

Wan 2.5 (Preview)
Wan 2.7 Pro

AI Judge Analysis

Wan 2.5 (Preview)

  • + Excellent cinematic lighting and dynamic movement.
  • + High levels of detail in the horse's musculature and the astronaut's suit.
  • + Visually appealing composition with a vibrant nebula.
  • Failed the specific spatial instruction for the horse to be on top of the astronaut.

Wan 2.7 Pro

  • + Clean, high-resolution rendering.
  • + Interesting surreal touch with miniature planets floating in the foreground.
  • Failed the specific spatial instruction for the horse to be on top of the astronaut.
  • The horse's anatomical connection to the saddle and astronaut's legs is slightly awkward.

Verdict: Both Wan 2.5 (Preview) and Wan 2.7 Pro failed to follow the logical reversal requested in the prompt ('horse on top, not vice versa'), instead providing the common 'astronaut riding a horse' trope. Wan 2.5 (Preview) is the better image overall due to its cinematic lighting, dynamic pose, and superior integration of the characters into the environment.

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
Wan 2.5 (Preview)
Wan 2.7 Pro

AI Judge Analysis

Wan 2.5 (Preview)

  • + Successfully transferred the exact clothing items (coat, scarf, watch, ring) from Image 2.
  • + Maintained high visual quality and realistic lighting on the fabrics.
  • Failed the identity preservation requirement by replacing the first person's face and skin with the man from Image 2.
  • Altered the person's hair and facial features despite instructions to keep them unchanged.

Wan 2.7 Pro

  • + Successfully preserved the subject's identity, including his unique vitiligo patterns, face, and hair.
  • + Kept the background elements and full body pose consistent with Image 1.
  • Failed to use the requested outfit from Image 2, instead generating an unrelated gold-patterned blazer.
  • Missed the specific accessories like the sunglasses, plaid scarf, and blue jeans from the target image.

Verdict: Both models failed to follow the complete set of instructions. Wan 2.5 (Preview) perfectly captured the requested clothing but erroneously replaced the person's identity with the man from the reference image, whereas Wan 2.7 Pro correctly preserved the person's identity and skin patterns but failed to use the correct outfit from Image 2. Wan 2.7 Pro is slightly preferred for adhering to the complex identity preservation, which is typically the more difficult part of a 'base person' edit.

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.”

Wan 2.5 (Preview)
Wan 2.7 Pro

AI Judge Analysis

Wan 2.5 (Preview)

  • + Features a more cinematic composition with vivid night lighting and rain effects
  • + Perfectly captures the passenger in the back seat as requested
  • + Excellent capypara expression and detailed fur texture
  • The taxi sign is inexplicably situated on the hood/dashboard area rather than the roof

Wan 2.7 Pro

  • + Impressive fur and skin texture realism
  • + Correct lateral view through the window showing the city streets
  • Failed the spatial aspect of the prompt by placing the passenger in the front seat instead of the back
  • The capybara's hands look more human-like/primate-like than capybara paws

Verdict: Wan 2.5 (Preview) more accurately followed the spatial requirements of the prompt by placing the passenger in the back seat, even though the taxi's exterior light is misplaced on the dash. Wan 2.7 Pro had better overall photorealism and lighting, but placed the passenger in the front seat, which changed the narrative dynamic of the 'normal cab ride' requested.

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.”

Wan 2.5 (Preview)
Wan 2.7 Pro

AI Judge Analysis

Wan 2.5 (Preview)

  • + Excellent typography with a high-end 3D metallic feel.
  • + Dramatic cinematic lighting with realistic fire and smoke effects.
  • + Strong adherence to all text requirements with perfect legibility.
  • The circular central cutout creates a slightly disjointed overlap between the parchment and the sky.
  • The thorns in the border look a bit repetitive/digital.

Wan 2.7 Pro

  • + Beautiful illustrative style that feels like a vintage storybook.
  • + Richly detailed border including extra thematic elements like lanterns and a cauldron.
  • + Balanced composition that integrates the central scene seamlessly with the text.
  • The font for 'Halloween Party Invitation' is slightly less impactful than Model A.
  • Lighting is more flat and illustrative rather than cinematic as requested.

Verdict: Both models followed the prompt exceptionally well, producing professional-grade invitations with perfect text rendering. Wan 2.5 (Preview) produced a more modern, cinematic look with impressive lighting and 3D effects, while Wan 2.7 Pro delivered a more charming, detailed vintage illustration that feels more like a complete piece of art.

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
Wan 2.5 (Preview)
Before After
Wan 2.7 Pro

AI Judge Analysis

Wan 2.5 (Preview)

  • + Excellent full and thick hair density.
  • + Perfectly preserves the source image facial features and glasses.
  • + Very realistic hair texture and natural integration with the sideburns.
  • The hairstyle is slightly stylized/perfomed rather than just natural growth.

Wan 2.7 Pro

  • + Natural, realistic hairline and texture.
  • + Preserves the face and lighting from the source image accurately.
  • The hair feels a bit thinner or patchier near the top compared to the 'full, thick' request.
  • The integration with the glasses temples is slightly less clean than Model A.

Verdict: Both models succeeded at adding hair while preserving the identity and surroundings of the subject perfectly. Wan 2.5 (Preview) provided a more voluminous and flattering 'full, thick' head of hair as requested, whereas Wan 2.7 Pro opted for a slightly more receded and realistic thinning look that doesn't quite meet the 'full' descriptor as well.

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.”

Wan 2.5 (Preview)
Wan 2.7 Pro

AI Judge Analysis

Wan 2.5 (Preview)

  • + Excellent adherence to the 'minimal' prompt with a single focus piece
  • + Large, bold text that is very easy to read
  • + Soft, clean 3D render style with very smooth gradients
  • The salmon texture looks a bit plastic-like compared to realistic PBR
  • Text alignment overlaps slightly with the background edges

Wan 2.7 Pro

  • + Very high detail in textures, especially for the rice and salmon
  • + More accurate isometric 3D perspective
  • + Includes additional subtle details like chopsticks and soy sauce that enhance the scene
  • Included more items than the 'minimal garnish' requested
  • Text is a bit smaller and less 'bold' compared to model A

Verdict: Wan 2.5 (Preview) produced a very clean and simple 'icon-style' image that closely follows the minimalist requirement. However, Wan 2.7 Pro is the superior image due to its more sophisticated PBR material simulation, better isometric geometry, and significantly higher detail in the food textures themselves.

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
Wan 2.5 (Preview)
Wan 2.7 Pro

AI Judge Analysis

Wan 2.5 (Preview)

  • + Excellent caricature style with professional-level digital illustration quality
  • + Maintains the outfit from the source image to aid character recognition
  • + Perfectly incorporates all thematic elements like the news desk, dogs in jerseys, and a hockey game on screen.
  • The facial resemblance is slightly generic compared to the source image
  • The hand holding the microphone is a bit small.

Wan 2.7 Pro

  • + Stronger facial resemblance to the subject in the source image
  • + Creative use of a hockey stick as a microphone stand
  • + Incorporates nice touches like the paw-print lapel pin and dogs in hockey jerseys.
  • Text in speech bubbles is a bit generic and unnecessary
  • The background setting looks more like a living room with a large TV than a professional news set
  • The hands on the hockey stick are visually distorted and anatomically awkward.

Verdict: Both models successfully interpreted the prompt, but Wan 2.5 (Preview) produced a more cohesive and centered caricature that feels like a professional illustration. While Wan 2.7 Pro captured the subject's likeness better and had clever ideas like the hockey-mic, its execution was marred by awkward hand rendering and less polished composition.

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.”

Wan 2.5 (Preview)
Wan 2.7 Pro

AI Judge Analysis

Wan 2.5 (Preview)

  • + Excellent depiction of god rays and sunrise lighting.
  • + Dynamic, high-energy poses that match the 'tumbling' and 'chasing' prompt.
  • + Vibrant colors and high-impact visual appeal.
  • The fox kit has unnaturally bright, glowing blue eyes that look artificial.
  • Floating water droplets feel out of place and logically inconsistent with a sunrise meadow.

Wan 2.7 Pro

  • + More realistic anatomical features and eye colors for all animals.
  • + Better interaction and physical overlap between the animals, creating a cohesive group.
  • + Subtle, realistic dew sparkles and fur textures.
  • The kitten's facial expression and mouth look slightly distorted.
  • Slightly less 'masterpiece' feel in terms of dramatic lighting compared to the other model.

Verdict: Wan 2.5 (Preview) creates a more cinematic and dramatic image with superior lighting, but includes some AI-typical artifacts like glowing eyes and strange floating droplets. Wan 2.7 Pro offers a more grounded and realistic interpretation with better animal anatomy and interaction, making it more successful as a 'photorealistic' scene despite having slightly less dramatic lighting.

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
Wan 2.5 (Preview)
Wan 2.7 Pro

AI Judge Analysis

Wan 2.5 (Preview)

  • + Excellent adherence to the Studio Ghibli cel-animation character style.
  • + Correctly interprets the 'dreamy background' with soft lighting and floating leaves.
  • + Maintains character expressions and poses while translating them into a distinct anime aesthetic.
  • The man's face loses some of the specific likeness from the source image compared to model B.

Wan 2.7 Pro

  • + Beautiful watercolor texture that feels very much like Ghibli concept art or background paintings.
  • + High structural preservation of the original subjects' facial features.
  • Looks more like a filter applied over a photo rather than a complete redrawing into an illustration style.
  • The lighting is flat compared to the requested dreamy mood.

Verdict: Wan 2.5 (Preview) provided a much more transformative and accurate 'Studio Ghibli' result by redrawing the scene in a cel-shaded anime style with atmospheric elements like floating leaves. While Wan 2.7 Pro captured a beautiful hand-painted watercolor texture, it felt like a stylized filter over the original photo rather than a stylistic reimaging.

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
Wan 2.5 (Preview)
Before After
Wan 2.7 Pro

AI Judge Analysis

Wan 2.5 (Preview)

  • + Successfully added wind-blown hair effect
  • + Maintained the woman's facial features and clothing accurately
  • + Blurred the dog's tail to imply energetic motion
  • The added leaves look like static, bright green graphics rather than integrated natural elements
  • The movement in the hair appears slightly stiff

Wan 2.7 Pro

  • + Created a much more dynamic and natural hair flow
  • + The flying leaves have varied colors and motion blur that match the scene lighting
  • + High preservation of the source image details and subject
  • None notable for this specific edit request

Verdict: Wan 2.7 Pro is the clear winner as it successfully creates a high-energy, lively atmosphere with realistic motion. While Wan 2.5 (Preview) adds the requested elements, its leaves look like artificial stickers, whereas Wan 2.7 Pro integrates the leaves and hair movement with realistic lighting and motion blur.

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.”

Wan 2.5 (Preview)
Wan 2.7 Pro

AI Judge Analysis

Wan 2.5 (Preview)

  • + Excellent typography with correct spelling and accent mark
  • + Strong vector logo composition that feels professional and clean
  • + Textured background provides a convincing vintage paper feel
  • The cloche design is a bit generic and blocky compared to the text banner

Wan 2.7 Pro

  • + Beautifully detailed woodcut-style illustration of the cloche and steam
  • + Sophisticated emblem layout with nice laurel accents
  • + Successfully incorporates requested vintage color palette
  • Spelling error in the main text as Florian is spelled Florion
  • The composition is crowded with extraneous elements in the corners
  • Misinterpreted the cloche as a cake stand on a pedestal

Verdict: Wan 2.5 (Preview) produced a superior logo for actual use, as it followed the typography instructions perfectly, including the correct spelling and accent for 'Caffè Florian'. While Wan 2.7 Pro offered a more intricate illustration style, the spelling error and Busy background elements made it less effective as a clean vector emblem.

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.”

Wan 2.5 (Preview)
Wan 2.7 Pro

AI Judge Analysis

Wan 2.5 (Preview)

  • + Excellent iconography for the Saturn V and Lunar Module.
  • + Strong adherence to the requested NASA-inspired color palette.
  • + Readable, large typography for the main labels.
  • Confusing layout where labels for 'Descent' and 'Landing' have no associated icons.
  • Text spelling for 'Tranquility' is slightly off and Collins' portrait icon looks like a soldier.
  • Logical flow of the trajectory and icons is cluttered.

Wan 2.7 Pro

  • + Perfect logical flow of the infographic from top to bottom.
  • + Clean, professional vector style with high-quality supporting text and data.
  • + Better use of the flat-vector aesthetic with consistent iconography for all 6 steps.
  • Text rendering has minor errors like 'DESCRIPT' instead of 'DESCENT'.
  • The icons for the Earth and Moon are very small relative to the poster size.
  • The astronaut figures at the bottom are generic silhouettes rather than distinct portrayals.

Verdict: Wan 2.7 Pro is the clear winner for its superior infographic layout and logical progression, which perfectly follows the 6 requested steps in a clean vertical format. While Wan 2.5 (Preview) has more detailed individual illustrations, it fails to organize them into a coherent educational poster and leaves labels without corresponding icons. Wan 2.7 Pro also incorporates impressive supporting details like altitudes and velocities that enhance the modern infographic feel.

Next steps

Explore each model