Head to head
Esc

Models · slot A

to navigate to pick

Vidu Q2 ShengShu Technology Wan 2.7 Pro Alibaba

Settled by community votes across 20 shared challenges, with an AI judge weighing in on each.

Vidu Q2

19.8 arena score

#42 of 62 in Text-to-Image

Skill signature · Text-to-Image

Wan 2.7 Pro

21.0 arena score

#36 of 62 in Text-to-Image

Vote tally

Where the votes landed

Vidu Q2

0%

win rate

Ties

0%

Wan 2.7 Pro

0%

win rate

Shared challenges 20

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.”

Vidu Q2
Wan 2.7 Pro

AI Judge Analysis

Vidu Q2

  • + Excellent depiction of sunlight and shadows.
  • + Highly realistic glass reflections and refractions of the plant behind it.
  • + Very sharp textures on the book and wooden table.
  • The glass cube has an open top or missing side, as the book appears to be resting on thin glass edges with no solid top surface visible.

Wan 2.7 Pro

  • + Perfect adherence to all spatial instructions in the prompt.
  • + Naturalistic lighting from the window on the left as requested.
  • + Realistic material textures for the weathered wooden table.
  • The sphere's texture is slightly mottled/marbled rather than a solid blue sphere.
  • The glass cube has some internal vertical lines that look more like structural pillars than pure glass panes.

Verdict: Both models followed the complex spatial prompt very well, including the specific placement of the plant and sphere. Wan 2.7 Pro is the winner because it successfully rendered the cube as a solid object supporting the book, whereas Vidu Q2 depicted the glass with missing or inconsistently rendered top panes, making the physics of the scene look slightly off.

Man and Car in California

Editing
Edit instruction

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

Source
Vidu Q2
Wan 2.7 Pro

AI Judge Analysis

Vidu Q2

  • + Excellent preservation of the man's facial features and hair style from the source image.
  • + Accurately places the man behind the steering wheel in a driving position.
  • + High degree of consistency for the Rolls Royce design and color.
  • The sense of speed on the road looks a bit stylized/blurred compared to the static car.

Wan 2.7 Pro

  • + Beautiful landscape composition that looks like an authentic California coastline.
  • + Good preservation of the vehicle details.
  • Compleately failed to preserve the man's identity, replacing him with a generic individual.
  • The person is positioned in the passenger seat instead of the driver's seat.
  • The wheels on the car and the road lines have some perspective warping.

Verdict: Vidu Q2 is the clear winner because it successfully integrated the specific man from the source image into the driver's seat of the car. Wan 2.7 Pro failed the core editing task by replacing the man with a different person and placing him on the wrong side of the vehicle.

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.”

Vidu Q2
Wan 2.7 Pro

AI Judge Analysis

Vidu Q2

  • + Excellent depiction of skin texture and veins
  • + Realistic wear and tear on the bicycle frame
  • + Successfully captures the 'imperfect framing' and 'candid' feel requested
  • Significant anatomical errors in the hands and number of fingers
  • Structural issues with the bicycle chain and pedal placement
  • Lacks the requested motion blur on the background car

Wan 2.7 Pro

  • + Better overall composition and sense of place
  • + More coherent bicycle structure compared to Model A
  • + Good lighting and reflections on the wet pavement
  • The image is too clean and lacks the requested motion blur
  • The 'rain' is barely visible as fine noise rather than actual droplets or streaks
  • Slightly less 'candid' as the framing feels very centered and deliberate

Verdict: Vidu Q2 excels in textures and the gritty, candid feel of the prompt, but suffers from severe anatomical distortions in the subject's hands. Wan 2.7 Pro produces a cleaner, more structurally sound image that matches the setting well, though it misses specific technical details like motion blur and imperfect framing. Wan 2.7 Pro is the preferred image as its flaws are less distracting than the hand deformities in Vidu Q2.

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.”

Vidu Q2
Wan 2.7 Pro

AI Judge Analysis

Vidu Q2

  • + Excellent depiction of ornate engraved plate armor with high detail
  • + Strong adherence to lighting prompts with warm torchlight reflections
  • + Very high textural resolution on the leather straps and metal surfaces
  • The character looks a bit too pristine and 'model-like' for a battle-worn warrior
  • The hair braiding is simple compared to the beads requested

Wan 2.7 Pro

  • + Perfect interpretation of hair braided with small beads
  • + Captures the 'battle-worn' aesthetic more convincingly with realistic facial weathering
  • + Excellent bokeh sparks and background atmospheric depth
  • The leather strap across the chest lacks the crisp high-definition texture seen in the other model
  • Metal engraving is slightly less intricate than model A

Verdict: Both models performed exceptionally well, but Wan 2.7 Pro captured the character's 'battle-worn' essence and the specific hair detail (beaded braids) much more accurately. Vidu Q2 produced a more polished, high-contrast image with superior texture on the material surfaces, though the subject feels less like a gritty paladin and more like a clean fantasy hero.

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.”

Vidu Q2
Wan 2.7 Pro

AI Judge Analysis

Vidu Q2

  • + Successfully includes the requested vibrant accents.
  • + Maintains a high-key, clean white background.
  • Text is largely gibberish or heavily distorted, making it unusable as a menu.
  • Layout is chaotic with overlapping sections and inconsistent column widths.
  • The grid layout requested is poorly executed compared to the competitor.

Wan 2.7 Pro

  • + Excellent typography with mostly legible English text and coherent menu items.
  • + Strict adherence to the requested grid layout with professional spacing.
  • + Higher realism in food photography that matches the category labels.
  • The 'sides' and 'drinks' categories were not explicitly requested in the prompt, though they fit the context.
  • Text still contains minor spelling errors ('Bissue', 'Alferdo', 'Riautto').

Verdict: Wan 2.7 Pro is the clear winner as it produces a professional, usable menu layout with recognizable food and legible text. Vidu Q2 fails on the fundamental requirement of a menu by providing garbled text and a disorganized layout that lacks the requested clean grid structure.

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.”

Vidu Q2
Wan 2.7 Pro

AI Judge Analysis

Vidu Q2

  • + Excellent photorealistic texture on the burger bun and patty
  • + Text integration feels naturally blended with the fire and lighting
  • + Dynamic and chaotic splashing sauce adds to the motion feel
  • The currency symbol is incorrect, showing a crossed 'E' rather than a standard Euro symbol
  • The burger ingredients are somewhat clumped together rather than being fully 'exploded'

Wan 2.7 Pro

  • + Perfect adherence to all text requirements including the Euro symbol and starburst
  • + Superior 'exploded' layout with clearly separated ingredients like onions and cucumbers
  • + Professional graphic design balance and cleaner background composition
  • Texture on the cheese and patty looks slightly more plastic/CG than Model A
  • The flying herbs look a bit repetitive and flat

Verdict: Wan 2.7 Pro is the winner because it followed every specific instruction, including the starburst shape and the correct Euro currency symbol which Vidu Q2 failed to render accurately. While Vidu Q2 has slightly more realistic food textures, Wan 2.7 Pro captures the 'exploded' concept much better with its spread-out ingredients and superior layout for an advertisement.

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.”

Vidu Q2
Wan 2.7 Pro

AI Judge Analysis

Vidu Q2

  • + Excellent realistic chalk texture on the lettering
  • + Authentic smudging and chalkboard residue across the surface
  • Significant spelling errors throughout the menu items
  • Price on the first item is incorrect based on the prompt

Wan 2.7 Pro

  • + Perfect adherence to the requested text and prices
  • + Very clean and readable composition
  • + Excellent background environment with warm lighting
  • Handwriting looks slightly more like a digital font than natural chalk variations
  • The chalk texture is very uniform and lacks the grit seen in Model A

Verdict: Wan 2.7 Pro is the clear winner for its superior ability to follow complex text instructions perfectly, including the exact dates, menu items, and pricing. While Vidu Q2 captures a more realistic 'handwritten chalk' aesthetic with better texture, its failure to spell common words correctly and use the right prices makes it less useful for the specific prompt.

Pose & Character Mashup

Editing
Edit instruction

“Use Image 1 as the exact pose reference and Image 2 as the character reference. Recreate the person/character from Image 2 in the exact dynamic pose and body position from Image 1. Keep the exact face, hair, clothing style/details, and expression from Image 2. Match the lighting and environment of Image 1. The final image must show the character from Image 2 performing the precise action/pose from Image 1 with perfect anatomy and natural integration.”

Source
Vidu Q2
Wan 2.7 Pro

AI Judge Analysis

Vidu Q2

  • + Successfully integrated character features from Image 2 including facial likeness, sunglasses, and the scarf.
  • + Precise adaptation of the complex body pose from Image 1.
  • + High visual clarity and sharp detail preservation in the face.
  • The hands are severely distorted with extra fingers and unnatural anatomy.
  • The lighting transition from the character onto the background is slightly harsh.

Wan 2.7 Pro

  • + Perfectly preserved the original background and composition of Image 1.
  • Completely failed the edit instruction to change the character to the subject of Image 2.
  • Maintained the woman from the source image instead of performing the character swap.

Verdict: Vidu Q2 successfully followed the instruction to perform a character swap, expertly mapping the man's face and clothing onto the gymnast's pose, though it struggled with hand rendering. Wan 2.7 Pro failed the task entirely, providing an output identical to the pose reference image with no discernible changes.

The Reversed Rodeo

Text-to-Image

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

Vidu Q2
Wan 2.7 Pro

AI Judge Analysis

Vidu Q2

  • + Vibrant, cosmic color palette with beautiful galaxy details
  • + Dynamic, energetic pose for both horse and rider
  • Failed to follow the contradictory instruction of 'horse on top'
  • Anatomical issues with the horse's rear right leg connecting poorly to the body

Wan 2.7 Pro

  • + Naturalistic and clean lighting on the astronaut suit
  • + Good use of planetary elements in the background
  • Failed to follow the contradictory instruction of 'horse on top'
  • The horse's legs are thin and have inconsistent anatomy
  • Less 'surreal' or 'cinematic' than the other model, feeling more like a basic collage

Verdict: Both Vidu Q2 and Wan 2.7 Pro failed the 'trick' prompt instruction to have the horse on top of the astronaut, instead opting for the standard horse-rider configuration. Vidu Q2 is the preferred image because its surreal cosmic aesthetic better captures the high-detail cinematic feel requested, whereas Wan 2.7 Pro suffers from awkward horse anatomy and a flatter composition.

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
Vidu Q2
Wan 2.7 Pro

AI Judge Analysis

Vidu Q2

  • + Successfully transferred the pea coat, scarf, and accessories (watch, glasses) from the reference image.
  • + Maintained the color and pattern accuracy of the plaid scarf.
  • + Integrated the face and skin of the original subject fairly well despite some changes.
  • Failed to keep the face and hair completely unchanged, adding a mustache and altering features.
  • The background and overall composition have been significantly altered rather than preserved.
  • Strange sand-like textures are appearing over the clothing and skin.

Wan 2.7 Pro

  • + Successfully preserved the original person's facial features and the background environment.
  • + Captured a full-body view that attempts to include the shoes as requested.
  • + Realistic shadow and lighting integration with the surroundings.
  • Completely failed to use the correct outfit from Image 2, choosing a gold/black patterned suit instead of the blue pea coat and scarf.
  • Lost much of the vitiligo detail on the subject's torso by covering it with a different pattern.
  • Poor garment draping and proportion on the legs.

Verdict: Vidu Q2 followed the clothing instructions much better, accurately replicating the pea coat and scarf, but it failed to preserve the source subject's identity and the original background as requested. Wan 2.7 Pro succeeded in source preservation (keeping the face and beach unchanged) but failed the primary editing task by providing a completely different outfit that was not in the reference image. Vidu Q2 is the preferred winner because it actually performed the style transfer requested, despite some facial drift.

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.”

Vidu Q2
Wan 2.7 Pro

AI Judge Analysis

Vidu Q2

  • + Excellent adherence to the scene layout with the passenger correctly positioned in the back seat.
  • + High photographic realism in the car interior and lighting.
  • + The capybara's expression and posture perfectly match the 'professional' and 'paws on wheel' instructions.
  • The passenger's phone is slightly distorted.
  • The yellow cap is a bit stiff/plastic-looking compared to the fur.

Wan 2.7 Pro

  • + Excellent fur texture on the capybara's head.
  • + Good depiction of the bored expression on the businesswoman.
  • Failed the spatial layout by placing the passenger in the front passenger seat instead of the back seat.
  • The paws on the steering wheel look more like primate/human hands than capybara paws.
  • The seatbelt passes through the capybara's neck in a physically impossible way.

Verdict: Vidu Q2 is the clear winner as it correctly followed the instructions regarding the passenger being in the back seat and provided a much more coherent interior composition. Wan 2.7 Pro placed the businesswoman in the front seat and suffered from significant anatomical and clipping issues, notably the seatbelt merging into the capybara and the hands looking excessively human.

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.”

Vidu Q2
Wan 2.7 Pro

AI Judge Analysis

Vidu Q2

  • + Features very cinematic lighting on the jack-o-lantern and parchment texture
  • + Includes the thorns and twisted trees around the border as requested
  • Significant spelling errors in the title and banner text
  • Failed to render the correct date (2025 instead of 2026)
  • The 'night sky' is only visible behind the scroll edges, making the composition feel cramped

Wan 2.7 Pro

  • + Excellent text rendering with near-perfect spelling for all requested lines
  • + Highly detailed composition with a clear night sky, moon, and multiple layers
  • + Strong adherence to all prompt elements including the specific date and location
  • The art style is more like a clean digital illustration than a 'vintage' gothic poster
  • Less atmospheric 'dark parchment' feel compared to the other model

Verdict: Wan 2.7 Pro is the clear winner due to its superior text rendering and strict adherence to the requested event details, including the correct date and location. While Vidu Q2 captured a more atmospheric lighting style, it failed significantly on legibility and factual accuracy, which is critical for an invitation.

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
Vidu Q2
Before After
Wan 2.7 Pro

AI Judge Analysis

Vidu Q2

  • + Excellent preservation of the source background and clothing.
  • + The hair texture and lighting match the environment very well.
  • + Produces a very thick, full head of hair as requested.
  • The hairline is a bit low and looks slightly like a hairpiece due to the hard edge.
  • The hair is styled in a way that feels a bit unnatural for the character's rugged look.

Wan 2.7 Pro

  • + Natural and realistic hairline that blends well with the forehead.
  • + The messy, wavy style fits the rugged aesthetic of the character and scene.
  • + Perfect preservation of facial features and textures.
  • The hair feels slightly less 'thick' or 'full' compared to Model A, appearing a bit flat on top.
  • Slight blurring where the hair meets the background sky.

Verdict: Both models performed exceptionally well in preserving the source image while adding hair. Vidu Q2 provided the thickest hair, but Wan 2.7 Pro achieved a much more believable and natural hairline that looks like a genuine part of the subject's head.

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.”

Vidu Q2
Wan 2.7 Pro

AI Judge Analysis

Vidu Q2

  • + Excellent 3D miniature felt/clay aesthetic
  • + Strong, bold typography that is easy to read
  • + Includes a creative flag interpretation integrated with the text
  • The diorama base is a bit small for the plate
  • Slightly less realistic PBR material properties on the fish compared to model b

Wan 2.7 Pro

  • + Very clean, high-clarity isometric composition
  • + Superior PBR material rendering with realistic subsurface scattering on the sushi
  • + Sophisticated typography and professional layout
  • Includes extra elements like chopsticks and soy sauce not requested in the 'minimal' prompt
  • Floating artifacts in the top corners of the image

Verdict: Wan 2.7 Pro produces a more professional and realistic 3D render with beautiful material textures and a very clean layout. While Vidu Q2 captures the 'cartoon' aspect well, Wan 2.7 Pro's execution of the isometric diorama style is more polished and visually appealing, despite some minor floating artifacts in the background.

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
Vidu Q2
Wan 2.7 Pro

AI Judge Analysis

Vidu Q2

  • + Excellent character likeness to the source person.
  • + Clever integration of all themes with a news desk set on an ice rink.
  • + Preserves the original clothing (denim shirt and black t-shirt).
  • Anatomical issue with the right hand holding the microphone.
  • Minor rendering artifacts in the background mesh of the hockey goal.

Wan 2.7 Pro

  • + Successfully incorporates all prompt elements including pets and hockey team spirit.
  • + Clean caricature style with clear text rendering.
  • + Good composition with centered subject and background TV.
  • Loses the specific facial likeness of the source image.
  • Changed the character's clothing entirely from the source image.
  • The hockey stick/microphone hybrid is a bit strange visually.

Verdict: Vidu Q2 is the clear winner because it successfully creates a caricature that still looks exactly like the person in the source image, while also preserving her original outfit. It creatively blends the themes by placing a news desk directly onto a hockey rink, whereas Wan 2.7 Pro produces a more generic face and ignores the clothing from the reference photo.

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.”

Vidu Q2
Wan 2.7 Pro

AI Judge Analysis

Vidu Q2

  • + Bright and vibrant meadow with beautiful god rays
  • + Captures the 'tumbling' and interactive energy requested
  • + High detail on the individual flowers and butterfly wings
  • Generated two golden retriever puppies instead of the requested one
  • Anatomical issues on the fox's hind legs
  • Butterflies are repeated and look less integrated

Wan 2.7 Pro

  • + High degree of photorealism and fur texture
  • + Correct counting of the requested animals (one of each)
  • + Excellent composition focusing on the central interaction
  • Fox kit looks slightly older/larger than the other 'baby' animals
  • The kitten's pose is a bit awkward against the puppy's side

Verdict: Wan 2.7 Pro followed the counts in the prompt correctly, providing exactly one golden retriever, kitten, bunny, and fox, whereas Vidu Q2 added an extra puppy. Wan 2.7 Pro also features more realistic fur textures and higher overall clarity, making it the better interpretation of a 'hyper-photorealistic' scene.

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
Vidu Q2
Wan 2.7 Pro

AI Judge Analysis

Vidu Q2

  • + Excellent character design that authentically mimics the Ghibli anime style.
  • + Strong, clean line work typical of animated films.
  • + Maintains the distinct facial expressions and poses from the source image effectively.
  • The background is a bit generic and lacks the intricate hand-painted detail Ghibli is known for.
  • Colors are somewhat flat compared to a traditional watercolor aesthetic.

Wan 2.7 Pro

  • + Beautiful watercolor texture that captures the hand-painted feel of Ghibli background art.
  • + Soft, warm, and nostalgic color palette is very accurate to the prompt.
  • + Superior integration of characters into a dreamy, painterly environment.
  • The faces lean slightly more toward realism than the classic Ghibli character aesthetic.
  • Some minor loss of clarity in the line work due to the heavy texture.

Verdict: Both models do an excellent job of preserving the composition and subject matter of the original 'Distracted Boyfriend' meme. Vidu Q2 captures the specific 'anime character' look of Ghibli more accurately, but Wan 2.7 Pro is the overall winner for its masterful application of watercolor textures and nostalgic lighting, which more effectively transforms the entire image into a cohesive 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
Vidu Q2
Before After
Wan 2.7 Pro

AI Judge Analysis

Vidu Q2

  • + Excellent preservation of the woman's face and original features.
  • + Highly effective interpretation of hair blowing in the wind.
  • + Substantial number of leaves added to create a sense of environment.
  • The leaves feel somewhat flat and disconnected from the depth of the scene.
  • A small artifact is present on the dog's leash where it meets the hand.

Wan 2.7 Pro

  • + The hair motion is very dynamic and realistic, spreading naturally.
  • + The lighting on the dog and path is well-preserved.
  • + Leaves are integrated better into the scene's depth, with some appearing on the ground/grass.
  • The woman's facial features were slightly altered, especially around the eyes.
  • Fewer leaves overall compared to the 'dynamic' request.
  • A slight blur or ghosting artifact on some of the flying leaves.

Verdict: Both models successfully interpreted the dynamic motion request. Vidu Q2 did a better job of preserving the subject's identity, while Wan 2.7 Pro created a more naturalistic hair-flow effect and better spatially-aware leaf placement, though it slightly changed the woman's face. Vidu Q2 is the preferred winner for maintaining the structural integrity of the original photo while clearly fulfilling all prompt instructions.

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.”

Vidu Q2
Wan 2.7 Pro

AI Judge Analysis

Vidu Q2

  • + Clean vector-style coloring
  • + Effective use of warm brown and cream tones
  • + Correct cloche dome and steam iconography
  • Severe spelling hallucinations in the brand name
  • Messy typography with inconsistent letter shapes
  • Repeated text elements at the bottom

Wan 2.7 Pro

  • + High-quality vintage illustrative style
  • + Excellent typography with accurate spelling of 'Est. 1720'
  • + Cohesive round emblem composition
  • Slight misspelling of the name as 'Florion' instead of 'Florian'
  • Includes stray decorative elements in the corners not mentioned in the prompt

Verdict: Wan 2.7 Pro is the clear winner for its superior visual quality, professional layout, and legible typography which closely matches the requested vintage aesthetic. While Vidu Q2 followed the prompt's simplicity, it struggled significantly with text rendering, producing unintelligible words compared to the almost-perfect spelling and elegant design of Wan 2.7 Pro.

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.”

Vidu Q2
Wan 2.7 Pro

AI Judge Analysis

Vidu Q2

  • + Clean vector illustration style
  • + Includes all major requested visual components like the lunar module and planetary bodies
  • Text is largely gibberish and incoherent
  • Layout is disorganized and doesn't follow a logical timeline order
  • Failed to use the specific NASA-inspired navy palette as the primary background

Wan 2.7 Pro

  • + Excellent text rendering with accurate names and mission details
  • + Perfect adherence to the requested steps and chronological flow
  • + Strong color palette usage and professional infographic layout
  • Small typo in 'Descent' (rendered as DESCRIPT)
  • Minor artifacting on the NASA logo in the bottom corner

Verdict: Wan 2.7 Pro significantly outperformed Vidu Q2 by following the logical sequence of the mission steps and rendering highly legible, accurate text. While Vidu Q2 produced generic vector art with nonsense labels, Wan 2.7 Pro created a functional, educational infographic that accurately identifies the Apollo 11 crew and mission phases.

Next steps

Explore each model