ShengShu Technology's text-to-image and reference-to-image model with support for character consistency and multi-reference image processing
Settled by community votes across 20 shared challenges, with an AI judge weighing in on each.
Vidu Q2
#42 of 62 in Text-to-Image
Wan 2.7
#39 of 62 in Text-to-Image
Where the votes landed
Vidu Q2
0%
win rate
Ties
0%
Wan 2.7
0%
win rate
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.”
AI Judge Analysis
Vidu Q2
- + Excellent adherence to the glass cube prompt with realistic thick edges.
- + Very high visual quality and realistic textures on the book and sphere.
- + Beautiful lighting and shadow casting that matches the described window light.
- − The plant is more overhead than 'behind' the cube, though still partially visible through it.
- − The glass cube lacks a physical top panel, allowing the book to seemingly float or rest on the edges.
Wan 2.7
- + Accurately places the plant behind the cube as requested.
- + Correctly renders reflected light and internal reflections within the glass.
- + Good photorealistic texture on the weathered wooden table.
- − The internal geometry of the glass cube is inconsistent, with some edges appearing like mirrors.
- − The blue sphere has a slightly rough, mottled texture compared to the smooth sphere in the other image.
Verdict: Vidu Q2 produces a more aesthetically pleasing image with superior lighting and clarity, capturing the 'soft window light' perfectly. Wan 2.1 follows the spatial instructions better by placing the plant clearly behind the cube, but the image contains more confusing glass reflections that detract from the overall realism. Vidu Q2 is the winner for its professional photographic quality and cleaner composition.
Man and Car in California
Editing“Make a photo of the man driving the car down the California coastline”
AI Judge Analysis
Vidu Q2
- + Excellent preservation of the car's design and details.
- + The man from the source image is clearly recognizable and logically integrated into the driver's seat.
- + High visual quality with realistic motion blur and accurate lighting.
- − The man's scale relative to the car is slightly small.
- − Minor perspective issue where the car seems to be angled slightly differently than the road lane.
Wan 2.7
- + Natural lighting that blends the car into the coastal environment.
- + Good composition with the winding road and coastline.
- − Completely failed to use the man from the source image, substituting a distorted generic person.
- − The driver's face is severely malformed.
- − Lower resolution and more painterly texture compared to the source.
Verdict: Vidu Q2 is the clear winner as it successfully integrated the specific man and car from the source images into the new environment while maintaining high image fidelity. Wan 2.7 failed the primary editing task by replacing the subject with a distorted, unrecognizable 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.”
AI Judge Analysis
Vidu Q2
- + Excellent skin texture and facial details
- + Captured the 'imperfect framing' prompt with a tight, candid crop
- + Very convincing wet textures and refractions
- − Anatomical errors in the hands and several impossible bicycle parts
- − Background car is static with no motion blur as requested
Wan 2.7
- + Strong environment storytelling with a believable Japanese street scene
- + Captures the full silhouette and action of the man
- + Good composition and wet pavement reflections
- − Lacks motion blur on passing cars
- − Lower resolution/clarity on the subject's face compared to Model A
- − The street feels a bit 'clean' for a candid/imperfect frame prompt
Verdict: Vidu Q2 produces a much more intimate and high-fidelity image that perfectly captures the skin texture and 'imperfect framing' requested, though it suffers from significant structural AI artifacts in the bike and hands. Wan 2.1 provides a better sense of place and a more coherent full-body subject, but it feels more like a generic stock photo than a candid 50mm shot. Vidu Q2 is the preferred choice for its superior texture and adherence to the cinematic, close-up aesthetic requested.
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.”
AI Judge Analysis
Vidu Q2
- + Excellent metallic texture with realistic wear and orange-toned lighting reflections.
- + Beautiful intricate engraving on the armor and rich texture on the leather straps.
- + Superior cinematic lighting that creates more depth and visual interest.
- − The facial features look slightly too clean or 'airbrushed' for a battle-worn character.
- − Lower density of braids compared to the prompt's likely intent.
Wan 2.7
- + Perfect adherence to the 'hair braided with small beads' requirement with multiple visible braids.
- + Excellent skin texture featuring more realistic battle damage, dirt, and age lines.
- + Very strong adherence to the 'lifelike eyes' and 'faint scars' descriptors.
- − The armor engravings are slightly less sharp and detailed compared to the leather and skin.
- − The torch in the background is a bit distracting and less 'bokeh' than the abstract sparks in Model A.
Verdict: Both models performed exceptionally well, but Wan 2.7 is the winner for its superior adherence to the specific character details like the braided hair with beads and the gritty, battle-worn skin texture. While Vidu Q2 produced more aesthetically pleasing armor and cinematic lighting, Wan 2.7 felt more believable as a seasoned paladin with lifelike facial details.
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.”
AI Judge Analysis
Vidu Q2
- + Features multiple vibrant food photos with good clarity
- + Includes sections for appetizers, pizza, and mains as requested
- − Text consists of gibberish characters and severe letter distortions
- − Graphic elements like columns overlap and feel cluttered
Wan 2.7
- + Excellent typography with legible, realistic English text
- + Perfectly organized grid layout that follows the minimalist prompt
- + Professional composition featuring realistic restaurant branding and contact info
- − The layout is more of a flyer or digital menu than a traditional multi-page menu
- − Background includes out-of-frame props like a pen and herbs which weren't specifically requested
Verdict: Wan 2.7 significantly outperforms Vidu Q2 by producing legible, high-quality text and a clean, professional aesthetic. While Vidu Q2 struggles with nonsensical text characters and a chaotic layout, Wan 2.7 delivers a functional design that looks like a real-world restaurant menu.
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.”
AI Judge Analysis
Vidu Q2
- + Excellent photorealistic texture on the meat patty and buns
- + Strong, vibrant lighting that blends the subject into the fiery background
- + Clean and legible primary typography
- − The currency symbol is garbled/incorrect in the price tag
- − The burger arrangement is more 'stacked' than 'exploded' compared to the other model
Wan 2.7
- + Accurate rendering of the Euro currency symbol (€)
- + Dynamic exploded composition with more separation between ingredients
- + Consistent fiery effect applied across all text elements
- − The food textures look slightly more illustrative/rendered than photorealistic
- − Random flying seeds and cucumber slices were not explicitly requested
Verdict: Both models followed the complex prompt with high accuracy, but Wan 2.7 delivered a better 'exploded' effect and correctly rendered the requested Euro currency symbol. Vidu Q2 has more realistic textures for the food itself, but its failure on the currency symbol and a less dynamic composition make it the runner-up.
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.”
AI Judge Analysis
Vidu Q2
- + Excellent realistic chalk texture with smudges and natural variations
- + Handwriting feels organic and consistent with a hand-drawn style
- − Numerous spelling errors including 'Musshoom', 'Lemepun', and 'Octopd'
- − Incorrect price on the first item and garbled text at the bottom
Wan 2.7
- + Perfect text accuracy and spelling for all menu items
- + Clean and legible layout that follows all prompt instructions
- + Correct pricing and dates as requested
- − The text looks like a digital font rather than authentic hand-lettered chalk
- − Lacks the organic smudging and 'dusty' realism of a real chalkboard
Verdict: Wan 2.7 is the clear winner for its superior text rendering capabilities, accurately spelling every word and number from the prompt. While Vidu Q2 captures a much more authentic chalk texture and 'handwritten' feel, its complete inability to spell basic words makes it less useful for a menu-specific task.
Pose & Character Mashup
Editing“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.”
AI Judge Analysis
Vidu Q2
- + Successfully integrated nearly all character details from Image 2, including the sunglasses, scarf, and black sweatshirt.
- + Accurately replicated the complex leg-crossing pose and overall body position from Image 1.
- + Matched the yellow background and red ottoman from the source environment.
- − The hands have anatomical errors, specifically the lower left hand which has too many fingers.
- − The character's expression is slightly altered compared to the neutral confidence seen in Image 2.
Wan 2.7
- + Preserved the original composition of Image 1 perfectly.
- − Completely failed to perform the edit, essentially returning the source Image 1 with minor color adjustments.
- − Did not incorporate the character, clothing, or attributes from Image 2 at all.
Verdict: Vidu Q2 successfully completed the complex task of merging a character's identity and clothing with a specific dynamic pose, showing high prompt adherence despite some anatomical flaws in the hands. Wan 2.7 failed the task entirely, providing an output that is nearly identical to one of the source images without applying the requested character swap.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
AI Judge Analysis
Vidu Q2
- + Vibrant color palette with nebula-like skin on the horse enhancing the surreal theme.
- + High level of cinematic lighting and glowing particles.
- + Good integration of the character into the fantastical environment.
- − The astronaut's left leg position is anatomically awkward relative to the horse's back.
Wan 2.7
- + Excellent anatomical rendering of both the astronaut's suit and the horse.
- + Clearer background elements with realistic planets and galaxies.
- + Better composition and use of negative space.
- − The horse's design is slightly conventional and less 'surreal' than the horse in Vidu Q2.
Verdict: Both models failed to follow the trick instruction 'horse on top, not vice versa,' instead providing the standard astronaut-on-horse image. Between the two, Wan 2.7 is the stronger image due to its superior anatomical correctness and clean, high-resolution details in the environment, whereas Vidu Q2 leans more into the surreal prompt with its glowing nebula horse.
Outfit Transfer Challenge
Editing“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.”
AI Judge Analysis
Vidu Q2
- + Successfully transferred the exact clothing items (peacoat, plaid scarf, watch, sunglasses) from Image 2.
- + Maintains the skin vitiligo patterns on the arm with high consistency to Image 1.
- + Accurately places the sand texture on the arm and face.
Wan 2.7
- + Maintains the subject's exact facial features and skin condition significantly better than the competitor.
- + Preserves the original background and composition of Image 1 perfectly.
- + Naturally integrates the vitiligo pattern onto the hands and neck.
- − Completely failed to use the outfit from Image 2, generating a generic black and gold suit instead.
- − Incorrectly changed the pose of the subject's legs from Image 1.
- − Added excessive jewelry that was not present in either source image.
Verdict: Vidu Q2 is the clear winner for following the primary instruction of transferring the outfit from Image 2, including the peacoat, scarf, and accessories. While Vidu Q2 slightly altered the subject's face (adding a mustache and changing eye shape), Wan 2.7 failed the core task by generating an entirely different, regal outfit that bore no resemblance to the reference image.
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.”
AI Judge Analysis
Vidu Q2
- + Excellent internal space logic with the passenger correctly placed in the rear seat back.
- + High-quality lighting and reflections on the car window and interior surfaces.
- + Detailed fur texture and realistic interaction between the capybara's paws and the steering wheel.
- − The passenger's phone is slightly distorted/elongated.
- − The driver's jacket looks more like a modern mechanic's shirt than a traditional uniform.
Wan 2.7
- + The capybara's expression is very calm and fits the prompt well.
- + The taxi rooftop light is visible, adding to the exterior realism.
- − Failed the spatial prompt by putting the passenger in the front seat instead of the back.
- − The capybara's paws are rendered with strange, multiple sharp claws that look unnatural.
- − The car's door pillar is missing, creating a nonsensical joined window space.
Verdict: Vidu Q2 is the clear winner as it correctly followed the spatial instruction to place the passenger in the back seat, whereas Wan 2.7 placed her in the front next to the driver. Vidu Q2 also features much more realistic lighting and anatomy for the capybara's paws compared to the claw-like appendages in the competing image.
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.”
AI Judge Analysis
Vidu Q2
- + Features more cinematic lighting with a glowing parchment effect.
- + Dynamic border with thorns and cobwebs that feels more organic.
- − Several severe spelling errors including 'Intovigtion' and 'invieed'.
- − Incorrect date and time formatting (30.70.2025 and Tmm).
Wan 2.7
- + Perfect text rendering for all requested fields including the title and event details.
- + Highly detailed and clean vintage illustration style with consistent borders.
- + Accurately follows the specific date (30.10.2026) and instructions.
- − The 'scroll banner' is more of a flat ribbon at the bottom rather than a central feature.
- − Slightly less 'moody' or dark than the prompt suggested, leaning towards a clean illustration.
Verdict: Wan 2.7 is the clear winner due to its superior text rendering, correctly spelling every requested word and date whereas Vidu Q2 suffered from significant typos and hallucinated numbers. While Vidu Q2 had a slightly more atmospheric lighting style, Wan 2.7 produced a professional-grade invitation that is actually usable for its intended purpose.
Bald man challenge
Image Editing“Give the person a full, thick head of natural hair with realistic texture, density, and a natural hairline. Preserve facial features and lighting.”
AI Judge Analysis
Vidu Q2
- + Successfully adds thick hair while keeping the background and clothing identical.
- + The hair texture matches the rugged aesthetic of the original image.
- − The hairline is a bit messy and slightly obscures the glasses frame.
- − The forehead area shows some minor blending artifacts where the hair meets the skin.
Wan 2.7
- + Adds a very natural, well-integrated head of hair with realistic volume.
- + Preserves facial features, glasses, and lighting perfectly.
- + Excellent blending at the temples and hairline.
- − The hair is slightly less 'thick' than Model A, though still very realistic.
Verdict: Both models performed excellent edits, perfectly preserving the source image's lighting, clothing, and background. Wan 2.7 is the winner because the integration of the hair is more seamless, whereas Vidu Q2 has slight artifacts where the hair meets the forehead and glasses.
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.”
AI Judge Analysis
Vidu Q2
- + Excellent typography with a clean, pillowy 3D effect.
- + High-quality material rendering for the fish and rice textures.
- + Creative interpretation of the flag as an physical icon within the scene.
- − Lighting is a bit harsh on the sushi toppings leading to blown-out highlights.
- − The base diorama has strange, unidentifiable blobs on the corners.
Wan 2.7
- + Perfect adherence to the 45-degree isometric perspective.
- + Very clean and organized composition that emphasizes the 'miniature' feel.
- + Accurate rendering of multiple sushi types and condiments like wasabi and ginger.
- − The text 'JAPAN' is slightly misaligned horizontally.
- − The flag icon is a simple 2D graphic rather than a 3D asset.
Verdict: Both models followed the prompt exceptionally well, but Wan 2.7 provides a superior isometric layout and more variety in the sushi components. While Vidu Q2 has more impressive individual textures and better 3D typography, Wan 2.7's composition feels more balanced and professional as a miniature diorama.
Over-the-top cartoon caricature
Editing“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.”
AI Judge Analysis
Vidu Q2
- + Excellent caricature style that maintains a strong likeness to the source person.
- + Successfully integrates hockey (rink background, puck, net), TV news (microphone, desk), and dogs in a cohesive scene.
- + High visual clarity with clean lines and vibrant colors.
- − The fingers on the hand holding the microphone are anatomicaly distorted.
- − The small dog on the right is standing on a stack of papers in a somewhat awkward way.
Wan 2.7
- + Creative use of speech bubbles to emphasize the themes of the request.
- + Includes a humorous detail of a dog wearing a hockey helmet.
- + Preserves the selfie-style pose from the source image.
- − The facial features are significantly altered, losing much of the likeness from the source photo.
- − Contains a spelling error in the speech bubble ('Rolee' instead of 'Rule').
- − The composition feels a bit cluttered with overlapping elements.
Verdict: Vidu Q2 is the winner because it creates a high-quality caricature that is clearly recognizable as the person in the source image, whereas Wan 2.7 creates a more generic face. Vidu Q2 also does a superior job of integrating the professional elements (news desk and microphone) with the hobbies (hockey rink background and dogs) into a single, polished illustration.
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.”
AI Judge Analysis
Vidu Q2
- + Excellent dynamic composition with a sense of playful movement.
- + Beautiful color palette with vibrant wildflowers and warm lighting.
- + Very soft, detailed fur textures on all animals.
- − Includes two golden retriever puppies instead of one.
- − The fox kit has slightly stylized, almost cartoonish eyes compared to the others.
Wan 2.7
- + Perfect adherence to the count of animals requested.
- + Great depiction of 'god rays' and dew sparkles as requested in the prompt.
- + High-quality fur detail and naturalistic lighting on the subjects.
- − The kitten's pose and anatomy (standing on the bunny) look a bit awkward.
- − The composition is more static and cluttered compared to the other image.
Verdict: Wan 2.7 followed the prompt's count more accurately by including exactly one of each animal, and it captured the 'god rays' effect beautifully. However, Vidu Q2 produced a more joyful and dynamic composition with better overall visual appeal despite adding an extra puppy. Wan 2.7 is the winner for better prompt adherence and atmospheric lighting.
Studio Ghibli Anime Style
Editing“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”
AI Judge Analysis
Vidu Q2
- + Excellent adherence to the Studio Ghibli art style including eye and mouth shapes.
- + Maintains clear, vibrant, and clean line work typical of modern anime.
- + Perfectly captures the exaggerated expressions requested in an illustrative format.
- − The man's hand on his hip looks a bit malformed compared to the source.
Wan 2.7
- + Successfully applies a soft, hand-painted watercolor texture.
- + Preserves the facial features and likeness of the original people more accurately.
- + Excellent use of warm, nostalgic, and dreamy lighting.
- − Does not fully commit to the specific 'Ghibli' aesthetic, leaning more toward a general watercolor portrait.
- − The foreground woman's face looks slightly uncanny between realism and illustration.
Verdict: Vidu Q2 is the clear winner for prompt adherence as it successfully translates the source image into the iconic Studio Ghibli character design style with clean line art. Wan 2.7 provides a beautiful watercolor effect that matches the 'nostalgic' mood instructions but fails to capture the specific animation style requested, maintaining too much realism in the facial structures.
Golden Hour Stroll
Image Editing“Add dynamic motion to this photo: make hair blow in the wind, add leaves flying, energetic and lively feel.”
AI Judge Analysis
Vidu Q2
- + Excellent adherence to the 'flying leaves' request with a large quantity of colorful leaves.
- + Effective hair motion that creates a clear sense of wind direction.
- + Perfect preservation of the face, clothing, and background details.
Wan 2.7
- + Natural and realistic hair flow that feels integrated with the subject.
- + Strong preservation of the original image's lighting and colors.
- + Good sense of motion without overwhelming the scene.
- − The 'flying leaves' are significantly less prominent compared to the result in Image A.
- − Several leaves appear as blurry brown smudges rather than distinct leaf shapes.
Verdict: Vidu Q2 is the clear winner as it more fully realized the user's request for an 'energetic and lively' feel by adding a generous amount of dynamic orange leaves that pop against the green background. While Wan 2.7 produced a very natural hair edit, its leaf additions were sparse and lacked the visual impact requested by the prompt.
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.”
AI Judge Analysis
Vidu Q2
- + Successfully captures the requested steam effect inside the cloche.
- + Good use of color tones matching the warm brown and cream request.
- − Significant spelling errors throughout the logo including 'Farmiin' and 'Fopli20'.
- − The typography is messy and overlaps with the banner border.
Wan 2.7
- + Excellent layout with a clean vector emblem style.
- + Very accurate spelling for the 'Est. 1720' banner and legible typography.
- + Excellent source preservation and subtle paper texture on the background.
- − Mistyped 'Florian' as 'Florion'.
- − The steam effect is a bit static and illustrative rather than atmospheric.
Verdict: Wan 2.7 is the clear winner as it produces a professional, usable vector-style logo with clean lines and mostly accurate text. Vidu Q2 fails on basic typography, resulting in garbled text that renders the logo unusable despite the nice cloche illustration.
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.”
AI Judge Analysis
Vidu Q2
- + Clean vector illustration style.
- + Distinct and high-quality iconography for the lunar modules.
- − Nonsense text for almost every label.
- − Logical flow is disjointed and does not follow the requested 1-6 step sequence.
- − Palette is overly desaturated compared to the NASA-inspired request.
Wan 2.7
- + Excellent text rendering with legible and accurate labels.
- + Follows the requested 6-step mission sequence perfectly.
- + High adherence to the NASA-inspired color palette and modern infographic layout.
- − Small minor typo in 'DESCRIPT' (meant to be DESCENT).
- − Minor typo in 'Tranquiliry'.
Verdict: Wan 2.7 significantly outperformed Vidu Q2 by producing a logical, legible, and accurate infographic which followed the prompt's sequence step-by-step. While Vidu Q2 had nice vector illustrations, the text was unintelligible gibberish and it failed to organize the mission stages correctly. Wan 2.7 effectively captured the NASA aesthetic with clean typography and relevant technical data points.
Explore each model
Alibaba's Wan 2.7 image generation and editing model for text-to-image, reference-guided generation, and instruction-based image edits