Alibaba's text-to-image and image-to-image generation model from the Wan AI suite, offering high-quality visual generation capabilities
Settled by community votes across 19 shared challenges, with an AI judge weighing in on each.
Wan 2.5 (Preview)
#27 of 62 in Text-to-Image
Wan 2.6
#28 of 62 in Text-to-Image
Where the votes landed
Wan 2.5 (Preview)
0%
win rate
Ties
0%
Wan 2.6
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
Wan 2.5 (Preview)
- + Excellent photographic quality with realistic dust motes and soft bokeh.
- + High-quality texture on the red book and the wooden table.
- + Clean, minimalist composition that looks professional.
- − The blue sphere is completely opaque, lacking global illumination/refraction inside the glass cube.
- − Odd floating reflection/artifact directly under the book on the top glass pane.
Wan 2.6
- + Successfully captured the sphere as translucent glass rather than opaque matte.
- + Strong adherence to the 'window light from the left' instruction with visible window frame shadows.
- + The plant is clearly behind the cube and visible through the glass.
- − The glass cube has some structural inconsistencies in its edges.
- − The scale of the 'small' sphere is slightly large relative to the cube.
Verdict: Both models followed all spatial instructions accurately. Wan 2.5 (Preview) produced a more aesthetically pleasing, high-end photograph with beautiful lighting, though the sphere lacked realistic glass properties. Wan 2.6 did a better job with the material properties of the glass sphere and the specific direction of the window light, but the overall image feels slightly less polished.
Man and Car in California
Editing“Make a photo of the man driving the car down the California coastline”
AI Judge Analysis
Wan 2.5 (Preview)
- + Successfully preserved the original car model and its orientation.
- + Accurately represents a generic California coastline background.
- − The man is poorly rendered and too small to detail.
- − The wheels suffer from severe motion blur artifacts that look unnatural.
Wan 2.6
- + The man is clearly visible and his likeness is well-preserved from the source.
- + High visual quality with a more dynamic and expansive landscape.
- − The car model was significantly altered and shortened from the original source.
- − The perspective shift resulted in losing the iconic front grille of the vehicle.
Verdict: Wan 2.5 (Preview) is better at keeping the original car's structure and orientation but fails to include a recognizable person. Wan 2.6 provides a much higher-quality character integration that matches the source image perfectly, though it compromises the car's original proportions and design. Wan 2.6 is preferred for successfully executing the most difficult part of the edit prompt.
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
Wan 2.5 (Preview)
- + Excellent detail in the reflections on the wet pavement
- + Anatomically correct hands and realistic skin texture
- + Strong composition with a clear, sharp focus on the subject
- − Lacks visible motion blur from passing cars as requested
- − Rain effect is slightly less atmospheric compared to the competitor
Wan 2.6
- + Successfully incorporates motion blur on passing vehicles
- + Highly realistic depiction of water droplets on the man's jacket
- + Captures a gritty, cinematic street atmosphere with 'imperfect' framing
- − Minor anatomical inconsistency in the hands and how the tool is held
- − Face texture is a bit harsher and less natural than Image A
Verdict: Wan 2.5 (Preview) produces a cleaner, more technically proficient image with superior hand details and skin textures. However, Wan 2.6 better adheres to the specific stylistic requests of the prompt, including the motion blur and the gritty, candid atmosphere of a rainy street. Wan 2.6 is the preferred choice for following the specific atmospheric cues, despite minor rendering artifacts in the hands.
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
Wan 2.5 (Preview)
- + Excellent clarity on the engraved armor patterns.
- + Clean facial features with realistic textures.
- + Effective use of warm lighting on the shoulder plate.
- − The beads in the hair look more like modern piercings or studs.
- − Character looks a bit too young and clean for 'battle-worn'.
Wan 2.6
- + Superb adherence to 'battle-worn' with grit, sweat, and realistic dirt.
- + Excellent interpretation of hair beads as decorative jewelry.
- + Highly detailed texture on the leather straps and frayed cloth.
- − Slightly more cluttered composition compared to the cleaner focus of Model A.
Verdict: Wan 2.6 is the clear winner as it captures the 'battle-worn' atmosphere much more effectively than Wan 2.5 (Preview). Wan 2.6 provides superior detail on the leather textures, more creative beadwork in the hair, and a more convincing facial expression that communicates the fatigue of a paladin.
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
Wan 2.5 (Preview)
- + Organized grid layout specifically following the three requested sections
- + Consistent lighting and plating style across all food photography
- + Cleaner font choice for a minimalist aesthetic
- − Nonsensical placeholder text even for large headers
- − Logical errors in categorization, such as placing pizza slices in the mains section
Wan 2.6
- + Includes realistic pricing and better text structure for a menu
- + Vibrant graphic design accents that match the prompt's request
- + High-quality, appetizing food photography with variety
- − Layout is cluttered with overlapping images and lacks clear whitespace
- − Misaligned headers where 'Appetizers' points to a pizza and 'Pizza' is listed twice in text lists
Verdict: Wan 2.5 (Preview) produces a much cleaner, more 'minimalist' design that adheres to the requested grid structure, though its text logic is poor. Wan 2.6 offers more realistic menu elements like pricing and vibrant accents but suffers from a cluttered composition and repetitive section headers. Overall, Wan 2.5 feels like a more professional design template for casual dining.
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
Wan 2.5 (Preview)
- + Excellent font rendering with a creative melting cheese and fire effect.
- + Clean, professional layout perfect for a digital advertisement.
- + Realistic burger textures and consistent light source from the embers.
- − The 'exploded' effect feels slightly static compared to the prompt's request for motion.
Wan 2.6
- + Dynamic 'exploded' composition with sauce dripping and ingredients angled for motion.
- + Intense fire and smoke effects that match the 'fiery' theme perfectly.
- + The text integration into the flames is very impactful.
- − The 'LIMITED TIME ONLY' text is partially obscured by floor flames, reducing legibility.
- − The burger toppings are slightly overlapping, making the individual components less distinct than Model A.
Verdict: Wan 2.5 (Preview) produces a cleaner, more legible advertisement with superior typography and a polished commercial feel. While Wan 2.6 captures the 'dynamic' and 'fiery' aspects with more energy, Wan 2.5 is the preferred choice for a professional ad due to its better balance and clear hierarchy of information.
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
Wan 2.5 (Preview)
- + Excellent text legibility and accuracy
- + Captures the chalkboard aesthetic with realistic smudges
- − The text style looks slightly more like a digital marker brush than real chalk
- − Missing the 'Herbs' portion of the second menu item
Wan 2.6
- + Superb chalk texture with realistic dust and varying opacity
- + Follows the text prompt precisely including the final menu item
- + Excellent 'elegant cursive' interpretation for the title
- − Slightly lower contrast makes the bottom text a bit harder to read
- − The chalk dust at the bottom looks slightly clumped
Verdict: Both models performed exceptionally well on typography and layout. Wan 2.6 is the winner because it successfully included all requested text ('Herbs' and 'Cookies') and provided a much more convincing chalk texture compared to the smoother, marker-like appearance in Wan 2.5 (Preview).
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
AI Judge Analysis
Wan 2.5 (Preview)
- + High visual clarity and sharp textures on the horse's coat.
- + Cinematic lighting with a clear sense of depth and scale.
- + Dynamic composition with the horse appearing to gallop over the curvature of a planet.
- − Failed the primary negative constraint: the astronaut is riding the horse instead of the horse riding the astronaut.
- − Anatomical issues with the horse's legs, specifically the rear left leg extending awkwardly from the body.
Wan 2.6
- + Beautiful lighting effects and nebula colors in the background.
- + Detailed rendering of the space suit and horse tack.
- − Failed the primary negative constraint: the astronaut is riding the horse instead of the horse riding the astronaut.
- − The trailing reins appear to be floating or disconnected in an illogical way behind the astronaut.
Verdict: Both Wan 2.5 (Preview) and Wan 2.6 failed to follow the specific spatial instruction to place the 'horse on top' of the astronaut, instead providing the cliché interpretation of a 'space cowboy.' Wan 2.5 (Preview) is slightly preferred due to better resolution and a more grounded cinematic composition, despite the anatomical errors in the horse's legs.
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
Wan 2.5 (Preview)
- + Successfully replicates the outfit, jewelry, and sunglasses from Image 2.
- + Maintains high visual clarity and matches the lighting of the background well.
- − Failed the primary identity preservation constraint by replacing the face and hair of the person in Image 1 with the person from Image 2.
Wan 2.6
- + Correctly preserves the identity, unique skin patterns, hair, and sand on the face of the person in Image 1.
- + Accurately applies the coat, scarf, and sunglasses from Image 2 to the target subject.
- + Excellent source preservation of the background and wooden structure.
- − The scarf pattern is slightly modified (more red tones) compared to the original in Image 2.
Verdict: Wan 2.5 (Preview) failed the fundamental requirement of identity preservation, essentially pasting the head of the man from Image 2 onto the scene. Wan 2.6 perfectly followed all instructions, keeping the specific features of the person in Image 1 while realistically composting the complex layers of clothing and accessories from Image 2.
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
Wan 2.5 (Preview)
- + Excellent photorealistic texture on the capybara's fur and the taxi dashboard
- + Dynamic composition with a more vibrant, neon-lit New York atmosphere
- + Strong focus on the interior details like the meter and steering wheel placement
- − The capybara's front paws look more like primate hands than rodent paws
- − The taxi roof light is positioned oddly as if visible through the windshield
Wan 2.6
- + Better anatomical representation of capybara paws on the steering wheel
- + Very convincing bored expression on the passenger that matches the prompt perfectly
- + Natural lighting and rain effects on the window glass
- − The composition is slightly less symmetrical with the passenger feeling very close to the driver
- − Slightly more blurring on the character details compared to Model A
Verdict: Both Wan 2.5 (Preview) and Wan 2.6 followed the prompt exceptionally well, capturing the surreal yet professional atmosphere. Wan 2.5 (Preview) has slightly higher sharpness and more vibrant 'New York' colors, but Wan 2.6 wins on realism by correctly depicting the capybara's paws and the bored, mundane expression of the businesswoman.
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
Wan 2.5 (Preview)
- + Excellent text rendering with no spelling errors across all sections.
- + Clean, polished 3D-rendering style with high-quality cinematic lighting.
- + Well-defined border integration combining thorns, webs, and parchment.
- − The parchment texture is a bit too clean and light for a 'dark parchment' request.
- − Layout feels slightly crowded with the large curved title text.
Wan 2.6
- + Strong atmosphere with a dark, moody color palette and effective use of shadows.
- + Detailed twisted trees create a more immersive 'gothic' environment.
- + Good adherence to the 'dark parchment' texture requested in the prompt.
- − The small scroll banner has some minor graphical glitches/blending issues with the text background.
- − The text style for the event details is more generic compared to the title.
Verdict: Both models followed the complex prompt extremely well, including precise dates and locations. Wan 2.5 (Preview) produced a very sharp, professionally typeset look with vibrant lighting, while Wan 2.6 captured the moody, gritty 'gothic' atmosphere and dark parchment texture much more effectively. Wan 2.5 is slightly preferred for its superior text clarity and polish.
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
Wan 2.5 (Preview)
- + Excellent preservation of the original facial features and bone structure.
- + The hair texture matches the existing beard hair reasonably well.
- + Maintains the exact lighting and background from the source image.
- − The hairline on the forehead looks slightly artificial and stamped on.
- − The hair volume is a bit conservative compared to 'full and thick'.
Wan 2.6
- + Provides a very full, lush head of hair with great volume.
- + The hair flow and styling look very natural and well-integrated.
- + Successfully preserves facial identity and environmental context.
- − The hair slightly overlaps the glasses frame in a way that looks a bit less clean than Model A.
- − Slightly alters the shape of the upper head/forehead area to accommodate the volume.
Verdict: Both models performed exceptionally well at this task, maintaining near-perfect source preservation. Wan 2.6 is the slightly better choice as it better fulfilled the 'full, thick head of hair' part of the prompt with a more natural-looking style, whereas Wan 2.5 (Preview) produced a slightly stiffer hairline.
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
Wan 2.5 (Preview)
- + Excellent typography with clean, bold execution and logical placement.
- + Vibrant rendering with high-quality PBR-style lighting and shadows.
- + Perfectly centered and clean composition.
- − The camera angle is lower than the requested 45-degree isometric view.
- − Text layout places the flag to the right rather than below 'SUSHI' as implied by the hierarchy.
Wan 2.6
- + Perfect adherence to the 45-degree isometric camera angle.
- + Superior miniature diorama feel with multiple sushi pieces and traditional wooden board.
- + Crisp text rendering and accurate flag icon.
- − The 'JAPAN' text is slightly off-center compared to the 'SUSHI' block.
- − The overall color palette is a bit more muted than Model A.
Verdict: Both models followed the prompt exceptionally well, particularly regarding text rendering. Wan 2.6 is the winner as it accurately captured the 45-degree isometric perspective and the 'miniature diorama' aesthetic more effectively than Wan 2.5 (Preview), which felt more like a close-up character render.
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
Wan 2.5 (Preview)
- + Features a classic big-head caricature style that leans more into the 'exaggerated' prompt.
- + Preserves the specific denim shirt from the source image better than the other model.
- + Incorporates a hockey broadcast on a screen to reinforce the professional setting.
- − The transition between the neck and the body looks somewhat disconnected.
- − The hockey stick is placed awkwardly to the side rather than being integrated into the character's actions.
Wan 2.6
- + Creates a more comprehensive and visually rich TV studio environment with professional lighting and equipment.
- + Stronger interaction with the props, showing the character holding the hockey stick and microphone simultaneously.
- + Variety in dog breeds adds more visual interest and character to the 'love for dogs' aspect.
- − The facial likeness is less distinct as a caricature of the specific source person compared to Model A.
- − Changes the character's clothing to a suit, losing the source image's denim shirt detail.
Verdict: Wan 2.5 (Preview) provides a better caricature of the actual person from the source image and preserves her original outfit, though the composition is simpler. Wan 2.6 creates a much more polished and creative scene with better character-prop interaction, but it loses some of the subject's identifiable likeness in the process. Wan 2.6 is preferred for its superior composition and more successful interpretation of the 'humorous' and 'caricature' themes as a whole.
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
Wan 2.5 (Preview)
- + Excellent dynamic motion and energy across all four animals
- + Vibrant colors and clear focus on the foreground subjects
- + Accurately includes all four requested species with high-quality fur textures
- − The fox's eyes appear overly saturated and slightly unnatural in color
- − The water droplets/dew are disproportionately large
Wan 2.6
- + Beautifully soft lighting and atmospheric god rays that feel more integrated
- + More naturalistic fur rendering and eye colors for the animals
- + The 'tumbling' interaction requested in the prompt is better realized through closer proximity
- − The fox's front-right leg has an anatomical issue where it attaches to the body
- − The background kittens/fox feel a bit more cluttered in the composition
Verdict: Both models captured the complex prompt and all four animals perfectly. Wan 2.6 provides a more atmospheric and 'wholesome' aesthetic with superior light diffusion, whereas Wan 2.5 (Preview) offers a cleaner, higher-contrast image with better anatomical clarity but slightly stylized eyes on the fox. Wan 2.6 is the slight winner for its more realistic fur and 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
Wan 2.5 (Preview)
- + Excellent adherence to the Studio Ghibli cel-shaded animation style.
- + Preserves the composition and poses of the original meme perfectly.
- + The lighting and color palette feel nostalgic and warm.
- − The faces look more like modern generic anime than specific Ghibli characters.
- − The addition of floating leaves is a bit cliché.
Wan 2.6
- + Beautiful hand-painted watercolor texture that fits the prompt's request for textures.
- + Softer pastel color palette creates a more dreamy atmosphere.
- + Great preservation of the specific clothing details and facial expressions from the source.
- − The line art is slightly less defined, losing some of the structural clarity of the characters.
Verdict: Both models did an exceptional job of translating the 'Distracted Boyfriend' meme into the requested style while maintaining the source image's identity. Wan 2.5 (Preview) captures the cel-shaded look of a Ghibli film, but Wan 2.6 is the winner for perfectly executing the 'hand-painted textures' and 'soft pastel colors' requested in the prompt, resulting in a more artistic watercolor-inspired illustration.
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
Wan 2.5 (Preview)
- + Successfully added wind-blown hair effect in a natural-looking direction.
- + Followed the instruction to add flying leaves throughout the scene.
- + Preserved the woman and dog's identity and posture perfectly.
- − The flying leaves are somewhat low-resolution and look like simple green shapes.
- − A small artifact appears above the dog's right ear where the tail of a leaf meets the fur.
Wan 2.6
- + Effectively rendered the hair blowing in the wind while maintaining facial clarity.
- + Added flying leaves with slightly better lighting and integration into the scene than Model A.
- + Excellent source preservation of the original environment and subjects.
- − The large leaf in the bottom left corner is slightly blurry compared to the rest of the image.
- − One small floating leaf near the woman's shoulder lacks a distinct stem, making it look a bit like a green blob.
Verdict: Both models performed exceptionally well at editing the source image while maintaining its integrity. Wan 2.6 is the slight winner because the flying leaves it added feel more integrated into the scene's lighting, and the motion in the hair feels slightly more fluid and energetic compared to Wan 2.5 (Preview).
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
Wan 2.5 (Preview)
- + Excellent typography including the requested accent mark.
- + Strong vector emblem aesthetic with a clear banner.
- + Balanced composition that feels like a complete brand identity.
- − The steam is inside the cloche which is physically unusual.
- − The background texture looks more like crumpled paper than a subtle logo texture.
Wan 2.6
- + More sophisticated and minimalist vector icon style.
- + Logical placement of steam rising from the cloche.
- + Beautifully rendered subtle 'distressed' texture on the background.
- − The Est. 1720 banner is much smaller and less prominent than requested.
- − Integration of the banner onto the side of the cloche is slightly unbalanced.
Verdict: Wan 2.5 (Preview) better captured the specific layout requested, particularly the prominence of the banner and the specific typography, though the steam placement is odd. Wan 2.6 produced a more professional-looking vector icon and superior background texture, but sacrificed the banner detail. Wan 2.5 (Preview) is the winner for adhering more closely to the structural elements of the prompt.
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
Wan 2.5 (Preview)
- + Excellent adherence to the infographic structure and steps.
- + Clean, professional flat-vector aesthetic with a solid NASA-inspired palette.
- + Accurate text rendering for labels and astronaut names.
- − The 'Descent' and 'Landing' text alignment is slightly floating and lacks connecting icons.
- − The Saturn V rocket illustration is a bit generic and resembles a modern shuttle mix.
Wan 2.6
- + Legible, clean typography for the title and astronaut names.
- + Correct use of the requested color palette.
- − Completely failed to generate the infographic steps and icons.
- − Image appears like a low-resolution printed towel or fabric texture instead of a crisp digital vector poster.
- − Lacks all visual elements requested except for the names.
Verdict: Wan 2.5 (Preview) successfully created a complex, multi-step infographic that followed the prompt's structural and stylistic requirements almost perfectly. In contrast, Wan 2.6 failed to produce any of the requested icons or steps, providing only a sparse background with three names. Wan 2.5 is the clear winner for its superior prompt adherence and visual quality.
Explore each model
Alibaba's multimodal generation model from the Wan AI suite, supporting text-to-video, image-to-video, reference-to-video with audio, and text-to-image, in both Chinese and English