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 2.7
#39 of 62 in Text-to-Image
Where the votes landed
Wan 2.5 (Preview)
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
Wan 2.5 (Preview)
- + Excellent photographic lighting and depth of field
- + Clean, minimalist composition
- + High-quality textures on the sphere and wood
- − The glass cube is missing its back right vertical edge
- − The book appears to be floating slightly above the glass surfaces
Wan 2.7
- + Strong spatial coherence and realistic glass refraction
- + Highly detailed textures on the book spine and weathered wood
- + Accurate light interaction with the window in the background
- − The placement of the sphere's reflection on the left panel is slightly confusing geometrically
Verdict: While both models followed the prompt perfectly, Wan 2.7 is the superior image due to its incredible realistic detail, especially in the texture of the wooden table and the book spine. Wan 2.5 (Preview) has a beautiful aesthetic but suffers from a significant geometric error where the back corner of the glass cube is missing.
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)
- + Excellent preservation of the specific car model and features from the source.
- + High visual quality with realistic motion blur in the wheels and road.
- + Successfully incorporates the subject's dreadlocks and black scarf inside the vehicle.
- − The driver's face is small and lacks detail due to the angle.
- − The palm trees appear a bit repetitive in their placement.
Wan 2.7
- + Beautiful composition of the California coastline and cliffside road.
- + Accurately places the car in a scenic sunset/golden hour lighting environment.
- − Completely fails to preserve the identity of the man, replacing him with a distorted, different person.
- − The car's front grille and headlight details are slightly more muffled compared to the source.
Verdict: Wan 2.5 (Preview) is the clear winner because it successfully carries over the identity of both subjects: the specific white Rolls Royce and the man with locs and a black scarf. While Wan 2.7 creates a more picturesque landscape, it fails the primary editing task by replacing the man with a different, poorly rendered face.
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 shallow depth of field and bokeh realism
- + Rich, saturated colors and beautiful reflections on wet surfaces
- + Stronger 'cinematic' feel requested by the prompt
- − Failed to include passing cars for the motion blur effect
- − Composition is very balanced and centered, lacking the 'imperfect framing' requested
Wan 2.7
- + Successfully captured the 'imperfect framing' and 'candid' street photography style
- + Higher technical accuracy for the environment and background elements
- + More realistic skin texture and clothing details for a candid photo
- − The depth of field is deeper than the 'shallow 50mm' look requested
- − Lacks the motion blur of passing cars requested in the prompt
Verdict: Wan 2.5 (Preview) produces a more aesthetically pleasing, cinematic image with superior depth of field, but fails on the specific 'street photography' framing requirements. Wan 2.7 better captures the requested candid, imperfect style of a Japanese street scene, even though both models missed the motion blur requirement. Wan 2.7 is the likely winner for its more convincing adherence to the specific 'candid street' and 'imperfect framing' descriptors.
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 engraving details on the pauldrons
- + High-quality skin texture with realistic dirt and minor bruising
- + Atmospheric warm lighting effects on the armor
- − The beads in the hair look more like metal spheres than decorative beads
- − The background torch has some digital artifacts and looks slightly disconnected
Wan 2.7
- + More natural and varied beadwork in the braids
- + Character looks significantly more 'battle-worn' and experienced
- + Superior depth of field with convincing golden bokeh
- − The engravings on the chest plate are slightly less sharp than Model A's pauldrons
- − One of the leather straps passes through a metal plate in a way that suggests a clipping error
Verdict: Wan 2.7 is the preferred choice as it captures the 'battle-worn' theme with more character and authenticity, featuring a more rugged appearance and better bokeh. While Wan 2.5 (Preview) has slightly sharper metal engravings, its character looks too youthful and clean for a seasoned 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)
- + Strict adherence to the requested grid layout for sections.
- + Follows the request for bold sans-serif fonts and specific section names.
- + High resolution, clean white background with professional lighting on food.
- − Nonsense text and significant spelling errors throughout.
- − Repetitive food imagery (all dishes look very similar with basil toppings).
Wan 2.7
- + Excellent text legibility and realistic branding details including prices and social media icons.
- + Diverse and appetizing food photos that actually correspond to classic menu items.
- + Highly polished, professional composition with lifestyle flat-lay elements.
- − Missing the specific 'Appetizers/Pizza/Mains' grid layout, showing a general grid instead.
- − The background is not purely white as it includes table props.
Verdict: Wan 2.5 (Preview) followed the structural components of the prompt more closely by organizing the page into the requested sections, but suffered from gibberish text and repetitive imagery. Wan 2.7 produced a much more realistic and usable menu design with legible text and varied food photography, though it opted for a generic grid rather than the specific sectored layout requested. Wan 2.7 is the overall winner for its superior visual quality and technical execution of text.
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 photorealistic texture on the patty and bun.
- + The glowing sauce drip on the title text is creatively executed.
- + Balanced composition with a strong sense of upward motion.
- − The starburst for the price is slightly irregular in shape.
Wan 2.7
- + High-energy composition with great use of liquid splashes and embers.
- + Crisp and clear typography for all three required text elements.
- + Includes extra details like pickles and sesame seeds flying in the air.
- − The bun looks slightly less realistic and more like a 3D render than Model A.
- − The 'LIMITED TIME ONLY' text feels a bit crowded at the bottom.
Verdict: Both models followed the complex prompt near-perfectly, including all text elements and the specific price. Wan 2.5 (Preview) is slightly preferred for its superior photorealistic textures, especially on the meat patty, whereas Wan 2.7 has a slightly more 'glossy' commercial illustration feel but handles the starburst element more cleanly.
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)
- + Text has a very convincing chalk texture with authentic 'dustiness' and smudges.
- + Handwriting looks truly manual with natural slants and variations in stroke weight.
- + Accurately rendered all the requested text and prices with high legibility.
- − The title is in a blocky style rather than the 'elegant cursive' requested.
- − The perspective is slightly angled, making some text less prominent in the composition.
Wan 2.7
- + Perfectly centered and balanced composition.
- + Followed the text content prompt accurately for the menu items.
- + The background environment (cafe wall) is aesthetically pleasing.
- − The text looks like a digital font rather than natural chalk handwriting.
- − The 'chalk' texture is too uniform and lacks the physical grainy characteristics shown in Image A.
- − Failed the 'elegant cursive' requirement for the title.
Verdict: Wan 2.5 (Preview) produced a much more realistic result that actually looks like a physical chalkboard with authentic chalk dust and human handwriting variations. While Wan 2.7 has better layout and framing, the text appears too clean and digital, failing to capture the 'handwritten-style' and 'chalk texture' specified in the prompt.
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)
- + Excellent dynamic lighting with cinematic lens flares.
- + Vibrant color palette and deep space contrast.
- + Detailed textures on the horse's coat and astronaut's suit.
- − Failed the specific spatial instruction (the astronaut is riding the horse, not vice-versa).
- − Anatomical issues with the horse's front-left leg and floating stirrup.
Wan 2.7
- + Natural and balanced composition with a clear view of the Earth.
- + Good rendition of the horse's mane and bridle hardware.
- + Sharp clarity throughout the entire frame.
- − Completely ignored the negative constraint/instruction for the horse to be on top.
- − The horse's legs are disproportionately long and thin.
- − Static posing lacks the 'surreal' or 'cinematic' energy requested.
Verdict: Both Wan 2.5 (Preview) and Wan 2.7 failed the core challenge of the prompt, which specifically requested the horse to be on top of the astronaut ('horse riding astronaut'). Instead, both models generated the common trope of an astronaut riding a horse. Wan 2.5 (Preview) is the better image visually, as it offers more cinematic lighting and dynamic movement compared to the flat, static appearance of Wan 2.7.
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 exact clothing, scarf, and accessories from Image 2.
- + Maintains a realistic lighting match between the person and the beach background.
- − Completely fails to preserve the identity, face, and hair of the person in Image 1, replacing them with the person from Image 2.
- − Crops the image to a square format, losing parts of the original composition.
Wan 2.7
- + Perfectly preserves the person's exact face, hair, and unique skin patterns from Image 1.
- + Successfully adapts the pose and body shape while maintaining the background and original aspect ratio.
- − Fails to use the specific clothing from Image 2, instead generating a generic 'elaborate' outfit.
- − The generated hands have anatomical issues and strange skin blending.
Verdict: The two models failed in opposite ways. Wan 2.5 (Preview) achieved the clothing transfer perfectly but ignored the instruction to keep the person's face and hair unchanged, essentially just swapping the background for the man in Image 2. Wan 2.7 successfully preserved the person's identity and background as requested, but failed to use the specific source clothing provided in Image 2. Wan 2.7 is the likely winner for successfully completing the much harder task of identity preservation and image editing, even though the clothing match was poor.
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 photographic quality with realistic rain droplets and lighting.
- + Correct placement of the passenger in the back seat as requested.
- + Highly detailed rendering of the capybara's fur and the taxi interior.
Wan 2.7
- + Sharp rendering of the capybara's coat and human features.
- + Clear view of the city streets through the window.
- − Failed to place the passenger in the back seat; she is sitting in the front passenger seat.
- − Composition feels slightly cramped with the capybara's head overlapping the door frame.
- − The paws on the steering wheel look anatomically strange and lack the weight found in the other image.
Verdict: Wan 2.5 (Preview) followed the prompt much more accurately by placing the businesswoman in the back seat, whereas Wan 2.7 placed her in the front next to the driver. Wan 2.5 also achieved a superior cinematic atmosphere with realistic lighting and rain effects that better fit the 'night in Manhattan' theme.
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 cinematic lighting within the central jack-o-lantern and backdrop.
- + High level of texture detail on the pumpkin and the twisted tree.
- + Successful integration of all requested text with perfect spelling.
- − The main title text is cut off slightly by the top and side borders.
- − The composition feels a bit cramped with the large text overlapping the scenery.
Wan 2.7
- + Perfectly balanced layout that feels like a real vintage poster.
- + Crisp, legible text with elegant gothic font choice.
- + Highly detailed and decorative border that incorporates webs, thorns, and skulls beautifully.
- − The lighting is less cinematic and more illustrative/flat compared to Model A.
- − Added extra elements like 'Est. 1847' and 'Dress code' which were not in the prompt.
Verdict: Wan 2.5 (Preview) excels in lighting and realistic textures, creating a more moody and atmospheric 'spooky' feel, though its text placement is slightly poorly integrated with the borders. Wan 2.7 provides a much more polished and professional invitation layout with excellent spacing and graphic design elements, making it the better choice for a functional poster. Overall, Wan 2.7 is preferred for its superior composition and legibility.
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)
- + Successfully added a thick head of hair with realistic volume.
- + Maintains excellent preservation of background and clothing.
- + The lighting on the hair matches the desert environment well.
- − The hairline on the forehead looks slightly artificial and rounded.
- − The hair texture is a bit too soft or smoothed over in some areas.
Wan 2.7
- + Exceptional hair texture and realism, showing individual strands and natural variation.
- + Excellent hairline integration that looks like it naturally grows from the scalp.
- + Near-perfect source preservation with virtually no changes to the face or environment.
- − The hair volume is slightly more conservative compared to the 'full, thick' request in model A.
Verdict: Both models handled the editing task exceptionally well, preserving the original image's identity and lighting flawlessly. Wan 2.7 (Image B) edges out Wan 2.5 because the hair texture and hairline look significantly more natural and realistic, whereas Image A has a slightly more 'wig-like' transition at the forehead.
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 rendering with clean, clear fonts
- + Beautiful soft 3D lighting and material textures
- + Perfectly centered and clean composition
- − Simple single-sushi composition might be considered 'too minimal' for a diorama
Wan 2.7
- + Successfully captures the 45° isometric perspective and diorama base
- + Offers more visual variety with multiple types of sushi and garnishes
- + Accurate rendering of the flag icon and text layout
- − The text has minor aliasing and a distracting white outline
- − Some minor artifacting on the chopsticks and soy sauce dish
Verdict: Wan 2.5 (Preview) produced a more aesthetically pleasing image with superior lighting and high-quality font rendering, though it was very minimal. Wan 2.7 better adhered to the technical 'isometric' and 'diorama' aspects of the prompt, providing a more complex scene that feels like a complete miniature set. Both performed exceptionally well on prompt adherence, but Wan 2.7's composition feels more appropriate for the 'diorama' request.
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)
- + Successfully incorporates all elements: hockey, dogs, and TV anchor desk.
- + Maintains the subject's denim outfit from the source image.
- + Clean, classic caricature style with a balanced composition.
- − The facial resemblance to the source image is somewhat generic.
- − The screen in the background shows a hockey player on a grass-like field instead of ice.
Wan 2.7
- + Captures the subject's facial features and eye color more accurately than Model A.
- + Highly creative and humorous use of space, including a tiny hockey rink and dogs in helmets.
- + Maintains the 'selfie' arm perspective from the original photo.
- − Includes some text spelling errors ('Rolee' instead of 'Rule').
- − The background is slightly more cluttered compared to the clean layout of Model A.
Verdict: Both models did an excellent job translating the source image into a caricature while hitting all the prompt requirements. Wan 2.5 (Preview) provides a more traditional TV studio setup and preserves the original clothing, but Wan 2.7 wins by capturing a much stronger facial resemblance and pushing the humor and creativity further with details like the dog in a hockey helmet and the floating puck.
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 depiction of motion and energetic interaction
- + Vibrant colors and strong lighting effects
- + Distinct and cute facial expressions on all characters
- − Physical anatomy on the fox is slightly distorted
- − Dew drops appear as large floating orbs rather than being on the grass
- − The fox's eyes appear somewhat artificial and glowing
Wan 2.7
- + Great fur textures and more realistic lighting transitions
- + Better integration of the animals into the meadow
- + More naturalistic anatomy for the rabbit and fox
- − The kitten has a slightly strange expression and pose
- − Lower energy in the composition compared to the other image
- − The light rays are a bit more diffused and less 'defined' than requested
Verdict: Wan 2.5 (Preview) captures the 'joyful' and 'playful' aspect of the prompt more effectively with dynamic poses, but the floating water droplets and fox anatomy are weak points. Wan 2.7 provides a much more grounded and realistic interpretation with superior fur textures and natural lighting. Wan 2.7 is preferred for its technical cohesion and realistic 8K aesthetics despite being slightly less energetic.
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)
- + Captures the iconic clean anime line art style specific to Studio Ghibli films.
- + Excellent facial expression mapping that translates the real-life meme to an anime context perfectly.
- + Adds whimsical elements like floating leaves and sparkles that enhance the dreamy mood.
- − Faces are slightly generic 'modern anime' rather than strictly the traditional round Ghibli aesthetic.
Wan 2.7
- + Strong hand-painted watercolor texture throughout the image.
- + Preserves the physical likeness of the original actors more closely than Model A.
- − The style feels more like a generic European watercolor illustration than a Studio Ghibli anime style.
- − The lighting is flat and lacks the 'glow' or 'wonder' requested in the prompt.
Verdict: Wan 2.5 (Preview) provided a much better stylistic transformation by successfully translating the source image into a recognizable anime format with glowing light and clean lines. While Wan 2.7 has a nice watercolor texture, it fails to capture the specific aesthetic of Studio Ghibli, looking more like a standard book 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)
- + Excellent wind effect on hair
- + Successfully added motion blur to the dog's tail
- + Consistent facial features and clothing preservation
- − The added leaves look like flat digital stickers rather than natural elements
- − The green color of the leaves is overly saturated and neon
Wan 2.7
- + Natural-looking leaves with realistic colors and textures
- + Leaves show a good sense of depth and motion
- + Excellent preservation of the subject and background
- − Hair movement is less dynamic than in the other model
- − Motion blur on the dog is subtle compared to the other model
Verdict: Wan 2.5 (Preview) does a better job of creating a dynamic wind effect on the hair and dog tail, but the added leaves look distracting and artificial. Wan 2.7 provides a much more cohesive and realistic image, with leaves that feel integrated into the scene's lighting and atmosphere, even if the hair movement is slightly more conservative.
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 rendering with perfect spelling and accent marks.
- + Clean vector-style composition that feels like a professional logo.
- + Great use of the background texture to enhance the vintage feel.
- − The steam is a bit thick and stylized compared to the rest of the logo.
Wan 2.7
- + Strong emblem layout with a coherent circular frame.
- + Includes nice decorative elements like the stars and wheat stalks.
- + Accurate adherence to the color palette.
- − The spelling 'Florion' is incorrect, missing the 'a'.
- − The cloche is transparent, which looks a bit awkward with the steam placement behind it.
- − The layout is slightly cluttered for a 'minimalist' request.
Verdict: Wan 2.5 (Preview) produced a superior logo with perfect spelling, elegant typography, and a balanced minimalist composition that fits the 'vector emblem' request. Wan 2.7 failed on the text rendering (spelling it 'Florion') and created a more cluttered design that moved away from the minimalist 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 'flat-vector' and 'crisp lines' instruction.
- + Clean and legible text for the main headers.
- + Strong visual storytelling through connected icons.
- − Missed the labels for 'Descent' and 'Landing' next to the actual graphics.
- − The astronaut portraits are a bit jarring compared to the flat vector style of the rest of the image.
Wan 2.7
- + Perfectly organized vertical flow that matches the chronological order of the prompt.
- + Included much more detailed technical text and data that feels like a real infographic.
- + Excellent text rendering for 1960s-era mission names and details.
- − Contains a misspelling ('DESCRIPT' instead of 'DESCENT').
- − The icons are much smaller and less impactful than those in Model A.
Verdict: Model B (Wan 2.7) is the superior infographic because it follows the chronological steps precisely in a logical vertical layout and includes relevant text data, whereas Model A has a somewhat confused layout with floating text labels. While Model A has larger and cleaner vector icons, Model B's overall composition and mission detail make it feel like a complete poster.
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