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
Settled by community votes across 19 shared challenges, with an AI judge weighing in on each.
Wan 2.6
#28 of 62 in Text-to-Image
Wan 2.7
#39 of 62 in Text-to-Image
Where the votes landed
Wan 2.6
0.0%
win rate
Ties
50.0%
Wan 2.7
50.0%
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 2.6
- + Excellent depiction of soft window lighting and realistic shadows.
- + Beautiful internal reflections and refractions through the glass cube.
- + High visual quality with a pleasing bokeh effect on the plant.
- − The glass cube has extra vertical internal edges that make it look like multiple panes rather than a simple cube.
Wan 2.7
- + Realistic textures on the wooden table and the book's spine.
- + Good placement of the plant behind the glass cube.
- + Clean geometry for the glass cube's exterior.
- − The blue sphere reflection on the left is physically incorrect as if it were a mirror, not glass.
- − The sphere has a slightly rough, non-glass texture compared to Model A.
Verdict: Both models followed the prompt instructions precisely. Wan 2.6 (Model A) is the winner because it handled the light physics and glass refractions much more convincingly than Wan 2.7 (Model B), which created a confusing mirrored reflection inside the cube.
Man and Car in California
Editing“Make a photo of the man driving the car down the California coastline”
AI Judge Analysis
Wan 2.6
- + Excellent preservation of the man's identity, including his specific hairstyle, scarf, and coat pattern.
- + High-quality action scene with realistic motion blur in the wheels and background.
- + Accurate car model preservation based on the source image.
- − The man is seated on the wrong side for a standard US road (UK/LHD configuration), though he is steering.
Wan 2.7
- + Successfully places the car on a coastal California road with golden hour lighting.
- + Maintains the car's exterior design and color well.
- − Completely fails to preserve the identity of the man, replacing him with a distorted, unrecognizable figure.
- − The person in the driver's seat is low-resolution and lacks any resemblance to the source image provided.
Verdict: Wan 2.6 is the clear winner because it successfully integrated the specific subjects from both source images into a new scene. Wan 2.7 failed the image editing task by discarding the subject's identity and replacing it with a garbled, generic figure, whereas Wan 2.6 kept the man's face, hair, and clothing perfectly intact.
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 2.6
- + Excellent shallow depth of field and bokeh that matches a 50mm lens profile.
- + Superb skin texture and life-like details on the man's hands and face.
- + Perfect execution of the wet pavement reflections and rainy atmosphere.
- − The raindrops on the man's jacket look a bit like static beads or glitter rather than soaked fabric.
Wan 2.7
- + Naturalistic 'candid' composition and wider framing of a Japanese street.
- + Realistic clothing textures showing dampness rather than just surface droplets.
- − Failed to incorporate the 'motion blur from passing cars' requested in the prompt.
- − The mechanical structure of the bicycle becomes nonsensical near the pedals and chain area.
- − Lacks the shallow depth of field requested, with much of the background remaining relatively sharp.
Verdict: Wan 2.6 is the clear winner as it successfully incorporated almost every technical requirement of the prompt, including the specific depth of field, motion blur, and high-quality skin textures. While Wan 2.7 captures a convincing street scene atmosphere, it ignored several key descriptors like motion blur and shallow focus, and suffered from significant geometric distortions in the bicycle's frame.
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 2.6
- + Excellent representation of ornate engraved plate armor with high-contrast reflections.
- + Superior lighting and atmosphere with vivid torchlight and realistic skin textures.
- + Very detailed treatment of the hair beads and fraying cloth underlayer.
- − The dirt on the face looks slightly like flat texture overlays in some spots.
- − The composition is very tightly cropped on the left side.
Wan 2.7
- + Strong symmetry and clear view of the complex braided hairstyle.
- + Clean, sharp rendering of facial features and scars.
- + Good depth of field with distinct bokeh elements in the background.
- − The armor engraving is less intricate and appears flatter than Model A.
- − Lighting feels a bit more generic and less like actual warm torchlight reflecting off the metal.
Verdict: Wan 2.6 is the winner due to its superior lighting and texture work; the way the torchlight interacts with the engraved armor and the frayed cloth feels more lifelike and cinematic. While Wan 2.7 provides a clearer look at the character's face and braids, its armor and lighting lack the depth and realism found in Wan 2.6.
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 2.6
- + Successfully uses a grid layout as requested
- + Includes specific sections for Appetizers, Pizza, and Mains
- + Features bold sans-serif fonts in a clean, professional manner
- − The text is mostly gibberish or misspelled ('RESTAUR MENU')
- − The grid lacks food variety, showing mostly pizza and salad
- − The layout feels slightly more like a flyer than a functional menu
Wan 2.7
- + Excellent text legibility and coherent menu items
- + High food variety in the grid, including pasta, burgers, and desserts
- + Sophisticated composition including lifestyle props like a pen and herbs
- − The food photos have rounded corners instead of the sharp minimalist grid often associated with the prompt
- − Does not follow the specific 'Mains' text section list, instead putting prices under photos
Verdict: Wan 2.6 followed the layout instructions for a grid and specific text sections more faithfully, but Wan 2.7 produced a significantly more usable and attractive design with legible text, diverse food imagery, and professional branding elements. Despite Wan 2.7 missing the text-only sections requested, its overall visual quality and coherent content make it the superior design piece.
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 2.6
- + Excellent photorealistic texture on the burger bun and patty.
- + Seamless integration of the fiery background with realistic smoke and lighting.
- + High-quality rendering of the main titles with a convincing flaming effect.
- − The price starburst looks like a flat 2D sticker compared to the 3D scene.
- − A sauce stream appears to be unrealistically originating from inside the top bun.
Wan 2.7
- + Stronger 'exploded' composition with more dynamic spacing of the ingredients.
- + Price starburst is better integrated into the overall fiery theme and lighting.
- + Clean, professional typography that is very easy to read.
- − The food items look more like 3D digital illustrations than photorealistic photography.
- − Inclusion of random floating seeds/nuts that weren't requested and don't fit the burger theme.
Verdict: Wan 2.6 captures the 'photorealistic' requirement much better, with textures and lighting that feel like a high-end food advertisement photoshoot. While Wan 2.7 has a more dynamic layout and better starburst integration, its overly clean and slightly plastic aesthetic makes it feel more like a digital illustration than a real burger.
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 2.6
- + Excellent chalk texture with realistic smudges and dusty residue
- + Truly handwritten appearance with natural variations in letter size and slant
- + Perfect text accuracy including the clipped prompt text completion
- − The 'cursive' requirement for the title is only partially met with print/cursive hybrid letters
Wan 2.7
- + Perfect text rendering without any spelling errors
- + Clean and centered composition
- + Attractive cafe-style background lighting
- − Text looks like a digital font rather than natural chalk handwriting
- − Fails the 'no printed or digital fonts' requirement
- − Lacks the specific chalky texture and variations requested in the prompt
Verdict: Wan 2.6 is the clear winner as it successfully captured the 'handwritten' and 'chalk texture' requirements, appearing like an authentic chalkboard. Wan 2.7, despite having perfect legibility, used a clean digital-looking font that ignored the instructions for natural handwriting and chalk variations.
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 2.6
- + Excellent cinematic lighting and atmospheric effects
- + High level of detail in the astronaut suit and horse's mane
- − Completely failed the negative constraint to put the horse on top of the astronaut
- − The horse's back right leg is missing its lower half
Wan 2.7
- + Clear and coherent composition with sharp focus
- + Good rendering of the horse's anatomy and planets
- − Completely failed the negative constraint to put the horse on top of the astronaut
- − Lacks the 'surreal' and 'cinematic' lighting depth requested
Verdict: Both Wan 2.6 and Wan 2.7 failed the specific spatial instruction to place the horse on top of the astronaut. However, Wan 2.6 is the better purely visual result as it captured the 'cinematic' and 'surreal' keywords through dramatic lighting and nebula effects, whereas Wan 2.7 looked like a standard composite.
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 2.6
- + Successfully transferred the pea coat, scarf, and sunglasses from Image 2.
- + Maintained the perspective, lighting, and placement of the person in relation to the wooden structure.
- + Preserved the sand patterns on the face and the hair detail accurately.
- − Cropped the image significantly compared to the original aspect ratio.
- − Failed to include the lower half of the outfit (jeans, belt) due to the tight crop.
- − The scarf pattern, though similar, is not an exact match to Image 2.
Wan 2.7
- + Successfully integrated a full-body outfit, including shoes, into the scene.
- + Maintained the full original composition and background elements well.
- + Handled the vitiligo patterns on the hands realistically beneath the new clothing.
- − Completely ignored the clothing in Image 2, generating a generic gold-embroidered coat instead.
- − Failed to include the sunglasses and scarf depicted in the source image.
- − Changed the person's pose slightly, making him stand away from the pillar rather than leaning against it.
Verdict: Wan 2.6 is the superior choice because it actually adhered to the prompt instructions to use the outfit from Image 2, successfully transferring the coat, scarf, and sunglasses. Wan 2.7, despite having a larger field of view and good technical execution of the vitiligo, completely failed to use the specified source clothing, instead generating a random ornate costume.
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 2.6
- + Excellent photorealism with realistic low-light noise and rain textures
- + Captures the 'bored' expression of the passenger perfectly
- + The capybara's pose and anatomy look more integrated with the driver seat
- − The capybara's paws are somewhat indistinct and blend into the steering wheel
Wan 2.7
- + Clearer depiction of the capybara's paws on the steering wheel
- + Very sharp image resolution and clean lighting
- − The capybara's fur has a slightly artificial, 'rendered' look compared to Model A
- − The passenger is positioned awkwardly close to the driver, making the backseat feel like a front seat
Verdict: Wan 2.6 is the winner because it achieves a much higher level of cinematic photorealism, particularly in the lighting and atmosphere of a New York taxi at night. While Wan 2.7 has clearer details on the paws, the spatial arrangement of the car interior is confusing, whereas the first image perfectly captures the requested bored expression and realistic depth.
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 2.6
- + Excellent atmospheric cinematic lighting with a realistic 3D feel.
- + Highly stylized texture on the main title text that fits the gothic theme.
- + The border design perfectly integrates webs and thorns as requested.
- − The parchment texture is less 'poster-like' and more of an overlay effect.
- − Small amount of background text is slightly less crisp than the main header.
Wan 2.7
- + Perfect text rendering for all lines including the specifically requested event details.
- + Clean and detailed vintage illustration style with more thematic elements like ravens and a cauldron.
- + Excellent parchment aesthetics that feel like a physical printed invitation.
- − The art style is more like a 2D illustration rather than the 'cinematic lighting' requested.
- − The 'webs and thorns' border is a bit more repetitive and flat compared to Model A.
Verdict: Wan 2.6 provides a much more atmospheric and cinematic image with deep shadows and glowing textures, making it feel very spooky. However, Wan 2.7 is the superior invitation designer, perfectly rendering every line of requested text with a much higher degree of clarity and providing a more cohesive 'vintage stationery' aesthetic. While Wan 2.6 has a stronger 'mood', Wan 2.7 is more functional and accurate to the prompt's structural requirements.
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 2.6
- + Successfully added a full head of hair that matches the requested description.
- + Maintains high resolution and realistic hair texture.
- − Noticeably alters the subject's face, making him look like a younger/different person.
- − The hairline integration with the forehead looks slightly forced compared to the original bone structure.
Wan 2.7
- + Excellent preservation of the original facial features and identity.
- + The hairline and hair growth pattern look incredibly natural and well-integrated with the scalp.
- + Near-perfect source preservation for all elements outside the hair area.
- − Small minor artifacting where the hair meets the side of the glasses frame.
Verdict: Wan 2.7 is the clear winner because it successfully added the hair while perfectly preserving the subject's identity and facial features. Wan 2.6 changed the man's face significantly, whereas Wan 2.7 created a seamless edit that looks like the original person simply grew hair.
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 2.6
- + Excellent typography rendering and placement
- + Very clean, minimal aesthetic that fits the 'miniature' prompt perfectly
- + Accurate 45-degree isometric perspective
- − The diorama base is a bit plain and simple
- − Includes flag icon on the same line as text instead of below
Wan 2.7
- + High level of detail in the food textures and materials
- + More variety in the sushi pieces while maintaining a clean look
- + Sophisticated rendering of the diorama base and dish elements
- − The text has slight visual artifacts (dark outlines) compared to the clean white of Model A
- − The text layout is slightly off-center
Verdict: Both models followed the prompt exceptionally well, but Wan 2.6 (Image A) produced a cleaner, more professional graphic design layout with perfect text rendering. Wan 2.7 (Image B) has slightly more interesting 3D modeling and material work on the sushi itself, but the overall composition and font clarity in Wan 2.6 make it the superior choice for the requested 'ultra-clean' aesthetic.
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 2.6
- + Successfully incorporates all prompt elements (TV anchor, dogs, hockey) in a balanced scene.
- + Good caricature style that retains reasonable likeness to the source person.
- + The TV studio setting is clear and professional-looking for a caricature.
- − The hockey stick has an awkward, extra-long handle that disappears behind her head.
- − The facial expression is a bit generic and loses some of the source subject's unique features.
Wan 2.7
- + Very creative and humorous interpretation with dogs wearing helmets and a miniature hockey rink.
- + Excellent preservation of the original selfie-style composition and high likeness to the source subject.
- + Text rendering in speech bubbles is clean and legible.
- − One of the speech bubbles contains a typo ('Dogs Rolee!' instead of 'Rule').
- − The 'TV anchor' profession is represented only by a small lapel mic and a screen, making it less obvious than model A.
Verdict: Both models followed the instructions well, but Wan 2.7 is the winner due to its superior creativity and better preservation of the source subject's facial features and selfie-style composition. While Wan 2.6 provided a more traditional studio layout, Wan 2.7 felt more personal and humorous, perfectly capturing the requested caricature vibe despite a small typo.
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 2.6
- + Exceptional god ray effects and atmospheric lighting
- + Highly dynamic poses that feel like they are 'tumbling' as requested
- + Detailed fur textures and realistic interaction between the animals
- − The fox's anatomy in the bottom right is slightly distorted during the tumble
Wan 2.7
- + Clearer distinctiveness of the different flower types
- + Good rendering of the golden retriever's face and fur
- + Accurate inclusion of all four requested animal types
- − The composition feels more static and posed rather than playful/tumbling
- − The kitten has an oddly protruding tongue/mouth artifact
- − God rays are less realistic and more like graphic lines
Verdict: Wan 2.6 is the superior image as it captures the 'tumbling' and 'joyful' vibe of the prompt much more effectively than Wan 2.7. Wan 2.6 features much more professional lighting and atmospheric depth, whereas Wan 2.7 feels a bit more like a flat collage with stiff poses.
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 2.6
- + Excellent character translation into a classic anime aesthetic.
- + Consistent watercolor texture throughout the image.
- + Dreamy lighting and soft pastel palette perfectly match the prompt.
- − Added sparkles/dust motes might feel a bit distracting to some users.
Wan 2.7
- + Strong preservation of the source image's facial features.
- + Good hand-painted texture and soft color palette.
- + Excellent background coherence.
- − The faces lean more toward 'digital painting' than true Ghibli-style illustration.
- − Slightly less 'dreamy' lighting compared to the alternative.
Verdict: Both models did an exceptional job at preserving the source image while applying the requested style. Wan 2.6 captures the specific 'Ghibli' aesthetic more effectively by simplifying facial features into a classic anime style, whereas Wan 2.7 maintains higher facial fidelity to the real people in the photo which makes them look slightly more like a 2D rotoscope. Wan 2.6 is the preferred choice for a more authentic 'illustration' feel.
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 2.6
- + Excellent wind-blown hair effect that looks natural and fluid
- + Vibrant green leaves added that match the park environment
- + High fidelity preservation of the original woman and dog
- − Leaves look a bit static and lack motion blur
Wan 2.7
- + Added a high volume of flying leaves to create a sense of motion
- + Brown leaves suggest an autumn breeze effect
- + Good preservation of the source image identity
- − The hair effect is slightly less cohesive than Model A
- − The lighting on the brown leaves doesn't perfectly match the sunny summer day lighting of the scene
Verdict: Both models followed the instructions effectively, adding wind-swept hair and flying leaves while keeping the original image intact. Wan 2.6 (Model A) is the winner as its hair modification is more realistic and the green leaves integrate more seamlessly into the lush green environment compared to the brown leaves in Wan 2.7.
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 2.6
- + Perfectly rendered text for both the name and the banner
- + Clean minimalist vector execution with effective use of negative space
- + Accurate representation of an 'Est. 1720' banner integrated into the emblem
- − The cloche shape is a bit thick, resembling a bowl or lid more than a traditional cloche
Wan 2.7
- + Excellent vintage badge composition with a sophisticated color palette
- + High-quality subtle texture on the background and within the emblem
- + Refined line art for the cloche and steam elements
- − Typos in the main text, spelling it 'Florion' instead of 'Florian'
- − The design is quite busy and borders on decorative rather than 'minimalist' as requested
Verdict: Wan 2.6 followed the prompt instructions more accurately, particularly regarding typography and the 'minimalist' requirement, producing a perfectly spelled and clean logo. While Wan 2.7 created a visually rich and aesthetically pleasing vintage badge, it failed on the critical detail of spelling the brand name correctly and exceeded the minimalist scope.
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 2.6
- + Legible main title
- + Accurately identifies the three crew names
- − Fails to include any of the requested 6 stages of the infographic
- − Composition is empty and lacks icons
- − The background texture looks like a printed towel or fabric rather than a vector poster
Wan 2.7
- + Perfectly follows all 6 requested steps with relevant icons
- + Excellent adherence to the NASA-inspired color palette and vector style
- + High-quality typography and information density
- + Strong visual composition following a logical flow
- − Minor spelling errors in smaller text like 'Descript' and 'Tranquiliry'
- − The map pin logic for 'Tranquiliry' is slightly disconnected from the main flow line
Verdict: Wan 2.6 failed the prompt instructions significantly, producing a largely empty image that omitted all the specific infographic steps requested. Wan 2.7, in contrast, followed every detailed instruction, creating a professional-grade vector infographic with clear icons and consistent branding despite some minor typos.
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