Head to head
Esc

Models · slot A

to navigate to pick

Qwen Image 2512 Alibaba Wan 2.7 Pro Alibaba

Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.

Qwen Image 2512

22.9 arena score

#30 of 62 in Text-to-Image

Skill signature · Text-to-Image

Wan 2.7 Pro

21.0 arena score

#37 of 62 in Text-to-Image

Vote tally

Where the votes landed

Qwen Image 2512

0%

win rate

Ties

0%

Wan 2.7 Pro

0%

win rate

Shared challenges 13

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.”

Qwen Image 2512
Wan 2.7 Pro

AI Judge Analysis

Qwen Image 2512

  • + Excellent material render for the red book cover and pages.
  • + Clean, geometric cube shape that matches the request perfectly.
  • + Correct lighting orientation from the left window.
  • The plant in the background is quite blurry and lacks definition.
  • The glass has a strong turquoise tint that makes it look like thick plate glass rather than clear glass.

Wan 2.7 Pro

  • + High visual quality with a very detailed, realistic fern in the background.
  • + The textures on the wooden table and the sphere are highly intricate.
  • + Excellent composition with a wider frame that feels more natural.
  • The red book is slightly floating above the glass surface instead of resting on it.
  • The cube appearance is slightly distorted on the right edge near the book's spine.

Verdict: Both models followed the prompt instructions perfectly, capturing all elements including the blue sphere and the red book. Wan 2.7 Pro is the superior image due to the much higher level of detail in the background plant and the realistic texture of the wooden table, whereas Qwen Image 2512 has a more synthetic, heavily-tinted look to the glass elements.

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.”

Qwen Image 2512
Wan 2.7 Pro

AI Judge Analysis

Qwen Image 2512

  • + Excellent shallow depth of field and bokeh
  • + Highly realistic skin textures and lighting
  • + Dynamic composition with impactful car light reflections
  • The subject is posing for the camera rather than actively 'repairing' the bike
  • The bike geometry has some structural inconsistencies around the handlebars

Wan 2.7 Pro

  • + Better adherence to the 'repairing' part of the prompt
  • + Captures the environment with a more authentic Japanese street feel
  • + Clearer representation of falling rain
  • Lack of motion blur on passing cars as requested
  • Visual quality feels slightly more 'generated' than the photographic realism of Model A
  • The bike's reflection on the pavement is physically inconsistent

Verdict: Qwen Image 2512 produces a much more cinematically professional image with superior skin textures and lighting, though the subject is looking at the camera. Wan 2.1 Pro adheres better to the specific action of repairing the bike, but fails to include the requested motion blur and has lower overall photorealism. Qwen Image 2512 is preferred for its striking visual quality and better execution of the photography-specific prompts like 50mm lens and bokeh.

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.”

Qwen Image 2512
Wan 2.7 Pro

AI Judge Analysis

Qwen Image 2512

  • + Exceptional engraved pattern detail on the breastplate and pauldrons
  • + Very lifelike eyes with realistic reflection and moisture
  • + Excellent atmospheric lighting and bokeh spark effects around the torch
  • The scars look a bit like surface scratches rather than healed or fresh tissue
  • The hair texture is slightly messy compared to the braided description

Wan 2.7 Pro

  • + Stronger adherence to the 'braided hair with beads' prompt with clearly defined, intricate braids
  • + Excellent skin texture showing subtle dirt and more realistic scarring
  • + Great materials rendering on the leather straps and metal tarnish
  • The composition is slightly further back than a 'close portrait'
  • The engraved patterns look a bit softer and less sharp than in the other model

Verdict: Qwen Image 2512 produces a more intimate and atmospheric portrait with stunning micro-details on the metal and eyes. However, Wan 2.7 Pro better captures the specific request for braided hair and provides a more realistic depiction of worn skin and leather textures. Wan 2.7 Pro is preferred for its overall coherence and better fulfillment of the specific character traits requested.

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.”

Qwen Image 2512
Wan 2.7 Pro

AI Judge Analysis

Qwen Image 2512

  • + Strong bold sans-serif fonts used in headings.
  • + Excellent grid layout for food photography.
  • + Vibrant colorful accents that separate sections effectively.
  • Text is largely gibberish and poorly rendered.
  • The section headers contain spelling errors like 'Appetiizizers'.

Wan 2.7 Pro

  • + Incredible text legibility and realistic product names/prices.
  • + Very high-quality photography and professional graphic design layout.
  • + Includes realistic details like a QR code and social media icons.
  • The grid is less organized than requested, prioritizing items over distinct sections.
  • The font choice is a mix rather than strictly bold sans-serif.

Verdict: Wan 2.7 Pro is the clear winner because it produces a functional, professional menu with near-perfect text rendering and realistic imagery. While Qwen Image 2512 followed the grid and font weight instructions well, its failure to generate legible text makes the design unusable compared to Wan 2.7 Pro's polished output.

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.”

Qwen Image 2512
Wan 2.7 Pro

AI Judge Analysis

Qwen Image 2512

  • + Excellent photorealistic texture on the meat patty and buns
  • + Superior integration of glowing fire effects within the text
  • + Better sense of motion with flying sauce and crumbs
  • The burger ingredients are less 'exploded' and more of a tilted stack

Wan 2.7 Pro

  • + Perfect adherence to the 'exploded' instruction with components widely suspended
  • + Text is extremely clear and well-positioned
  • + Includes additional details like onion rings and herbs
  • Lighting feels flatter and more like a digital composite than a photoreal shot
  • The bottom bun looks a bit artificial/plastic compared to the top bun

Verdict: Qwen Image 2512 produces a much more appetizing and photorealistic result with superior lighting and atmospheric effects, making it feel like a high-end food advertisement. While Wan 2.7 Pro followed the 'exploded' prompt more literally by spacing out every single ingredient, its final composition lacks the professional polish and integrated fire effects found in Qwen Image 2512.

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.”

Qwen Image 2512
Wan 2.7 Pro

AI Judge Analysis

Qwen Image 2512

  • + Excellent chalk texture with visible smudges and powdery effects.
  • + Captured the requested cursive handwriting style for the heading and items.
  • + Rich wood texture on the frame and realistic café background
  • Spelling error in 'Risitto' instead of 'Risotto'.
  • Slightly less clean layout with line breaks that cut off words awkwardly.

Wan 2.7 Pro

  • + Perfect spelling on all requested menu items.
  • + Very clean and readable layout with consistent line spacing.
  • + Good adherence to the full list of items within the frame.
  • The text looks a bit more like a digital font than authentic chalk handwriting.
  • The 'handwritten' style is very uniform, lacking natural human variation in the title.

Verdict: Qwen Image 2512 produces a much more authentic chalk texture and artistic handwriting style, capturing the 'handwritten' feel requested in the prompt, despite a small spelling error. Wan 2.7 Pro excels at literal text accuracy and layout but the resulting image looks more like a digital chalkboard template than a hand-drawn sign.

The Reversed Rodeo

Text-to-Image

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

Qwen Image 2512
Wan 2.7 Pro

AI Judge Analysis

Qwen Image 2512

  • + Excellent anatomical lighting and textures on the horse's coat.
  • + Clear, realistic rendering of the astronaut's suit and visor.
  • Failed the negative constraint; the astronaut is riding the horse.
  • Missing the surreal element of planetary objects in the background.

Wan 2.7 Pro

  • + Includes creative surreal elements like floating mini-planets.
  • + Good composition with a clear view of Earth and the cosmos.
  • Failed the negative constraint; the astronaut is riding the horse.
  • The horse's legs show anatomical distortions, particularly the front-right leg.

Verdict: Both Qwen Image 2512 and Wan 2.7 Pro failed the specific instruction to have the horse on top of the astronaut, instead defaulting to the common trope of an astronaut riding a horse. Wan 2.7 Pro is slightly better for its creative inclusion of surreal planetary elements, though Qwen Image 2512 has superior lighting and technical rendering of the subjects.

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.”

Qwen Image 2512
Wan 2.7 Pro

AI Judge Analysis

Qwen Image 2512

  • + Perfect adherence to character positioning with the woman correctly in the back seat.
  • + Accurately captures the 'bored' expression of the businesswoman as requested.
  • + High level of texture detail on the capybara's fur and the leather steering wheel.

Wan 2.7 Pro

  • + Excellent side-profile composition showing the movement of the street through the window.
  • + Very realistic lighting integration between the interior and the city lights.
  • Failed the spatial positioning requirement by placing the passenger in the front seat alongside the capybara.
  • The capybara's paws are rendered as primate-like hands rather than animal paws.

Verdict: Qwen Image 2512 is the clear winner as it correctly followed the spatial instruction to place the woman in the back seat, whereas Wan 2.7 Pro placed her in the front passenger seat. Qwen Image 2512 also better captured the 'bored' expression of the businesswoman and provided more anatomically appropriate paws for the capybara.

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.”

Qwen Image 2512
Wan 2.7 Pro

AI Judge Analysis

Qwen Image 2512

  • + Atmospheric cinematic lighting with a moody night sky
  • + Clear text for the event details at the bottom
  • + Detailed thorny border and webs consistent with the prompt
  • Spelling error in the main title: 'Hallowern' instead of 'Halloween'
  • The scroll banner is slightly clunky and cuts into the lower text

Wan 2.7 Pro

  • + Excellent typography with perfect spelling of 'Halloween'
  • + Highly detailed illustration with extra thematic elements like lanterns and a cauldron
  • + Beautifully framed composition with a clear vintage parchment aesthetic
  • The 'night sky' is smaller and less atmospheric than requested
  • Some tiny text elements in the corners are illegible

Verdict: Wan 2.7 Pro is the clear winner because it correctly spells 'Halloween' in the main title, whereas Qwen Image 2512 includes a noticeable typo ('Hallowern'). Wan 2.7 Pro also offers a much richer and more polished illustration that perfectly captures the vintage gothic aesthetic requested in the prompt.

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.”

Qwen Image 2512
Wan 2.7 Pro

AI Judge Analysis

Qwen Image 2512

  • + Excellent 3D miniature diorama feel with a detailed multi-layered base
  • + Rich, saturated colors and consistent cartoonish textures
  • + Perfect alignment of text and flag icon at the top center
  • The text style is a bit bulky and has an unnecessary cartoon stroke compared to the 'refined' request

Wan 2.7 Pro

  • + Elegant, clean typography with high professional design appeal
  • + Superior 'refined' and smooth material textures that look more premium
  • + Includes extra details like chopsticks and soy sauce that enhance the scene
  • The diorama base is just a thick plate rather than a proper 'miniature scene' base
  • Small floating debris/artifacts in the corners of the image

Verdict: Wan 2.7 Pro produces a significantly more polished and professional-looking graphic with refined textures and sophisticated typography that better fits the 'ultra-clean' request. While Qwen Image 2512 does a better job of creating a 'miniature diorama' base as requested, its overall visual style feels more like a mobile game asset than a high-end 3D render.

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.”

Qwen Image 2512
Wan 2.7 Pro

AI Judge Analysis

Qwen Image 2512

  • + Excellent fur texture and sharpness
  • + Captures all requested animals with clear, expressive eyes
  • + Vibrant, high-contrast lighting that feels magical
  • Static, 'posed' composition rather than the requested action of 'tumbling'
  • The anatomy where the puppy's paws meet the other animals is slightly blurred and indistinct

Wan 2.7 Pro

  • + Successfully captures the requested action of 'playfully chasing' and 'tumbling'
  • + Dynamic composition with a sense of movement
  • + Beautiful implementation of god rays and dew sparkles in the grass
  • The fox's front right leg is anatomically incorrect and looks like a black bird's wing or claw
  • The kitten's pose is a bit awkward and lacks the fur detail of the other animals

Verdict: Wan 2.7 Pro followed the prompt's action requirements more closely by showing the animals in motion, whereas Qwen Image 2512 opted for a more static portrait. However, Qwen Image 2512 achieved a much higher level of photorealistic detail and facial clarity, making it more visually appealing despite the lack of movement.

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.”

Qwen Image 2512
Wan 2.7 Pro

AI Judge Analysis

Qwen Image 2512

  • + Excellent typography with perfect spelling in a classic script style.
  • + Strong composition with high-quality cross-hatching detail on the cloche.
  • + Captures the steam and banner elements with great visual weight and balance.
  • The steam is a bit more illustrative and heavy than a typically minimalist logo.

Wan 2.7 Pro

  • + Symmetrical and clean circular emblem style suitable for a vector-based brand identity.
  • + Includes extra thematic details like 'Venezia Italia' which fits the historical context.
  • + Accurately represents the warm brown and cream tones requested.
  • Misspelled the name as 'Florion' instead of 'Florian'.
  • The cloche is small relative to the other framing elements.
  • Visual artifacts present in the corners with unrelated icons cut off.

Verdict: Qwen Image 2512 is the clear winner as it correctly spells the brand name and provides a much more cohesive and professional illustration. While Wan 2.1 Pro creates an authentic-looking emblem, the spelling error and distracting corner artifacts make it less usable as a logo.

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.”

Qwen Image 2512
Wan 2.7 Pro

AI Judge Analysis

Qwen Image 2512

  • + Features a high-quality illustration of the Saturn V rocket.
  • + Clean, modern background illustration of the lunar surface.
  • + Accurately captures the requested NASA-inspired color palette.
  • Numerous spelling errors in text (e.g., 'Translurtcoit', 'Desceeint').
  • Confusion in step numbering and overlapping labels.
  • The layout feels cluttered and lacks a logical infographic flow.

Wan 2.7 Pro

  • + Excellent infographic layout with a clear, linear vertical progression.
  • + Impressive text rendering with accurate spelling for technical terms.
  • + Superior adherence to the 'flat-vector style' and 'consistent iconography' requirements.
  • The rocket in the 'Launch' step is generic rather than a Saturn V.
  • Text at the very bottom is slightly too small to be legible.

Verdict: Wan 2.7 Pro is the clear winner as it successfully created a functional, readable infographic with a logical vertical flow and correct spelling. Qwen Image 2512 produces nice individual illustrations but fails as an infographic due to significant spelling errors, duplicate numbering, and a disorganized layout.

Next steps

Explore each model