Alibaba's Wan 2.7 Pro image generation and editing model with higher-quality outputs and support for 4K image generation
Settled by community votes across 4 shared challenges, with an AI judge weighing in on each.
Wan 2.7 Pro
21.4
arena score
#29 of 44 in Text-to-Image
Skill signature
Not enough comparable category data
The chart appears once both models have ratings across at least three shared arena categories.
Z-Image Turbo
24.7
arena score
#15 of 44 in Text-to-Image
Vote tally
Where the votes landed
Wan 2.7 Pro
0%
win rate
Ties
0%
Z-Image Turbo
0%
win rate
Shared challenges
4
Challenge by challenge
The strongest take from each model on every shared challenge, with the AI judge's read.
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.”
Wan 2.7 Pro
Z-Image Turbo
AI Judge Analysis
Wan 2.7 Pro
- + Excellent adherence to the 'exploded burger' requirement with all ingredients suspended.
- + Crisp and legible typography that perfectly follows the fire/glow styling instructions.
- + High-quality photorealistic textures on the lettuce, patty, and bun.
- − The 'starburst' for the price is a bit simple compared to the other text effects.
- − The lettuce piece is disproportionately large compared to the bun.
Z-Image Turbo
- + Strong glowing effect on the pricing starburst and title text.
- + Good sense of atmosphere with the fiery background and flying liquid droplets.
- − Failed to provide an 'exploded' burger, showing a mostly assembled stacked burger instead.
- − The lettuce texture looks slightly plastic or artificial compared to Model A.
- − Text layout is less dynamic, feeling like a standard stack.
Verdict: Wan 2.7 Pro is the clear winner as it perfectly executed the difficult 'exploded' burger composition requested in the prompt, whereas Z-Image Turbo provided a standard stacked burger. Wan 2.7 Pro also handled the specific placement of multiple text elements with better clarity and adherence to the layout instructions.
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.”
Wan 2.7 Pro
Z-Image Turbo
AI Judge Analysis
Wan 2.7 Pro
- + Excellent text rendering with perfect spelling and complete sentences.
- + Natural chalk textures including smudges and dust at the bottom of the board.
- + Beautiful composition that captures a warm café atmosphere in the background.
- − The font looks slightly too uniform and digital, missing the 'elegant cursive' request for the title.
- − The text is very clean and lacks the more varied 'human' slant found in real handwriting.
Z-Image Turbo
- + The handwriting style is very realistic with natural variations in spacing and letterform.
- + Strong chalk texture that feels authentic to a physical board.
- − Contains a spelling error ('Mustroom' instead of Mushroom).
- − The title is in standard block lettering rather than the requested 'elegant cursive'.
- − The layout is cropped tight, losing the 'cozy café' atmosphere requested.
Verdict: Wan 2.7 Pro is the clear winner for its perfect spelling and ability to follow the complex menu instructions without truncating the items. While Z-Image Turbo has a more authentic 'handwritten' aesthetic, its spelling error and lack of background context make it a less successful interpretation of the prompt.
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.”
Wan 2.7 Pro
Z-Image Turbo
AI Judge Analysis
Wan 2.7 Pro
- + Excellent photorealism and texture on the capybara's fur.
- + Accurately places the passenger in the back seat as requested.
- + Highly detailed street background with realistic glass reflections.
- − The capybara's hands look more like primate hands than capybara paws.
- − Minor perspective issue with the driver's head size relative to the car frame.
Z-Image Turbo
- + Natural lighting on the subject's face.
- + Good representation of the bored expression on the passenger's face.
- − The passenger is seated in the front passenger seat instead of the back seat.
- − Detailed paws look somewhat mutated and lack the clear front-paw placement requested.
- − The background is less detailed and lacks the vibrant 'New York at night' feel.
Verdict: Wan 2.7 Pro is the clear winner because it correctly placed the businesswoman in the back seat, whereas Z-Image Turbo placed her in the front next to the driver. Wan 2.7 Pro also provided a much more immersive and realistic New York city background and superior texture work on the taxi interior and the capybara itself.
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.”
Wan 2.7 Pro
Z-Image Turbo
AI Judge Analysis
Wan 2.7 Pro
- + Excellent typography rendering with perfect spelling of all details
- + High-quality, polished illustration style with consistent lighting
- + Superior layout that balances the border, graphics, and text elegantly
- − Illustration style leans slightly more 'storybook' than 'vintage gothic parchment'
Z-Image Turbo
- + Stronger adherence to the 'dark parchment' texture requested
- + Atmospheric, cinematic lighting on the central jack-o-lantern
- − Spelling error in location text ('The Archves' instead of 'The Arches')
- − Fragmented layout with scroll banners that appear disconnected from the background
- − The sub-text at the top is very small and difficult to read
Verdict: Wan 2.7 Pro is the clear winner as it successfully rendered all requested text accurately and integrated it into a professional, cohesive layout. While Z-Image Turbo captured the parchment texture well, it failed on spelling details and had a less polished composition.
Next steps
Explore each model
Tongyi-MAI's 6-billion parameter distilled text-to-image model optimized for speed, achieving high-quality generation in 8 steps or fewer with support for bilingual text rendering