Alibaba's Wan 2.7 image generation and editing model for text-to-image, reference-guided generation, and instruction-based image edits
Settled by community votes across 3 shared challenges, with an AI judge weighing in on each.
Wan 2.7
19.0
arena score
#34 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
0%
win rate
Ties
0%
Z-Image Turbo
0%
win rate
Shared challenges
3
Challenge by challenge
The strongest take from each model on every shared challenge, with the AI judge's read.
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
Z-Image Turbo
AI Judge Analysis
Wan 2.7
- + Excellent layout and overall visual aesthetic.
- + Higher image quality and better environmental context.
- + Completes the third menu item correctly despite the prompt being cut off.
- − The font looks like a clean digital script rather than actual chalk handwriting.
- − The text has a consistent drop shadow and uniform thickness that feels artificial.
- − Missing 'elegant cursive' for the title.
Z-Image Turbo
- + Persuasive chalk texture with realistic powdery edges.
- + Captures the 'handwritten' request much better with natural letter variations.
- + Adheres to the specific request for chalk texture instead of a digital overlay.
- − Contains a spelling error ('Mustroom').
- − The composition is a bit more cramped with the text nearly touching the edges.
- − Slightly less clarity in the overall image compared to model A.
Verdict: Wan 2.7 produces a more visually polished image, but fails the negative constraint by using what appears to be a digital font with artificial shadows. Z-Image Turbo much more accurately captures the requested realistic chalk handwriting style and texture, making it the better choice for this specific prompt despite a minor spelling error.
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
Z-Image Turbo
AI Judge Analysis
Wan 2.7
- + Excellent photorealism in the textures of the capybara's fur and the jacket fabric.
- + Successfully placed the human passenger in the back seat as requested.
- + The lighting and reflections on the glass and car body are very realistic for a nighttime city scene.
- − The passenger is sitting in the right-side seat, making it look like she is in the front passenger seat rather than the back.
- − The capybara's claws/paws are slightly distorted as they grip the wheel.
Z-Image Turbo
- + The capybara's expression and posture perfectly match the 'calm, professional' description.
- + Good separation of foreground and background with city light bokeh.
- + Accurate rendering of the driver's cap and uniform jacket.
- − The passenger appears to be in the front passenger seat, failing the 'back seat' part of the prompt.
- − The perspective of the steering wheel and the driver's arms is slightly awkward and lacks depth.
- − Low visibility of the 'New York' setting outside compared to Model A.
Verdict: Wan 2.7 provides a much more detailed and photorealistic image with convincing textures and complex city reflections. While both models failed to clearly place the passenger in the back seat (both appearing to put her in the front next to the driver), Wan 2.7's superior rendering of the taxi's exterior and interior environment makes it the stronger choice.
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
Z-Image Turbo
AI Judge Analysis
Wan 2.7
- + Perfect text rendering for all requested fields including the specific date and location
- + Highly detailed and decorative border with thorns, webs, and skulls
- + Excellent composition with a focused central illustration and balanced layout
- − The style leans more toward vintage illustration than cinematic realism
- − The 'Est. 1847' text was not requested in the prompt
Z-Image Turbo
- + Captures a more cinematic and moody lighting style
- + The torn parchment aesthetic provides a nice sense of depth and texture
- − Misspelled location as 'The Archves'
- − The scroll banner text is placed at the top rather than near the banner element
- − The overall layout feels a bit cluttered with overlapping elements
Verdict: Wan 2.7 is the clear winner as it followed every instruction perfectly, including complex text rendering with zero spelling errors. While Z-Image Turbo captured the cinematic lighting well, it failed on a key detail by misspelling the location name and lacked the polished, professional layout found in Wan 2.7.
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