Head to head
Esc

Models · slot A

to navigate to pick

Stable Diffusion 3.5 Medium Stability AI Wan 2.7 Pro Alibaba

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

Stable Diffusion 3.5 Medium

16.8 arena score

#56 of 62 in Text-to-Image

Skill signature · Text-to-Image

Wan 2.7 Pro

20.7 arena score

#38 of 62 in Text-to-Image

Vote tally

Where the votes landed

Stable Diffusion 3.5 Medium

0.0%

win rate

Ties

0.0%

Wan 2.7 Pro

100.0%

win rate

0.0% 0.0% ties 100.0%
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.”

Stable Diffusion 3.5 Medium
Wan 2.7 Pro

AI Judge Analysis

Stable Diffusion 3.5 Medium

  • + Excellent adherence to lighting instructions (soft light from the left)
  • + High clarity in the glass rendering and the blue sphere
  • + Very artistic, clean composition
  • The sphere appears to be floating unnaturally rather than resting on the bottom
  • The green plant is less distinct in the background compared to the other image

Wan 2.7 Pro

  • + Extremely realistic wood texture on the table
  • + The sphere correctly rests on the bottom of the cube with a visible reflection
  • + Comprehensive adherence to all spatial elements in the prompt
  • The red book is slightly cropped at the top and left
  • The 'cube' looks slightly more like a tall rectangular prism

Verdict: Both models followed the prompt perfectly, but Wan 2.7 Pro is the winner due to its superior realism and physical grounding, particularly how the sphere rests on the bottom of the cube. While Stable Diffusion 3.5 Medium produced a very clean and artistic image with great lighting, the floating sphere felt slightly less grounded in reality.

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.”

Stable Diffusion 3.5 Medium
Wan 2.7 Pro

AI Judge Analysis

Stable Diffusion 3.5 Medium

  • + Strong cinematic atmosphere with high-contrast lighting and rich colors.
  • + Excellent texture on the wet pavement with realistic puddles and reflections.
  • + Effective use of shallow depth of field to create an intimate mood.
  • Anatomical issues with the man's hands appearing fused and distorted.
  • The bicycle geometry is illogical, particularly the frame and pedal placement.
  • Does not include the requested motion blur from passing cars.

Wan 2.7 Pro

  • + Highly realistic skin textures and facial details on the man.
  • + Very accurate bicycle anatomy including the chain, gears, and frame.
  • + Better adherence to the 'candid' and 'natural' request with a neutral color profile.
  • The cars in the background are sharp rather than having motion blur as requested.
  • The lighting is somewhat flat compared to the cinematic request.
  • The man's feet proportions look slightly small relative to the rest of his body.

Verdict: Wan 2.7 Pro is the clear winner due to its superior anatomical rendering of both the human subject and the complex machinery of the bicycle, whereas Stable Diffusion 3.5 Medium suffers from significant structural distortions. While Stable Diffusion 3.5 Medium captured a more dramatic cinematic lighting, Wan 2.7 Pro achieved a much more convincing sense of realism and prompt adherence regarding skin texture.

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.”

Stable Diffusion 3.5 Medium
Wan 2.7 Pro

AI Judge Analysis

Stable Diffusion 3.5 Medium

  • + Intense and lifelike eyes with complex iris detailing
  • + Excellent dramatic lighting that creates high contrast on the skin and metal
  • + Vibrant color palette and energetic bokeh sparks
  • Missed the request for beads in the hair braids
  • The hair texture looks a bit oily and messy rather than just battle-worn
  • Less 'ornate' engraving on the armor compared to Model B

Wan 2.7 Pro

  • + Perfect adherence to all prompt details including the beads in the braids
  • + Exquisite texture on the leather straps and underlayer fabric
  • + Realistic scars and dirt application that Feels more integrated into the skin
  • Lighting is a bit flatter and less dramatic than Model A
  • The 'lifelike' quality of the eyes is slightly less striking than Model A

Verdict: Both models performed exceptionally well, but Wan 2.7 Pro followed the prompt more accurately by including the requested beads in the hair braids and providing more detailed textures on the leather and cloth. While Stable Diffusion 3.5 Medium produced a more dramatically lit and intense portrait, Wan 2.7 Pro felt like a more complete and coherent realization of the specific character description.

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.”

Stable Diffusion 3.5 Medium
Wan 2.7 Pro

AI Judge Analysis

Stable Diffusion 3.5 Medium

  • + Features a true white background as requested
  • + Includes multiple food photos in a structured grid
  • Text consists entirely of gibberish characters
  • Low visual quality with blurry images and inconsistent font weights
  • Layout is cluttered and lacks professional alignment

Wan 2.7 Pro

  • + Excellent typography with mostly legible text and bold sans-serif headers
  • + High-quality, appetizing food photography
  • + Professional composition featuring a realistic restaurant brand (Bread & Bowl)
  • Includes elements not strictly requested like social media icons and a QR code
  • Text has minor spelling errors (e.g., 'Calariri', 'Alferdo')

Verdict: Wan 2.7 Pro is the clear winner as it produces a professional-grade graphic design piece with legible text, logical sections, and high-quality food photography. Stable Diffusion 3.5 Medium fails to produce readable text and the resulting layout feels like an unfinished sketch rather than a professional menu.

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.”

Stable Diffusion 3.5 Medium
Wan 2.7 Pro

AI Judge Analysis

Stable Diffusion 3.5 Medium

  • + Excellent photorealistic texture on the bun and meat patty
  • + Accurate rendering of the price text and secondary message
  • + Natural-looking fire lighting effects on the subject
  • Failed to follow the 'exploded' instructions, showing a mostly assembled burger
  • Text lacks the requested 'fiery, glowing effect'
  • Starburst element is a simple black and white graphic rather than integrated into the scene

Wan 2.7 Pro

  • + Perfect adherence to the 'exploded' composition with suspended ingredients
  • + Excellent integration of the fiery, glowing text effects requested
  • + Dynamic layout with high energy and better thematic consistency
  • The 'MAGIC BURGER' title occupies a very large portion of the frame, slightly overshadowing the food
  • Some minor repetition in small garnish elements (cucumber/parfley)

Verdict: Wan 2.7 Pro is the clear winner as it followed every detail of the prompt, including the difficult 'exploded' burger composition and the specific 'fiery' styling for the text. Stable Diffusion 3.5 Medium produced a high-quality photorealistic image but failed significantly on the layout requirements and the aesthetic styling of the typography.

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.”

Stable Diffusion 3.5 Medium
Wan 2.7 Pro

AI Judge Analysis

Stable Diffusion 3.5 Medium

  • + Features a very realistic chalk texture and dust effect on a blackboard surface.
  • + Captures the requested 'slight slant' and natural variation in artistic flourishes.
  • Serious spelling errors and illegible text across almost the entire board.
  • Completely fails to render the requested date 'April 30, 2026' correctly.
  • Poor layout with overlapping text and nonsensical numbers.

Wan 2.7 Pro

  • + Excellent prompt adherence with near-perfect spelling of all menu items.
  • + Consistent and legible handwriting style across the entire board.
  • + Successfully renders the specific date and price points requested.
  • Handwriting appears slightly too uniform, bordering on a digital font look.
  • The chalk texture is less pronounced compared to the board in the other image.

Verdict: Wan 2.7 Pro is the clear winner as it successfully rendered all requested text, including the specific date and complex menu items, with perfect spelling. Stable Diffusion 3.5 Medium produced a more realistic chalk texture, but the text itself was largely illegible gibberish that failed to meet the core requirements of the prompt.

The Reversed Rodeo

Text-to-Image

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

Stable Diffusion 3.5 Medium
Wan 2.7 Pro

AI Judge Analysis

Stable Diffusion 3.5 Medium

  • + The astronaut follows the horse's anatomy realistically for a riding position.
  • + The lighting on the horse and astronaut matches the planet below well.
  • + The image has a high level of cinematic clarity and sharp focus.
  • Failed the specific structural instruction of 'horse on top, not vice versa'.
  • There are anatomical glitches with the horse's legs merged into the astronaut's boots.

Wan 2.7 Pro

  • + Features a more complex background with multiple planets and celestial bodies.
  • + The rendering of the horse's coat and muscle detail is very high quality.
  • + Clean composition with no significant limb artifacts.
  • Failed the specific structural instruction of 'horse on top, not vice versa'.
  • Gravity-defying elements like the tiny floating planets look a bit cluttered.

Verdict: Both Stable Diffusion 3.5 Medium and Wan 2.7 Pro completely failed the negative constraint/spatial instruction to place the horse on top of the astronaut, both providing the standard 'astronaut on horse' trope instead. Wan 2.7 Pro is the preferred image because its composition is cleaner and it avoids the anatomical clipping and leg artifacts present in the Stable Diffusion 3.5 output.

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.”

Stable Diffusion 3.5 Medium
Wan 2.7 Pro

AI Judge Analysis

Stable Diffusion 3.5 Medium

  • + Excellent close-up detail on the capybara's fur and expression
  • + Strong cinematic lighting that matches a NYC night atmosphere
  • + Accurate depiction of the yellow taxi driver cap and dark jacket
  • Missed the 'human in the back seat' prompt as she is sitting in the front passenger seat
  • Human character is not looking at a phone
  • Steering wheel is nearly invisible due to the tight framing

Wan 2.7 Pro

  • + Correctly places the human passenger in the back seat with a phone
  • + Accurately depicts the capybara with both paws on the steering wheel
  • + Captures the 'bored' expression of the passenger very well
  • The paws on the steering wheel look more like primate hands than capybara paws
  • The capybara's head has a slightly cut-and-paste appearance against the background
  • The car interior layout is slightly confusing with the passenger's proximity to the driver

Verdict: Wan 2.7 Pro is the clear winner for prompt adherence, correctly including the human passenger in the back seat with her phone, whereas Stable Diffusion 3.5 Medium placed her in the front and omitted the phone. While Stable Diffusion 3.5 Medium has superior textures and more artistic lighting, it failed on several key spatial and object-based instructions.

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.”

Stable Diffusion 3.5 Medium
Wan 2.7 Pro
0% wins 0% ties 100% wins

AI Judge Analysis

Stable Diffusion 3.5 Medium

  • + Successfully incorporates twisted trees and bats into the background
  • + The layout resembles a classic aged parchment poster
  • Numerous spelling errors including 'Halloweeen' and 'Inviloween'
  • Poor text rendering for the small details and location
  • Illogical placement of pumpkins in trees

Wan 2.7 Pro

  • + Flawless text rendering for both titles and specific details
  • + Exquisite artistic composition with cinematic lighting and a clear scroll banner
  • + Perfect adherence to all prompt elements including the specific date and location
  • The jack-o-lantern is central but sits in a landscape rather than on a single parchment sheet
  • Slightly less 'gritty' gothic aesthetic in favor of a polished digital art look

Verdict: Wan 2.7 Pro followed the instructions perfectly, delivering an image with immaculate text rendering and a beautiful, balanced composition. Stable Diffusion 3.5 Medium struggled significantly with the text requirements, producing multiple spelling errors and garbled details that make the invitation unusable.

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.”

Stable Diffusion 3.5 Medium
Wan 2.7 Pro

AI Judge Analysis

Stable Diffusion 3.5 Medium

  • + Strong texture rendering on the sushi nori and ikura.
  • + Vibrant color palette that pops against the background.
  • Missed the 'small flag icon' requirement.
  • The text 'SUSHI' has a strange transparency artifact on the first 'S'.
  • Did not include a 'raised diorama base', using a standard plate instead.

Wan 2.7 Pro

  • + Followed all prompt instructions including the flag icon and the raised diorama base.
  • + Excellent 3D miniature/cartoon aesthetic with clean, soft-rounded textures.
  • + Perfect text rendering and layout.
  • Minor stray elements at the very edges of the frame.

Verdict: Wan 2.7 Pro is the clear winner as it adhered to every specific detail of the prompt, including the flag icon and the diorama base which Stable Diffusion 3.5 Medium ignored. Wan 2.7 Pro also achieved a much more professional 'miniature 3D cartoon' aesthetic with cleaner typography and lighting.

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.”

Stable Diffusion 3.5 Medium
Wan 2.7 Pro

AI Judge Analysis

Stable Diffusion 3.5 Medium

  • + Vibrant, saturated colors that create a joyful aesthetic
  • + Detailed fur textures and expressive eyes on the animals
  • Failed to include the baby bunny requested in the prompt
  • The middle animal is an ambiguous cat-fox hybrid rather than a clear tabby kitten
  • The composition is static and lacks the 'tumbling/chasing' action requested

Wan 2.7 Pro

  • + Correctly included all four requested animals: puppy, kitten, bunny, and fox
  • + Successfully captured the dynamic action of tumbling and chasing
  • + Excellent implementation of 'god rays' and dew sparkles for a photorealistic look
  • The kitten's anatomy is slightly awkward where it interacts with the puppy and bunny
  • The puppy's tail has a slightly unnatural shape

Verdict: Wan 2.7 Pro is the clear winner as it followed the prompt perfectly, including all four specific animals and the requested action of tumbling together. Stable Diffusion 3.5 Medium failed to include the bunny and produced ambiguous animal species, resulting in a more generic and static portrait.

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.”

Stable Diffusion 3.5 Medium
Wan 2.7 Pro

AI Judge Analysis

Stable Diffusion 3.5 Medium

  • + Strong vintage illustration style with rich hand-drawn linework
  • + Accurate color palette according to the prompt
  • Significant spelling errors in both the brand name and the date
  • Lack of a clear cloche dome as requested
  • Overly complex and messy composition compared to a minimalist logo

Wan 2.7 Pro

  • + Perfectly follows the requested composition including a clear cloche, steam, and banner
  • + Captures the vector emblem style with clean, professional layouts
  • + Correctly renders the date 'Est. 1720'
  • Minor spelling error in the name ('Florion' instead of 'Florian')
  • Included unnecessary decorative elements in the corners outside the logo area

Verdict: Wan 2.7 Pro is the clear winner as it accurately interprets all elements of the prompt including the cloche dome, the specific date, and the vector logo aesthetic. Stable Diffusion 3.5 Medium failed on text accuracy and the central icon requirement, producing a cluttered and illegible emblem.

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.”

Stable Diffusion 3.5 Medium
Wan 2.7 Pro

AI Judge Analysis

Stable Diffusion 3.5 Medium

  • + Successfully used the specified NASA-inspired color palette.
  • + Achieved a modern, stylized aesthetic with nice linework.
  • Failed to provide legible text, with most words being gibberish.
  • The iconography is inconsistent and does not clearly match the requested steps.
  • Poor composition that feels cluttered and lacks a clear narrative flow.

Wan 2.7 Pro

  • + Excellent adherence to all six requested steps with perfectly matched iconography.
  • + Impressive text rendering with accurate names, dates, and technical data.
  • + Professional infographic layout with a clear vertical progression and a clean vector style.
  • Decent spelling overall but has minor typos like 'Descript' for Descent.
  • The astronaut icons at the bottom are slightly generic compared to the detailed gear icons.

Verdict: Wan 2.7 Pro is the clear winner as it perfectly followed the complex multi-step instructions and technical diagramming requested. While Stable Diffusion 3.5 Medium produced a stylized artistic image, it failed to provide functional icons or legible text, whereas Wan 2.7 Pro created a genuine, readable infographic with professional layout and accurate content.

Next steps

Explore each model