Head to head
Esc

Models · slot A

to navigate to pick

Stable Diffusion 3.5 Large 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 Large

22.8 arena score

#30 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 Large

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.”

Stable Diffusion 3.5 Large
Wan 2.7 Pro

AI Judge Analysis

Stable Diffusion 3.5 Large

  • + Excellent surface textures and realistic reflections on the glass and wood.
  • + Strong adherence to the lighting direction requested.
  • + High spatial clarity between the foreground and background elements.
  • Failed the spatial prompt logic by placing the red book inside the cube and the sphere on top of the book.
  • The cube structure appears more like a five-sided cover than a solid glass cube.

Wan 2.7 Pro

  • + Perfect adherence to all spatial instructions, placing the book on top and the sphere inside.
  • + Beautiful, realistic rendering of the green fern behind the glass.
  • + Naturalistic photography style with believable wood grain and shadows.
  • The base of the glass cube appears to have a mirrored finish that wasn't explicitly requested.
  • Slightly less 'clinical' or sharp focus on the glass edges compared to Model A.

Verdict: Wan 2.7 Pro is the clear winner because it followed every instruction in the complex spatial prompt, correctly placing the red book on top of the cube and the sphere inside it. In contrast, Stable Diffusion 3.5 Large failed the relational logic by placing the book under the sphere, despite both models producing high-quality, photorealistic textures.

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 Large
Wan 2.7 Pro

AI Judge Analysis

Stable Diffusion 3.5 Large

  • + Excellent atmospheric lighting and cinematic mood
  • + Strong adherence to the rain and wet pavement reflections
  • + Impressive skin texture and realistic age details on the man's arms
  • The bicycle frame geometry is physically impossible near the handlebars
  • Lacks the motion blur from cars requested in the prompt

Wan 2.7 Pro

  • + Exceptional realism in the skin and clothing textures
  • + More accurate bicycle mechanical details overall
  • + Better captures the 'candid' street photography aesthetic and depth of field
  • Missing the motion blur for passing cars
  • Reflections on the ground are slightly less pronounced than in Model A

Verdict: Wan 2.7 Pro is the superior image as it achieves a high level of photorealism with an believable candid aesthetic, while Stable Diffusion 3.5 Large suffers from significant anatomical errors in the bicycle's construction. Wan 2.7 Pro also handles the shallow depth of field and Japanese street environment more authentically.

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 Large
Wan 2.7 Pro

AI Judge Analysis

Stable Diffusion 3.5 Large

  • + Exquisitely detailed engraving on the plate armor
  • + Intense, lifelike expression with high-quality skin texture
  • + Excellent rendering of chainmail and fabric textures
  • Missed the prompt instruction for beads in the hair braids
  • The background characters are a bit blurry and indistinct

Wan 2.7 Pro

  • + Perfect adherence to the beads in braids prompt
  • + Accurate leather strap textures and belt buckles
  • + Excellent warm lighting effects from the torches
  • The facial feature rendering is slightly less sharp than Model A
  • The armor engraving is a bit simpler in design

Verdict: Both models performed exceptionally well, capturing the atmosphere of a battle-worn warrior. Stable Diffusion 3.5 Large wins on pure texture quality, especially regarding the intricate armor engravings and facial intensity, but Wan 2.7 Pro followed the specific prompt details more closely by including the requested beads in the hair and the leather strap details.

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 Large
Wan 2.7 Pro

AI Judge Analysis

Stable Diffusion 3.5 Large

  • + Strong minimalist aesthetic with bold typography
  • + High-quality, vibrant food photography
  • + Clean symmetrical composition
  • Poor text legibility with many spelling errors
  • Layout feels more like a poster than a functional menu
  • Sections for appetizers, pizza, and mains are not clearly demarcated from one another

Wan 2.7 Pro

  • + Excellent functional menu layout with logical sections
  • + Impressive text rendering and nearly perfect spelling
  • + Realistic presentation and professional graphic design elements
  • Image is a mock-up on a table rather than a raw design file
  • The 'colorful food photos in grid' are smaller compared to Model A

Verdict: Wan 2.7 Pro is the clear winner as it produced a highly functional and legible menu that follows all prompt instructions, including specific sections and pricing. Stable Diffusion 3.5 Large created a visually striking artistic layout, but the text is largely gibberish and it lacks the structural organization required for a restaurant 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 Large
Wan 2.7 Pro

AI Judge Analysis

Stable Diffusion 3.5 Large

  • + Excellent photorealistic texture on the meat and bun
  • + Dynamic lighting and impressive fire effects
  • + Strong sense of motion with glowing embers
  • Failed to include any of the requested text
  • Missing the 'exploded' view where components are separated

Wan 2.7 Pro

  • + Perfect adherence to text-based instructions and layout
  • + Correctly interpreted the 'exploded' burger composition
  • + Clean graphic design suitable for a real advertisement
  • The meat patty looks slightly less realistic than in the competing image
  • The cheese slice has a very flat, plastic-like texture

Verdict: Stable Diffusion 3.5 Large produced a visually stunning, high-conrast image with great lighting, but completely failed to include the requested text or the specific 'exploded' layout. Wan 2.7 Pro followed every part of the prompt, including the text elements and the suspended-component composition, making it the superior choice for an actual advertisement.

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 Large
Wan 2.7 Pro

AI Judge Analysis

Stable Diffusion 3.5 Large

  • + Excellent environmental context showing the cafe interior and lighting.
  • + The handwriting has a genuine chalk-like smear and texture.
  • Failed significantly on text accuracy with numerous typos like 'TODAAY' and 'Muglrrom'.
  • The year was rendered as 2024 instead of the requested 2026.
  • The layout becomes jumbled and unreadable toward the bottom.

Wan 2.7 Pro

  • + Flawless text rendering with 100% accuracy for all requested items and the specific date.
  • + Consistently high-quality chalk texture and handwriting style throughout the board.
  • + Successfully inferred and completed the truncated 'Brown But...' prompt to 'Brown Butter Chocolate Chip Cookies'.
  • The composition is a very tight shot of the board with less café atmosphere visible than the other model.
  • The handwriting is slightly more uniform than requested, leaning towards a 'chalk font' aesthetic rather than natural variation.

Verdict: Wan 2.7 Pro is the clear winner as it perfectly captured the complex text requirements, including the specific date and menu items which Stable Diffusion 3.5 Large failed to spell correctly. While Stable Diffusion 3.5 Large provided a more interesting wide shot of the café, its inability to render the core text prompt makes it less useful for this specific challenge.

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 Large
Wan 2.7 Pro

AI Judge Analysis

Stable Diffusion 3.5 Large

  • + Excellent cinematic lighting and atmosphere
  • + Dynamic sense of motion with dust/nebula effects
  • + Integrated high-quality composition with a vast planetary scale
  • Failed the negative prompt constraint: the horse is on the bottom, not the top

Wan 2.7 Pro

  • + Clean, high-resolution rendering of the astronaut and saddle
  • + Clear, surreal composition with floating miniature planets
  • Failed the negative prompt constraint: the horse is on the bottom, not the top
  • The horse's anatomy is slightly elongated and awkward
  • Lighting feels flat compared to the cinematic request

Verdict: Both models failed the specific spatial logic request ('horse riding astronaut... horse on top'), instead opting for the cliche astronaut riding a horse. Stable Diffusion 3.5 Large is the superior image due to its stunning cinematic lighting, atmospheric depth, and much more natural horse anatomy. Wan 2.7 Pro feels static and has some anatomical wonkiness in the horse's legs and torso.

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 Large
Wan 2.7 Pro

AI Judge Analysis

Stable Diffusion 3.5 Large

  • + Excellent texture on the capybara fur and clothing jacket
  • + Strong color saturation and bokeh effect for a nighttime city feel
  • + Detailed interior elements like the rearview mirror and dashboard lighting
  • Completely failed to include the human businesswoman in the back seat
  • One paw is missing from the steering wheel
  • Anatomy issues where the capybara has realistic human legs and jeans

Wan 2.7 Pro

  • + Successfully included all prompt elements, including the businesswoman and her phone
  • + Accurate capybara driver hat style as requested
  • + Both paws are clearly placed on the steering wheel
  • The human face and hands have some slight AI distortion
  • The capybara's paws look more like primate hands than rodent paws
  • The background exterior feels a bit flatter compared to the lighting in image A

Verdict: Stable Diffusion 3.5 Large produced a visually striking image with superior textures, but it completely ignored a major part of the prompt by omitting the businesswoman. Wan 2.7 Pro correctly followed the complex multi-subject instructions, capturing the interaction between the capybara driver and the bored passenger, making it the more successful image for this specific prompt.

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 Large
Wan 2.7 Pro

AI Judge Analysis

Stable Diffusion 3.5 Large

  • + Strong atmospheric lighting with a high-contrast cinematic moon
  • + Effective use of the parchment texture for the border
  • + Captures the 'twisted trees' prompt very well with a dark, spooky silhouette style
  • Completely failed to include the specific event details (Date, Time, Location) at the bottom
  • The layout is cluttered with text overlapping the central illustration
  • Minor typos in the banner text including 'nigth' instead of 'night'

Wan 2.7 Pro

  • + Perfect adherence to all text requirements, including date, time, and location
  • + Excellent composition that balances typography and illustration for a functional invitation
  • + Rich level of detail in the border elements including thorns, webs, and lanterns
  • The color palette is slightly warmer and less 'moody' than the prompt suggested
  • The illustration style is more illustrative/digital art and less 'vintage/cinematic' than Model A

Verdict: Wan 2.7 Pro is the clear winner for its superior ability to follow complex text-based instructions, perfectly rendering all required event details and the scroll banner without typos. While Stable Diffusion 3.5 Large captured the 'moody night sky' and cinematic atmosphere more effectively, its complete omission of the location and time details makes it fail as an invitation.

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 Large
Wan 2.7 Pro

AI Judge Analysis

Stable Diffusion 3.5 Large

  • + Features a highly detailed variety of sushi types
  • + Excellent texture work on the salmon and rice grains
  • Failed the text placement instructions by putting text on a physical sign rather than top-center
  • The composition feels cluttered and lacks the 'minimal garnish' requested

Wan 2.7 Pro

  • + Perfect adherence to text placement and formatting instructions
  • + Captures the 'miniature 3D cartoon' style with clean, soft PBR materials
  • + Beautifully centered isometric composition on a clean diorama base
  • Small amount of extra text ('Authentic Japanese Cuisine') not explicitly requested
  • Simplified sushi models compared to the complexity of the first image

Verdict: Wan 2.7 Pro followed the complex layout instructions significantly better than Stable Diffusion 3.5 Large, placing the text and flag exactly where requested in a graphic design format. While Stable Diffusion 3.5 Large produced more realistic textures, it failed the specific composition and text placement prompts, resulting in a cluttered scene rather than a clean diorama.

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 Large
Wan 2.7 Pro

AI Judge Analysis

Stable Diffusion 3.5 Large

  • + Features a luminous atmosphere with soft bokeh and glowing particles.
  • + Displays high-energy expressions that feel very joyful.
  • The kitten lacks distinct tabby markings and looks somewhat generic.
  • The rabbit has a butterfly merged with its ear.

Wan 2.7 Pro

  • + Excellent adherence to all specified animal types including a clear tabby pattern.
  • + Superior composition with more interaction between the animals.
  • The lighting is a bit flat compared to the requested god rays.
  • Shadows on the grass are slightly inconsistent with the light source.

Verdict: Wan 2.7 Pro is the winner because it successfully included all four distinct animal species with accurate markings, whereas Stable Diffusion 3.5 Large struggled with the kitten's appearance. Additionally, Wan 2.7 Pro captured a more cohesive group dynamic that better reflected the 'tumbling together' part of the prompt.

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 Large
Wan 2.7 Pro

AI Judge Analysis

Stable Diffusion 3.5 Large

  • + Strong minimalist vector aesthetic
  • + Excellent typography on the 'Est. 1720' text
  • + Good use of subtle grunge texture on the background
  • Spelling error in primary name ('Cafféé' instead of 'Caffè')
  • The cloche is split in a visually confusing way with odd shapes inside it

Wan 2.7 Pro

  • + Sophisticated vintage engraving style
  • + Higher overall visual quality and detail
  • + Accurate depiction of a cloche dome and steam swirls
  • Minor spelling error in the name ('Florion' instead of 'Florian')
  • Less minimalist than requested, leaning into a more decorative badge style

Verdict: Stable Diffusion 3.5 Large followed the minimalist aesthetic more closely but suffered from a significant spelling error in the main brand name and a messy central illustration. Wan 2.7 Pro produced a much more professional-looking vintage emblem with superior illustrative quality, though it slightly missed the 'minimalist' requirement and had a minor typo in the second word.

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 Large
Wan 2.7 Pro

AI Judge Analysis

Stable Diffusion 3.5 Large

  • + Large, detailed lunar surface illustration
  • + Interesting visual complexity in the background
  • Failed the vector-style requirement by including a Space Shuttle instead of a Saturn V
  • Nonsense text and symbols that don't follow an infographic structure
  • Incorrect colors, using a cream background instead of the requested palette

Wan 2.7 Pro

  • + Followed the specific step-by-step instructions perfectly with accurate icons
  • + Clean, modern vector infographic aesthetic that matches the prompt exactly
  • + Excellent legibility and historical accuracy with names, dates, and mission data
  • Minor spelling errors in text (e.g., 'Descript' instead of 'Descent')

Verdict: Wan 2.7 Pro is the clear winner as it followed every detail of the complex instructional prompt, producing a logically structured and beautiful infographic with the correct NASA color palette. Stable Diffusion 3.5 Large failed on a fundamental level by depicting a Space Shuttle—which never went to the moon—and failed to organize the content into a readable step-by-step vector infographic.

Next steps

Explore each model