Distilled version of SD 3.5 Large that generates high-quality images in just 4 steps, offering faster inference and reduced costs
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
Stable Diffusion 3.5 Large Turbo
#61 of 62 in Text-to-Image
Wan 2.7 Pro
#37 of 62 in Text-to-Image
Where the votes landed
Stable Diffusion 3.5 Large Turbo
0.0%
win rate
Ties
0.0%
Wan 2.7 Pro
100.0%
win rate
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.”
AI Judge Analysis
Stable Diffusion 3.5 Large Turbo
- + Excellent light and shadow rendering with directional window light.
- + Clean, modern aesthetic with high-quality textures on the wooden table.
- − Failed the spatial reasoning of the prompt by placing the book inside/at the base and the sphere on the book.
- − Plant is to the side rather than behind the cube as requested.
Wan 2.7 Pro
- + Perfect prompt adherence with the book on top and the sphere inside the cube.
- + Highly realistic photographic quality with natural-looking textures and reflections.
- + Correctly placed the plant behind the cube, visible through the glass.
- − The window light is more diffuse than the 'left' side specification might suggest, though still present.
Verdict: Wan 2.7 Pro followed every spatial instruction in the prompt perfectly, placing the red book on top of the cube and the sphere inside it. In contrast, Stable Diffusion 3.5 Large Turbo struggled with the arrangement, placing the book inside the cube and the sphere on top of the book. Wan 2.7 Pro also provided a much more realistic, cohesive photographic scene compared to the more digital render look of Stable Diffusion.
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.”
AI Judge Analysis
Stable Diffusion 3.5 Large Turbo
- + Successfully includes the red bicycle and the elderly man subject.
- − Anatomical errors in the hands and facial structure make the subject look distorted.
- − The bicycle geometry is physically impossible and lacks realistic mechanical parts.
- − Lacks the requested 'candid street photo' feel, appearing more like an AI illustration.
Wan 2.7 Pro
- + Excellent adherence to the 'candid street photo' style with realistic skin textures and lighting.
- + Correctly renders wet pavement reflections and a realistic urban Japanese environment.
- + High mechanical accuracy for the bicycle and natural human posing.
- − The requested 'motion blur from passing cars' is present but subtle, as the cars appear mostly stationary.
- − Missed the 'imperfect framing' prompt as the subject is well-centered.
Verdict: Wan 2.7 Pro significantly outperforms Stable Diffusion 3.5 Large Turbo by delivering a highly realistic, cinematic street photograph that looks authentic to the requested 50mm lens and natural lighting. Stable Diffusion 3.5 Large Turbo fails on basic anatomy and object physics, creating a distorted character and a nonsensical bicycle structure.
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.”
AI Judge Analysis
Stable Diffusion 3.5 Large Turbo
- + Strong composition and vibrant colors
- + Detailed engraving on the armor
- + Very clear and sharp facial features
- − Has a plasticky, CGI-like skin texture
- − Missed the 'beads' in the hair requirement
- − The lighting feels artificial and flat on the skin
Wan 2.7 Pro
- + Excellent adherence to all prompt details including beads, scars, and dirt
- + Photoreal skin texture and lifelike eyes
- + Beautiful warm torchlight and bokeh implementation
- − The leather straps overlap in a slightly confusing way
- − The armor engraving is slightly less sharp than Model A
Verdict: Wan 2.7 Pro is the clear winner for its superior realism and complete prompt adherence, successfully including the specific request for hair beads and realistic battle-worn skin. Stable Diffusion 3.5 Large Turbo produces a more stylized, digital art look with overly smooth skin that misses the 'battle-worn' ruggedness 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.”
AI Judge Analysis
Stable Diffusion 3.5 Large Turbo
- + Excellent food photography quality
- + Bold and readable headers for 'Pizza' and 'Mians'
- − Layout feels like a collection of objects rather than a functional menu design
- − Total lack of actual menu text (uses illegible lines)
- − Unrealistic food shapes that look like 3D renders rather than real dishes
Wan 2.7 Pro
- + Complete and professional menu layout with pricing and descriptions
- + Excellent grid-based organization of food photos
- + High typography quality with brand identity and contact details
- − Minor spelling errors in food items (e.g., 'Cala-riri', 'Seafood Riuotto')
- − Photos on the menu are slightly small for a 3x4 grid structure
Verdict: Wan 2.7 Pro is the clear winner as it creates a fully functional, professional-looking restaurant menu that adheres to all layout and content requirements. Stable Diffusion 3.5 Large Turbo fails to provide an actual design, instead offering a chaotic collage of food icons and mock-up lines that lack the utility required by the prompt.
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.”
AI Judge Analysis
Stable Diffusion 3.5 Large Turbo
- + Strong atmospheric lighting and fiery energy.
- + Good texture on the bun and lettuce.
- − Failed to include any of the requested text.
- − Not an 'exploded' view; the burger is mostly assembled and static.
- − Presence of an illogical stick or wire poking out the top.
Wan 2.7 Pro
- + Excellent adherence to the 'exploded' view with suspended components.
- + Perfect execution of all requested text including 'MAGIC BURGER', 'LIMITED TIME ONLY', and the price starburst.
- + Clean, professional advertisement layout.
- − The 'fiery' effect on the text is a bit literal and illustrative rather than integrated into the scene lighting.
Verdict: Stable Diffusion 3.5 Large Turbo failed to follow almost all instructions beyond the basic subject matter, missing all text and the required exploded composition. Wan 2.7 Pro provided a high-quality commercial-grade image that precisely followed every part of the prompt, including complex text rendering and a dynamic layout.
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.”
AI Judge Analysis
Stable Diffusion 3.5 Large Turbo
- + Clean aesthetic composition
- + Good café atmosphere with lighting and plants
- − Numerous spelling errors including 'apri 3l 20-', 'trulale', and 'ocopus'
- − The text is very stylized and looks more like a digital font than real chalk handwriting
- − Failed to include the specific year 2026 clearly
Wan 2.7 Pro
- + Perfect text adherence with $0 spelling mistakes for all requested items
- + Excellent chalk texture with realistic smudges and dust on the board
- + Handwritten style looks authentic and consistent with the prompt's request
- − The 'cursive' request for the title is interpreted more as a stylized print than traditional flowing cursive
- − Background is slightly less sharp than Model A
Verdict: Wan 2.7 Pro is the clear winner as it flawlessly rendered several lines of complex text with zero typos and maintained a realistic chalk-on-chalkboard texture. Stable Diffusion 3.5 Large Turbo struggled significantly with the text, producing several nonsensical words and failing to complete the menu items requested.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
AI Judge Analysis
Stable Diffusion 3.5 Large Turbo
- + Features a dynamic, cinematic angle with dramatic lighting.
- + The horse's mane and tail show fluid motion which adds to the surreal quality.
- + High-contrast aesthetic creates a bold, graphic look.
- − The horse's front leg is anatomically malformed and missing a hoof.
- − The astronaut's interaction with the saddle and reins is stiff and poorly defined.
Wan 2.7 Pro
- + Excellent anatomical rendering of both the horse and the astronaut's suit.
- + Rich, detailed background with various planets and stars adds to the cosmic theme.
- + Natural composition that feels cohesive and polished.
- − The lighting on the horse is a bit flat compared to the dramatic scene in Model A.
- − Interpretation is slightly more literal and less 'cinematic' in its framing.
Verdict: Both models followed the prompt successfully, including the horse riding the astronaut (horse on top). Wan 2.7 Pro is the winner due to its significantly better anatomical accuracy and rich background details, whereas Stable Diffusion 3.5 Large Turbo suffered from notable distortions in the horse's legs.
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.”
AI Judge Analysis
Stable Diffusion 3.5 Large Turbo
- + Excellent photographic lighting and cinematic atmosphere
- + The capybara's texture and clothing integration are very high quality
- + Composition feels intimate and professional
- − The passenger is very blurry and her action with the phone is not clearly visible
- − The capybara's cap looks more like a modern baseball cap than a traditional taxi hat
Wan 2.7 Pro
- + Perfect adherence to all prompt details, including the businesswoman on her phone
- + Realistic traditional taxi driver cap
- + Both elements (driver and passenger) are in sharp focus and clearly separated
- − The capybara's paws on the steering wheel look more like primate hands, which is anatomically incorrect
- − The lighting is a bit flatter compared to the cinematic feel of the other model
Verdict: Wan 2.7 Pro is the clear winner for prompt adherence, successfully rendering the bored businesswoman on her phone in the back seat which Stable Diffusion 3.5 Large Turbo mostly obscured. While Stable Diffusion 3.5 Large Turbo has more artistic lighting and better fur texture, it failed to clearly illustrate the 'bored businesswoman' part of the narrative.
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.”
AI Judge Analysis
Stable Diffusion 3.5 Large Turbo
- + Features a bold, high-contrast jack-o-lantern at the center.
- + Includes a thorny, web-filled border as requested.
- − Failed to include the specific event details (Date, Time, Location).
- − Failed to include the scroll banner and correct title text.
- − The composition feels empty with large blank spaces.
Wan 2.7 Pro
- + Excellent adherence to text instructions, including the full invitation details and scroll banner.
- + Sophisticated, polished illustration style that fits the 'vintage gothic' request perfectly.
- + Richly detailed composition with moody night sky, lanterns, and twisted trees.
- − The thorns in the border are less prominent than the vine and leaf motif.
- − One of the spiderwebs in the bottom corner is slightly disconnected.
Verdict: Wan 2.7 Pro followed the complex prompt requirements with near-perfect accuracy, including all specific text fields and the scroll banner. Stable Diffusion 3.5 Large Turbo failed to include the event details and most of the requested text, resulting in a generic and functional design compared to the polished and complete vintage invitation created by Wan 2.7 Pro.
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.”
AI Judge Analysis
Stable Diffusion 3.5 Large Turbo
- + Strong isometric composition with a clear diorama feel
- + Good use of 3D-style textures on the wooden base
- − Text rendering is poor with 'SUSHI' misspelled as 'SIIHI'
- − Flag icon is incorrect and appears as a generic red/white shape
- − The text is on floating signs rather than integrated at the 'top-center' of the frame
Wan 2.7 Pro
- + Perfect text rendering for both 'JAPAN' and 'SUSHI'
- + Includes a correct Japanese flag icon as requested
- + Excellent soft refined textures and high-clarity PBR materials
- − The 'diorama base' is a bit flat compared to the requested miniature style
- − Slightly more garnish than 'minimal', though still clean
Verdict: Wan 2.7 Pro followed the text instructions perfectly, including the correct spelling, font placement, and flag icon. Stable Diffusion 3.5 Large Turbo struggled with the spelling of 'SUSHI' and provided a generic flag, though it did capture the 3D diorama aesthetic slightly more literally with the wooden block.
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.”
AI Judge Analysis
Stable Diffusion 3.5 Large Turbo
- + Strong backlight and rim lighting effects
- + Vibrant colors and clean composition
- − Failed to include the requested baby bunny
- − Style is more 3D digital art than hyper-photorealistic
- − Anatomical issues with merged limbs between the cat and dog
Wan 2.7 Pro
- + Successfully included all four animals: puppy, kitten, bunny, and fox
- + Excellent capture of the 'god rays' and 'dew sparkles' atmospheric effects
- + High level of realism in fur textures and environments
- − Minor anatomical floating of the kitten's paw
- − Fox kit features are slightly more adult-like than a 'baby' kit
Verdict: Wan 2.7 Pro is the clear winner as it followed every detail of the prompt, including all four specific animals, whereas Stable Diffusion 3.5 Large Turbo missed the bunny. Additionally, Wan 2.7 Pro achieved a much higher level of photorealism and captured the complex lighting and dew effects requested, while Stable Diffusion 3.5 Large Turbo produced a more stylized, illustrative result with significant anatomical merging.
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.”
AI Judge Analysis
Stable Diffusion 3.5 Large Turbo
- + Strong vector aesthetic with bold contrast
- + Accurate fulfillment of the brown and cream color palette
- + Good use of texture on the background to enhance the vintage feel
- − Misspelled 'Caffè Florian' as 'Caffeé Florin'
- − The cloche is oddly merged with a mug handle, creating a confusing hybrid object
Wan 2.7 Pro
- + Excellent typography with correct accents and layout
- + Classical, ornate emblem style that fits the 1720 era
- + Clean, professional-grade vector lines and shading
- − Misspelled 'Florian' as 'Florion'
- − Included unnecessary peripheral icons in the corners of the frame
Verdict: Wan 2.7 Pro produces a significantly more sophisticated and professional logo that better captures the 'vintage' and 'emblem' requirements, despite a minor spelling error. Stable Diffusion 3.5 Large Turbo fails on its central imagery by merging the cloche with a coffee mug handle and suffers from multiple typos and awkward character rendering.
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.”
AI Judge Analysis
Stable Diffusion 3.5 Large Turbo
- + Strong artistic composition with a dynamic perspective.
- + Captures the high-contrast aesthetic of space art well.
- − Failed to include several requested steps, stopping after four items.
- − Text is largely gibberish and poorly formatted.
- − Does not follow the requested flat-vector infographic layout, opting for a collage style.
Wan 2.7 Pro
- + Excellent adherence to the infographic structure and step-by-step instructions.
- + High-quality text rendering and accurate spelling of names and technical terms.
- + Very clean vector aesthetic with consistent, modern iconography.
- − One minor typo in the word 'DESCENT' (rendered as 'DESCRIPT').
Verdict: Wan 2.7 Pro is the clear winner as it directly followed the complex instructional prompt, creating a functional and professional vertical infographic with all six requested steps and legible, accurate text. Stable Diffusion 3.5 Large Turbo failed on almost every instruction, producing a decorative poster with garbled text and incomplete information.
Explore each model
Alibaba's Wan 2.7 Pro image generation and editing model with higher-quality outputs and support for 4K image generation