Black Forest Labs' enhanced 12-billion parameter flow transformer with 6x faster generation than FLUX.1 [pro], delivering superior composition, detail, and artistic fidelity
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
FLUX1.1 [pro]
#50 of 62 in Text-to-Image
Wan 2.5 (Preview)
#27 of 62 in Text-to-Image
Where the votes landed
FLUX1.1 [pro]
0.0%
win rate
Ties
0.0%
Wan 2.5 (Preview)
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
FLUX1.1 [pro]
- + Excellent refraction and reflection details in the glass cube
- + High-fidelity texture on the red book cover
- + Clean and modern composition
- − The 'cube' is tall and rectangular rather than a standard cube shape
- − The blue sphere is quite large compared to the description of 'small'
Wan 2.5 (Preview)
- + Accurately depicts a standard cube shape
- + The blue sphere is sized more appropriately to the 'small' descriptor
- + Realistic lighting interaction with the table texture
- − The plant is more to the side than 'behind' the cube
- − Distracting dust or particle artifacts in the air
Verdict: Wan 2.5 (Preview) better followed the requested geometric proportions, providing a true cube and a smaller sphere. However, FLUX1.1 [pro] produced a much cleaner image with superior material rendering, specifically on the glass and book texture, making it more aesthetically pleasing despite the rectangular cube.
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
FLUX1.1 [pro]
- + Excellent capture of the 'candid street' aesthetic with realistic lighting
- + Beautiful reflections on wet pavement that feel integrated into the scene
- − Serious anatomical and structural failures: the bicycle is missing its rear half, and the man's lower legs and feet are nonsensical
- − Lack of motion blur from cars as requested
Wan 2.5 (Preview)
- + Successfully depicts the 'repairing' action with tools on the ground
- + Clear representation of light rain and atmospheric depth
- + Anatomically correct pose and fully formed bicycle
- − Lacks the requested motion blur from passing cars
- − The skin texture on the arms appears slightly smudged or filtered compared to the face
Verdict: While FLUX1.1 [pro] captures a more authentic 'street photography' mood and lighting style, it fails significantly on a structural level with a broken bicycle and mangled limbs. Wan 2.5 (Preview) provides a much more coherent and prompt-accurate scene, depicting a complete bicycle and a logical repairing action, making it the superior image despite a slightly less 'cinematic' feel.
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
FLUX1.1 [pro]
- + Intense, high-fidelity skin texture and lifelike eye detail
- + Excellent cinematic lighting with integrated bokeh sparks
- + Realistic integration of dirt and weathering on the character's face
- − The hair braids and beads requested are barely visible and poorly defined
- − Armor engraving is less distinct than the competitor
Wan 2.5 (Preview)
- + Excellent adherence to specific details like the braided hair with beads
- + Highly detailed engraving on the plate armor and visible texture on leather straps
- + Clearly defines the requested cloth underlayer and chainmail
- − The character looks much younger than expected for a battle-worn paladin
- − The torch in the background is a bit distracting compared to the more subtle sparks in Model A
Verdict: FLUX1.1 [pro] provides a more cinematic and gritty portrait with superior eye and skin realism, though it struggles with the specific hair braid requirement. Wan 2.5 (Preview) captures all the technical prompt details—including the hair beads, leather straps, and ornate engraving—much more accurately, even though the lighting and facial features are slightly more stylized. Wan 2.5 is the preferred choice for detailed prompt adherence, while FLUX1.1 is better for overall visual impact.
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
FLUX1.1 [pro]
- + Strong professional presentation with realistic silverware and layout
- + Clean use of white space and modern sans-serif fonts
- + Good variety in the photo grid with clear Pizza branding
- − The text is largely illegible and contains gibberish
- − The layout is more of a product mockup than a flat design
Wan 2.5 (Preview)
- + Perfectly follows the grid request for food photos
- + Highly legible section headers for Appetizers, Pizza, and Mains
- + Exceptional food photography quality and color vibrancy
- − Text on the right side becomes slightly cluttered
- − The header text 'Restormalit Menue' includes a misspelling
Verdict: FLUX1.1 [pro] provides a more realistic-looking photograph of a physical menu, but Wan 2.5 (Preview) better follows the structural requirements of the prompt by organizing the content into the requested sections (Appetizers/Pizza/Mains) with a clear, functional grid. Wan 2.5 is preferred for its superior layout organization and more readable typography.
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
FLUX1.1 [pro]
- + Excellent photographic texture on the meat and bun.
- + Clean and professional typography layout.
- − Failed the 'exploded burger' prompt by keeping the burger mostly assembled.
- − Included redundant neon text that wasn't requested in the prompt.
Wan 2.5 (Preview)
- + Perfectly captures the 'exploded' concept with suspended components.
- + Includes the fiery starburst for the price as requested.
- + Creative fiery, glowing effect on the main title text.
- − Lower resolution and more digital-looking artifacts compared to Model A.
- − Some physics oddities in how the sauce droplets are rendered.
Verdict: Wan 2.5 (Preview) adhered much better to the specific layout instructions, successfully rendering an exploded burger and the fiery starburst for the price. While FLUX1.1 [pro] produced a higher-quality photographic image, it failed to separate the burger components as requested and ignored the starburst instruction.
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
FLUX1.1 [pro]
- + Excellent handwritten texture with varied letter weights
- + Highly legible text with very few spelling errors
- + Accurately renders the complex phrase 'gluten free options'
- − Splits one menu item into two separate lines with incorrect pricing ($228 and $98)
- − Hallucinates words like 'Chipkies' and 'Herbss'
- − The text looks slightly too clean and digital compared to the requested chalk texture
Wan 2.5 (Preview)
- + Superb realism with chalk smudges and dusty texture on the board
- + Captures the 'handwritten' request perfectly with realistic slant and pressure variations
- + Correctly handles the pricing as requested ($24, $28, $9)
- − Slight repetition in the 'Cookies' line which was not requested
- − Text rendering on the bottom line is slightly less clear than the main headers
Verdict: Wan 2.5 (Preview) produced a far more realistic chalkboard with authentic smudge textures and a consistent handwritten style. While FLUX1.1 [pro] had very clear text, it struggled with the content of the menu items, hallucinating incorrect prices and splitting lines incorrectly. Wan 2.5 (Preview) is the winner for its superior adherence to the requested aesthetic and more accurate data rendering.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
AI Judge Analysis
FLUX1.1 [pro]
- + Excellent texture on the astronaut suit and horse's mane.
- + Creative surrealist concept with the horse having armor-like markings.
- − The horse's hind legs have anatomical irregularities.
- − The lighting on the horse's back seems disconnected from the main light source.
Wan 2.5 (Preview)
- + Strong composition with clear astronomical elements like the galaxy and Earth.
- + Naturalistic horse anatomy and dynamic action pose.
- − The astronaut's feet are positioned awkwardly above the stirrups.
- − Slightly less 'surreal' than requested, appearing more like a standard composite.
Verdict: Both models failed the specific logic check of placing the horse on top of the astronaut, instead defaulting to the common trope of an astronaut riding a horse. FLUX1.1 [pro] offers a more painterly and surreal atmosphere, while Wan 2.5 (Preview) provides a cleaner, more vibrant space-themed composition with better horse anatomy.
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
FLUX1.1 [pro]
- + Excellent photographic lighting and cinematic atmosphere.
- + Correct capybara fur texture and professional attire.
- − The passenger is seated in the front or a confusing mid-car position.
- − The steering wheel and driving stance are largely obscured.
Wan 2.5 (Preview)
- + Accurately depicts both paws on the steering wheel.
- + Cleverly places the passenger in the back seat as requested.
- − The capybara's paws have unnatural claw-like fingers.
- − The composition feels slightly cluttered around the dashboard area.
Verdict: Wan 2.5 (Preview) followed the prompt instructions more closely by placing the passenger in the back seat and showing both paws on the wheel. While FLUX1.1 [pro] has superior lighting and aesthetic realism, its spatial logic is flawed as the passenger appears to be in the front seat next to the driver.
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
FLUX1.1 [pro]
- + Features a beautifully spooky and centered jack-o-lantern illustration.
- + The thorn border is integrated well with the tattered parchment edges.
- + Captures a very moody, dark atmospheric night sky.
- − Significant text errors including redundant text and typos like 'You inivited to a n night'.
- − Failed the square format requirement by generating a vertical poster on a grey background.
Wan 2.5 (Preview)
- + Perfect text rendering for all requested fields with zero spelling errors.
- + Strictly followed the square format and included all prompt elements like cobwebs and thorns.
- + High-quality, polished 3D effects on the gothic title text.
- − The composition feels a bit crowded with the large jack-o-lantern and title overlapping the sky circle.
- − The 'night of frights' banner is slightly warped on the left side.
Verdict: Wan 2.5 (Preview) provided a superior design by following the square format constraint and rendering all text accurately and legibly. FLUX1.1 [pro] produced a more atmospheric illustration but failed significantly on text coherence, including multiple typos and redundant lines of information.
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
FLUX1.1 [pro]
- + Excellent adherence to the isometric miniature 3D cartoon style
- + Superior soft refined textures that look like high-quality clay renders
- + Very clean and aesthetic layout of the sushi variety on the diorama base
- − Failed to include the requested flag icon
- − The 'SUSHI' text is somewhat small and lacks the 'large bold' presence of the top text
Wan 2.5 (Preview)
- + Perfectly followed the flag icon instruction
- + Clearer text rendering with better hierarchy
- + Nice subsurface scattering effects on the sushi grain
- − The perspective is a standard eye-level/slight-down angle rather than the requested 45° isometric top-down
- − Focuses on only a single piece of sushi rather than a full scene or variety
- − The background has a gradient rather than being a solid color
Verdict: While Wan 2.5 (Preview) followed the specific text and icon instructions more accurately, it failed to produce the requested 45° isometric perspective. FLUX1.1 [pro] captured the intended isometric miniature diorama aesthetic perfectly, resulting in a much more balanced and visually appealing composition despite the missing flag.
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
FLUX1.1 [pro]
- + Excellent soft lighting and bokeh effect
- + High-quality fur texture rendering
- − Missed prompt requirement for a red fox kit
- − Only includes three animals instead of the requested four
- − Static composition lacks the 'chasing' and 'tumbling' action requested
Wan 2.5 (Preview)
- + Successfully included all four requested animals: puppy, kitten, bunny, and fox
- + Captured the movement of chasing and tumbling well
- + Included specific details like god rays and dew sparkles
- − The fox kit has unnaturally bright, glowing blue eyes
- − Anatomy on the kitten's front leg looks slightly distorted
- − Some dew drops appear to be floating in mid-air rather than on plants
Verdict: Wan 2.5 (Preview) adhered much better to the complex prompt by including all four specific animals and capturing the requested action of them chasing butterflies. While FLUX1.1 [pro] has a more polished and artistically soft aesthetic, it failed on several key prompt elements, including the red fox and the count of animals.
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
FLUX1.1 [pro]
- + Ornate and sophisticated design details
- + Professional vector-style illustration
- + Good use of rays and filigree to enhance the logo feel
- − Typos in the main text ('FRANILIAN' instead of 'FLORIAN')
- − Interpreted 'cloche dome' as more of an architectural dome
Wan 2.5 (Preview)
- + Perfect text rendering for both name and date
- + Accurate depiction of a food service cloche dome
- + Excellent texture and border detailing on the background
- − Vector lines on the banner are slightly inconsistent in thickness
- − Steam icon is a bit generic
Verdict: Wan 2.5 (Preview) is the winner because it successfully followed the text requirements, including the correct spelling of 'Caffè Florian'. While FLUX1.1 [pro] produced a beautiful, more complex illustration, it failed to spell the primary brand name correctly and misinterpreted the cloche dome as a building dome.
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
FLUX1.1 [pro]
- + Follows the list of 6 steps more comprehensively than the competitor.
- + Uses a consistent, cohesive flat-vector style across all elements.
- + Maintains the requested NASA-inspired color palette effectively.
- − Severe text hallucinations and spelling errors throughout the infographic.
- − The central rocket is a generic cartoon design rather than a Saturn V.
- − The numbering sequence is disorganized and repetitive (e.g., two step 6s).
Wan 2.5 (Preview)
- + Excellent text rendering and legibility for the main headers.
- + Accurately depicts the Saturn V rocket and the Lunar Module designs.
- + The layout for the orbital trajectories is logical and visually clear.
- − Fails to explicitly label or detail steps 4, 5, and 6 as separate entities.
- − The astronaut portraits are somewhat crude and inconsistent with the flat-vector style.
- − Includes a Space Shuttle-style orbiter which is historically inaccurate for the Apollo missions.
Verdict: FLUX1.1 [pro] better captures the aesthetic of a multi-step infographic and provides more supporting icons, but suffers from significant text and numbering errors. Wan 2.5 (Preview) produces much cleaner text and more accurate hardware silhouettes (Saturn V and LEM), though it missed some of the requested steps in the sequence. Wan 2.5 (Preview) is the preferred choice for a real-world application due to its legibility and professional composition.
Explore each model
Alibaba's text-to-image and image-to-image generation model from the Wan AI suite, offering high-quality visual generation capabilities