Head to head
Esc

Models · slot A

to navigate to pick

FLUX1.1 [pro] Ultra Black Forest Labs Wan 2.5 (Preview) Alibaba

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

FLUX1.1 [pro] Ultra

17.9 arena score

#51 of 62 in Text-to-Image

Skill signature · Text-to-Image

Wan 2.5 (Preview)

23.4 arena score

#27 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX1.1 [pro] Ultra

0%

win rate

Ties

0%

Wan 2.5 (Preview)

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.”

FLUX1.1 [pro] Ultra
Wan 2.5 (Preview)

AI Judge Analysis

FLUX1.1 [pro] Ultra

  • + Excellent refraction and reflection physics on the glass surfaces.
  • + Highly realistic textures on the red book cover and the wooden table.
  • + Clean, professional photographic composition with accurate lighting.
  • The blue sphere is levitating rather than sitting on a surface, which might look physically unnatural.
  • The plant is very close to the cube, making the 'behind' instruction feel a bit crowded.

Wan 2.5 (Preview)

  • + Strong adherence to the spatial relationship of the sphere sitting on the base.
  • + Captures the 'soft window light' very effectively with beautiful shadows and dust motes.
  • + Nice weathered texture on the edges of the book.
  • The sphere has multiple reflections that don't align perfectly with its position.
  • The glass edges appear slightly inconsistent in thickness compared to Model A.

Verdict: Both models followed the prompt instructions perfectly, including all requested objects and their spatial relationships. FLUX1.1 [pro] Ultra is the winner due to its superior rendering of glass and lighting physics, whereas Wan 2.5 (Preview) has slightly messy reflections inside the cube, even though it handled the 'sitting' position of the sphere more naturally.

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.”

FLUX1.1 [pro] Ultra
Wan 2.5 (Preview)

AI Judge Analysis

FLUX1.1 [pro] Ultra

  • + Excellent execution of long-exposure motion blur on the passing vehicle
  • + Very high resolution and clarity on the subject
  • + Natural and realistic pavement reflections
  • The man appears to be standing over the bike rather than actively repairing it
  • Composition feels slightly staged compared to image B

Wan 2.5 (Preview)

  • + Stronger narrative adherence with the man actively crouching and using tools to repair the bike
  • + Excellent natural skin texture and facial details
  • + Better captures the 'imperfect framing' and 'candid' feel requested
  • Failed to include the requested motion blur from passing cars
  • The rain texture looks a bit vertical and synthetic compared to the environment

Verdict: While FLUX1.1 [pro] Ultra produced a technically superior image with impressive motion blur and clean reflections, it missed the core action of 'repairing' the bike. Wan 2.5 (Preview) captured a much more authentic, candid moment with active repair work and excellent character detail, though it failed the motion blur requirement.

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.”

FLUX1.1 [pro] Ultra
Wan 2.5 (Preview)

AI Judge Analysis

FLUX1.1 [pro] Ultra

  • The image is completely black and failed to render.

Wan 2.5 (Preview)

  • + Excellent adherence to all prompt details including braided hair with beads, scars, and dirt.
  • + Highly detailed textures on the ornate engraving, leather straps, and frayed cloth.
  • + Strong cinematic atmosphere with realistic lighting and warm bokeh.
  • The 'bokeh sparks' requested look more like static blurred light orbs than dynamic sparks.

Verdict: FLUX1.1 [pro] Ultra failed to generate a visible image, resulting in a black frame. Wan 2.5 (Preview) provided a high-quality, detailed interpretation of the prompt, capturing the battle-worn aesthetic and complex textures of the paladin's gear perfectly.

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.”

FLUX1.1 [pro] Ultra
Wan 2.5 (Preview)

AI Judge Analysis

FLUX1.1 [pro] Ultra

  • + Excellent presentation of the menu as a professional physical mockup
  • + Very realistic and appetizing food photography for casual dining
  • + Clean, high-quality typography and balanced white space
  • Several spelling errors like 'Pizzzans' and 'Appet Love'
  • The layout is a bit scattered and less organized than a standard grid

Wan 2.5 (Preview)

  • + Strict adherence to the requested grid layout
  • + Clear logical separation of categories using colored lines
  • + Good balance of text blocks alongside images
  • Text is highly garbled and includes many gibberish words
  • Food photography is slightly repetitive with similar basil garnishes on almost every dish
  • The flat design feel is less professional than Model A's mockup

Verdict: FLUX1.1 [pro] Ultra produces a much more professional and realistic asset by presenting the menu as a physical mockup with high-quality photography, despite some spelling errors. Wan 2.5 follows the 'grid' instruction more literally but suffers from lower texture quality and more significant text artifacts. FLUX1.1 overall feels like a more complete design suitable for casual dining.

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.”

FLUX1.1 [pro] Ultra
Wan 2.5 (Preview)

AI Judge Analysis

FLUX1.1 [pro] Ultra

  • + Excellent typography with clean, legible font rendering
  • + High-quality, appetizing burger textures and details
  • + Good use of embers and fire to create a dark atmospheric background
  • Missed the 'starburst' request for the price tag
  • The burger is more of a 'tall stack' than a truly 'exploded' view where components are separated in all directions
  • Some small illegible AI-generated text artifacts at the very bottom

Wan 2.5 (Preview)

  • + Perfectly captures the 'exploded' concept with dynamic, floating ingredient placement
  • + Correctly included the fiery starburst for the price as requested
  • + Creative use of melting/dripping effects on the main title text
  • The 'LIMITED TIME ONLY' text is smaller and slightly harder to read due to spacing
  • Visual style is slightly more illustrative/CG than strictly photorealistic

Verdict: Wan 2.5 (Preview) produced a more dynamic and accurate interpretation of the prompt, successfully including the 'exploded' layout and the starburst element that FLUX1.1 [pro] Ultra missed. While FLUX1.1 [pro] Ultra has slightly higher realism in its textures, Wan 2.5 (Preview) is the better advertisement due to its superior composition and creative adherence to specific details.

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.”

FLUX1.1 [pro] Ultra
Wan 2.5 (Preview)

AI Judge Analysis

FLUX1.1 [pro] Ultra

  • + Excellent realistic chalk texture with dusty smudges
  • + Consistent thin handwriting style across the board
  • + Accurate date and pricing formatting
  • Numerous spelling and repetition errors like 'mushroomm' and 'fresh fresh'
  • Illegible gibberish text in the second line of the first item
  • Failed to use elegant cursive for the title

Wan 2.5 (Preview)

  • + Perfect text rendering with no spelling errors
  • + Beautiful slanted chalk handwriting that feels authentic
  • + Stronger composition with realistic chalk dust and eraser marks
  • Omitted 'Herbs' from the second menu item
  • Line spacing is slightly crowded at the bottom

Verdict: While FLUX1.1 [pro] Ultra captures the gritty texture of real chalk more accurately, it suffers from significant spelling errors and repetitive text. Wan 2.5 (Preview) provides a much more coherent and professional-looking menu with legible, error-free text and a more pleasing aesthetic overall.

The Reversed Rodeo

Text-to-Image

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

FLUX1.1 [pro] Ultra
Wan 2.5 (Preview)

AI Judge Analysis

FLUX1.1 [pro] Ultra

  • + Excellent visual clarity and high-resolution details on the horse's mane and the planet below.
  • + Cinematic composition with a very clear, wide-angle orbital perspective.
  • + Clean rendering of the astronaut suit and background satellites.
  • Failed the negative constraint: the astronaut is riding the horse, not the requested 'horse on top'.

Wan 2.5 (Preview)

  • + Dynamic sense of movement with the gallop pose and nebula lighting.
  • + Intricate detail on the astronaut's gloves and suit controls.
  • + Vibrant color palette with the purple galaxy background.
  • Failed the negative constraint: the astronaut is riding the horse, not the requested 'horse on top'.
  • Lighting on the horse is slightly inconsistent with the space environment.

Verdict: Both models failed the difficult negative constraint to place the horse on top of the astronaut, providing a standard 'astronaut on horse' interpretation instead. FLUX1.1 [pro] Ultra is preferred for its superior image quality, cleaner details, and more realistic orbital composition compared to Wan 2.5 (Preview).

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.”

FLUX1.1 [pro] Ultra
Wan 2.5 (Preview)

AI Judge Analysis

FLUX1.1 [pro] Ultra

  • + Excellent texture on the capybara's fur.
  • + Consistent lighting between the interior and the street lights.
  • Major logic failure placing the businesswoman in the front passenger seat instead of the back.
  • The capybara's body is awkwardly merged into the door frame.

Wan 2.5 (Preview)

  • + Perfect adherence to the spatial requirements, placing the woman in the back seat.
  • + Accurately depicts the capybara's paws on the steering wheel as requested.
  • + Captures the 'bored' expression of the passenger very effectively.
  • The text on the taxi roof sign is nonsensical (gibberish).
  • The capybara's head shape is slightly narrower than a typical capybara, resembling a groundhog.

Verdict: Wan 2.5 (Preview) followed the complex spatial instructions perfectly, correctly placing the businesswoman in the back seat and the capybara at the wheel. FLUX1.1 [pro] Ultra failed the primary composition by placing the passenger in the front seat, although it had slightly higher resolution for the textures of the capybara's fur.

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.”

FLUX1.1 [pro] Ultra
Wan 2.5 (Preview)

AI Judge Analysis

FLUX1.1 [pro] Ultra

  • + Excellent typography style that matches the gothic theme
  • + Very detailed frame made of thorns and branches
  • + Clean layout and high resolution
  • Included redundant and misspelled text under the banner
  • Missed the word 'Party' in the main title
  • The jack-o-lantern is a bit small relative to the page

Wan 2.5 (Preview)

  • + Perfect text accuracy including all requested words and details
  • + Highly detailed jack-o-lantern with realistic fire effects
  • + Better use of the border elements like spiderwebs and thorns
  • The font choice for the main title is slightly more playful than vintage gothic
  • The composition feels a bit tight at the edges

Verdict: Wan 2.5 (Preview) produced a superior result by correctly including all requested text, whereas FLUX1.1 [pro] Ultra missed a word in the title and generated gibberish repeat text below the banner. Wan 2.5 also delivered a more visually striking jack-o-lantern and better adhered to the atmospheric night sky and spiderweb requirements.

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.”

FLUX1.1 [pro] Ultra
Wan 2.5 (Preview)

AI Judge Analysis

FLUX1.1 [pro] Ultra

  • + Excellent adherence to the 'isometric' and 'diorama base' instructions
  • + High level of detail in the miniature scene including varied sushi types and props
  • + Clever integration of the text and flag into the background space
  • The text 'JAPAN' is slightly stylized which might not fit 'bold' as strictly as a sans-serif block
  • Includes a strange bug/insect detail on the board that wasn't requested

Wan 2.5 (Preview)

  • + Very clean and bold text rendering with a clear flag icon
  • + High quality 3D rendering with soft, appealing textures
  • + Good centering of the main object
  • Fails to create a 'diorama base', opting for a simple circular stand
  • Not a true 45° isometric perspective, feels more like a standard 3D character render
  • Lacks the 'miniature scene' complexity requested in the prompt

Verdict: FLUX1.1 [pro] Ultra followed the complex scene instructions much better, providing a full isometric diorama with multiple elements as requested. While Wan 2.5 (Preview) produced a very clean and attractive single object render with excellent text, it failed to capture the 'isometric miniature scene' aspect of the prompt.

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.”

FLUX1.1 [pro] Ultra
Wan 2.5 (Preview)

AI Judge Analysis

FLUX1.1 [pro] Ultra

  • + Excellent soft lighting and consistent artistic style
  • + Deep, cohesive field of depth in the meadow
  • + All four animals are clearly present and share a visually harmonious look
  • Stylized 'disney-fied' appearance rather than 'hyper-photorealistic'
  • The animals appear somewhat static and sitting rather than tumbling or chasing

Wan 2.5 (Preview)

  • + Captures the action of 'tumbling' and 'chasing' much more effectively
  • + Includes specific lighting details like god rays and large dew sparkles
  • + Realistic textures on the fox and kitten
  • The fox's eyes have unnatural, jagged pupils
  • The puppy's front paw is anatomically distorted
  • Floating water droplets look a bit like digital artifacts rather than natural dew

Verdict: Wan 2.5 (Preview) followed the prompt's action requirements more closely, depicting the animals in motion with clear god rays, though it suffered from anatomical glitches and strange eye artifacts. FLUX1.1 [pro] Ultra produced a much more polished and aesthetically pleasing 8K image, but it interpreted the scene as a static, stylized portrait rather than a photorealistic action shot.

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.”

FLUX1.1 [pro] Ultra
Wan 2.5 (Preview)

AI Judge Analysis

FLUX1.1 [pro] Ultra

  • + Excellent vector emblem style with balanced composition
  • + High-quality professional typography
  • + Great use of brown and cream tones
  • Spelling error in the main brand name ('Framlian' instead of 'Florian')
  • The 'Est. 1720' is not inside a banner as requested

Wan 2.5 (Preview)

  • + Perfect text rendering for both 'Caffè Florian' and 'Est. 1720'
  • + Matches the 'minimalist' instruction better than the alternative
  • + Successful implementation of the banner with correct text placement
  • The steam element is slightly less sophisticated in design
  • The cloche is a bit more generic than the detailed version in the other image

Verdict: While FLUX1.1 [pro] Ultra produces a more visually striking and complex emblem, it fails on the basic requirement of spelling the requested name correctly. Wan 2.5 (Preview) produces a cleaner, more minimalist logo that accurately follows all text instructions and banner placement.

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.”

FLUX1.1 [pro] Ultra
Wan 2.5 (Preview)

AI Judge Analysis

FLUX1.1 [pro] Ultra

  • + Excellent vector illustration style that feels modern and cohesive.
  • + Follows the requested color palette perfectly with subtle gradients.
  • + Successful layout of a curved horizon that provides a sense of scale.
  • The text is nonsensical gibberish instead of actual English.
  • The numbering and logical flow of the mission steps are confusing and incorrect.

Wan 2.5 (Preview)

  • + Features actual legible text and correctly identifies the mission crew.
  • + Logical flow of steps with clear visual connections between earth and moon.
  • + Saturn V rocket illustration is very accurate and detailed for a flat style.
  • Iconography is slightly inconsistent, with the large moon at the top looking more realistic than vector.
  • The composition is a bit crowded, especially the labels for descent and landing.

Verdict: Wan 2.5 (Preview) provided a much more functional infographic with readable text and accurate mission details, even if the flat-vector style is slightly less refined. FLUX1.1 [pro] Ultra has superior artistic style and composition, but fails completely as an infographic due to the text being unreadable gibberish and the icons lacking logical order.

Next steps

Explore each model