Head to head
Esc

Models · slot A

to navigate to pick

FLUX.1 [dev] Black Forest Labs Wan 2.5 (Preview) Alibaba

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

FLUX.1 [dev]

24.6 arena score

#16 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

FLUX.1 [dev]

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.”

FLUX.1 [dev]
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent photorealism with clean glass reflections
  • + Precisely follows the spatial relationship of the book sitting on the cube
  • + Elegant soft lighting consistent with a window source
  • The glass structure is more of a hollow frame than a solid cube
  • The blue sphere appears to be floating rather than sitting

Wan 2.5 (Preview)

  • + Natural textures on the book and wooden table
  • + Accurate depiction of a solid glass cube with realistic refraction
  • + Atmospheric lighting with visible dust motes
  • The plant is more 'next to' the cube than 'behind' it
  • The book seems slightly disconnected from the glass surface

Verdict: Both models followed the prompt instructions accurately, but FLUX.1 [dev] produced a more polished, high-end aesthetic with cleaner lines. Wan 2.5 (Preview) excelled in texture rendering and realistic light refraction through the solid glass, though the composition felt slightly less balanced than FLUX.1 [dev].

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.”

FLUX.1 [dev]
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent depiction of motion blur on the passing vehicle
  • + Natural skin textures and realistic lighting on the clothing
  • + Good adherence to the 50mm lens and shallow depth of field request
  • The subject is standing and holding the bike rather than actively repairing it
  • The framing feels a bit too clean and centered despite the 'imperfect framing' prompt

Wan 2.5 (Preview)

  • + Stronger adherence to the 'repairing' action with tools on the ground
  • + Excellent reflections on the wet pavement
  • + More authentic 'imperfect' street photography composition
  • The bike's kickstand and spokes have minor anatomical/geometric inconsistencies
  • Lacks the requested motion blur on passing vehicles

Verdict: FLUX.1 [dev] excels in photographic realism and accurately capturing motion blur, but the subject is simply holding the bike. Wan 2.5 (Preview) provides a better narrative by showing the man actually repairing the bike with tools, though it misses the motion blur requirement. FLUX.1 [dev] is the winner due to superior technical execution and skin texture realism.

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.”

FLUX.1 [dev]
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent photographic skin texture and lifelike eyes
  • + Beautiful lighting and bokeh effects
  • Failed to include the beads in the braids
  • The character looks too clean and manicured for 'battle-worn'
  • Missing the high-detail leather and cloth underlayer requested

Wan 2.5 (Preview)

  • + Accurately followed all prompt instructions including hair beads and leather straps
  • + Succesfully captured the 'battle-worn' aesthetic with dirt and scars
  • + Extremely detailed engraving on the armor and texture on the cloth layers
  • The bokeh circles in the background are slightly distorted
  • Facial symmetry is slightly less polished than Model A

Verdict: Wan 2.5 (Preview) is the clear winner for its superior prompt adherence, successfully incorporating specific details like the hair beads, scarred skin, and multi-layered clothing that FLUX.1 [dev] omitted. While FLUX.1 [dev] produced a very pretty portrait, it failed to capture the 'battle-worn' gritty essence requested by the prompt.

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.”

FLUX.1 [dev]
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent typographic hierarchy and legibility
  • + Clean, professional layout that closely resembles a real-world document
  • + High-quality, realistic food photography integrated into corners
  • Missed the 'grid' requirement for photos
  • Missing a dedicated 'Pizza' section heading in the layout

Wan 2.5 (Preview)

  • + Strong adherence to the 'food photos in grid' prompt requirement
  • + Includes all three requested sections: Appetizers, Pizza, and Mains
  • + Vibrant colors and high-contrast accents
  • Text is largely illegible gibberish
  • The layout feels cramped with little white space for a 'minimalist' design
  • Text rendering is inconsistent with several font weights and styles clashing

Verdict: FLUX.1 [dev] produces a much more professional and realistic menu design with superior typography and a polished minimalist aesthetic, though it misses the specific 'grid' layout for photos. Wan 2.5 (Preview) follows the structural prompts more closely by including a grid and all three sections, but the actual text rendering is poor and the overall design feels more like a template preview than a finished product. FLUX.1 [dev] is the preferred choice for its high visual quality and design coherence.

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.”

FLUX.1 [dev]
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent photorealistic texture on the meat patties and bun
  • + Clean, minimalist composition suitable for a high-end food ad
  • Missed the primary 'MAGIC BURGER' text title entirely
  • Failed to include the requested starburst for the price
  • The 'exploded' effect is a rigid vertical stack rather than a dynamic, mid-air suspension

Wan 2.5 (Preview)

  • + Perfect adherence to all text requirements including 'MAGIC BURGER' and 'LIMITED TIME ONLY'
  • + Highly dynamic 'exploded' composition with ingredients tilting and flying outward
  • + Accurately rendered the fiery starburst effect for the price as requested
  • The 'MAGIC BURGER' font has a melting cheesy effect that wasn't specifically requested but fits the theme
  • Slightly more 'digital art' feel compared to the raw realism of the competing image

Verdict: Wan 2.5 (Preview) followed the prompt instructions much more comprehensively, including all requested text elements and the specific 'starburst' pricing layout. FLUX.1 [dev] produced a high-quality image but failed on major prompt requirements like the main title and the dynamic motion of the ingredients.

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.”

FLUX.1 [dev]
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent text legibility and accuracy
  • + Centered and balanced layout
  • + Great wood texture on the frame
  • Text looks slightly too uniform and clean for real chalk
  • Includes some slight spelling errors in footer text ('drish', 'aur')

Wan 2.5 (Preview)

  • + Very realistic chalk texture with smudges and dust
  • + Authentic slanted handwriting style
  • + Excellent dynamic composition
  • Missing 'Herbs' from the second menu item
  • Redundant pricing ($28 for octopus looks like part of the name, and $9 repeats)

Verdict: FLUX.1 [dev] produced a much clearer and more legible board with fewer logical errors in the menu listings, though some footer text had minor spelling issues. Wan 2.5 (Preview) captured the realistic 'chalk' aesthetic much better with dust and smudges, but it failed to follow the text prompt accurately, omitting words and repeating price symbols awkwardly.

The Reversed Rodeo

Text-to-Image

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

FLUX.1 [dev]
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent lighting and cinematic color grading.
  • + Anatomically coherent horse and rider integration.
  • + High-quality textures on the space suit and horse mane.
  • Failed the specific spatial instruction for the horse to be on top of the astronaut.

Wan 2.5 (Preview)

  • + Very detailed background with nebulae and planetary elements.
  • + Sharp rendering of the astronaut's gear and reflective visor.
  • + Good sense of motion and action.
  • Failed the specific spatial instruction for the horse to be on top of the astronaut.
  • Minor anatomical issues with the horse's front legs.

Verdict: Both models failed to follow the trick instruction to place the horse on top of the astronaut, instead defaulting to the standard 'astronaut riding horse' configuration. FLUX.1 [dev] is the slightly better image due to its more realistic lighting, cleaner silhouettes, and lack of the anatomical distortion present in Wan 2.5 (Preview)'s horse.

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.”

FLUX.1 [dev]
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent photographic quality and depth of field
  • + Natural lighting interation on the capybara's fur
  • + Accurate depiction of a modern smartphone and hands
  • The woman appears to be in the passenger seat rather than the back seat
  • The capybara's paws are not placed logically on the steering wheel

Wan 2.5 (Preview)

  • + Correctly places the passenger in the back seat as requested
  • + Excellent capybara anatomy with paws realistically gripping the wheel
  • + High detail in the taxi interior and exterior rain effects
  • The passenger's face is slightly blurry and less detailed
  • The text on the taxi roof light is gibberish

Verdict: Wan 2.5 (Preview) followed the compositional instructions much better by placing the woman in the back seat and showing the capybara professionally steering, whereas FLUX.1 [dev] placed the woman in the front passenger seat. Wan 2.5 also provided a more convincing 'professional' uniform for the capybara, although FLUX.1 had superior lighting and skin texture for the human subject.

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.”

FLUX.1 [dev]
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.1 [dev]

  • + Strong thorns-only border framing the layout
  • + Excellent high-contrast cinematic lighting
  • Significant text errors including 'Falloween Rancy' and duplicated time values
  • Failed to include webs in the border as requested

Wan 2.5 (Preview)

  • + Perfect text rendering for all requested fields including specific dates and slogans
  • + Includes both webs and thorns in the border with a high-quality parchment texture
  • + Strong adherence to the moody night sky and twisted tree elements
  • The 'Halloween Party Invitation' title is slightly cramped against the top edge
  • The jack-o-lantern's fire effects are a bit busy compared to the rest of the image

Verdict: Wan 2.5 (Preview) significantly outperforms FLUX.1 [dev] by following all complex text instructions perfectly without any typos. While FLUX.1 [dev] has a nice graphic style, its failure to render the title correctly and the omission of webs in the border makes it less successful as a complete invitation design.

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.”

FLUX.1 [dev]
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent isometric miniature/diorama aesthetic.
  • + Captured the requested light blue background perfectly.
  • + High-quality 3D clay-like textures.
  • Text rendering is poor with 'SUSH CATON' and extra symbols.
  • Small flag icon is somewhat distorted.
  • Lighting is a bit flat compared to the other model.

Wan 2.5 (Preview)

  • + Perfect text rendering for 'JAPAN' and 'SUSHI'.
  • + Outstanding material quality with realistic PBR-style highlights.
  • + Composition is bold and visually striking.
  • Perspective is more eye-level than the requested 45° top-down isometric view.
  • Text placement is very large, dominating the scene rather than being a label.
  • Simple circular base is less like a 'diorama' than Model A.

Verdict: Wan 2.5 (Preview) produced a higher quality image with perfect text and superior PBR materials, though it missed the specific isometric 45-degree angle requested. FLUX.1 [dev] followed the perspective and diorama layout more closely but failed significantly on the text and clarity of the flag icon. Overall, Wan 2.5 is preferred for its professional rendering and accurate adherence to the primary text elements.

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.”

FLUX.1 [dev]
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.1 [dev]

  • + Warm and appealing lighting with nice bokeh
  • + Simple and clean composition
  • Failed to include a tabby kitten or a clearly distinct fox kit, rendering all animals as generic puppy/bunny hybrids
  • Stylized/illustrative look rather than the requested hyper-photorealistic style
  • Anatomically confused paws and ears on several creatures

Wan 2.5 (Preview)

  • + Excellent adherence to the specific animals requested, including a distinct tabby kitten and red fox kit
  • + High level of photographic detail in fur textures and environment
  • + Dynamic poses that accurately reflect the 'playfully chasing' and 'tumbling' prompt
  • The fox's eyes appear slightly uncanny with unnatural blue glows
  • Dew drops are rendered too large, appearing like floating glass droplets

Verdict: Wan 2.5 (Preview) significantly outperformed FLUX.1 [dev] by correctly identifying and rendering all four specific baby animals requested, whereas FLUX.1 [dev] produced generic creatures. Wan 2.5 (Preview) also better captured the 'hyper-photorealistic' and 'god rays' aspect of the prompt, creating a much more dynamic and detailed 8K scene.

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.”

FLUX.1 [dev]
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.1 [dev]

  • + Strong minimalist aesthetic with a clean vector feel.
  • + Accurate inclusion of the 'Est. 1720' text.
  • Misspelled the main brand name as 'Cafè Flarilaan'.
  • Misspelled 'Restaurant' in the banner.
  • Added unnecessary floating numbers like '11011' and '1941'.

Wan 2.5 (Preview)

  • + Perfectly spelled the brand name 'Caffè Florian'.
  • + Beautiful implementation of the paper texture and vintage border.
  • + Clearer, more balanced composition of the cloche and banner.
  • Text is slightly off-center within the banner.
  • The steam vector is a bit thick compared to the rest of the fine lines.

Verdict: Wan 2.5 (Preview) produced a superior logo by accurately spelling 'Caffè Florian' and adhering closely to the vintage aesthetic with a textured paper background. FLUX.1 [dev] failed significantly on text rendering, hallucinating extra numbers and misspelling the primary brand name.

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.”

FLUX.1 [dev]
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent vector aesthetic with a cohesive professional layout.
  • + Strong adherence to the requested color palette.
  • Text consists of garbled, illegible characters.
  • Includes nonsensical planets like Saturn and a red sphere that don't belong in the Earth-Moon system.
  • The logical flow of the infographic is confusing and non-linear.

Wan 2.5 (Preview)

  • + High level of prompt adherence with clear, legible text.
  • + Accurately represents the mission phases (Earth, Moon, Saturn V, Lunar Module).
  • + Includes creative and accurate supporting details like the astronaut names and Tranquility Base marker.
  • The 'Descent' and 'Landing' text labels are floating without specific icons attached.
  • Layout is slightly more cluttered compared to the minimalist goal of Model A.

Verdict: Wan 2.5 (Preview) is the superior choice because it successfully integrates the requested technical data and text labels into a coherent narrative, whereas FLUX.1 [dev] produces gibberish text and inaccurate planetary icons. While FLUX.1 [dev] has a slightly more sophisticated graphic design style, Wan 2.5 (Preview) provides a functional infographic that actually communicates the Apollo 11 mission steps.

Next steps

Explore each model