Head to head
Esc

Models · slot A

to navigate to pick

FLUX.1 [dev] Black Forest Labs Wan 2.7 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 2.7

20.5 arena score

#39 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.1 [dev]

0.0%

win rate

Ties

0.0%

Wan 2.7

100.0%

win rate

0.0% 0.0% ties 100.0%
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 2.7

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent refractive and reflective details in the glass cube.
  • + Modern, clean aesthetic with high-quality soft lighting.
  • + Precise object placement and crisp textures.
  • The cube geometry is slightly stylized with heavy internal bevels/frames.
  • The blue sphere appears to be floating rather than resting.

Wan 2.7

  • + Highly realistic textures, especially the vintage book and weathered wood table.
  • + Accurately places the plant behind the glass with realistic distortion.
  • + Naturalistic adherence to the scale of the requested objects.
  • The glass cube has some internal structural inconsistencies where reflections meet joints.
  • The blue sphere has a slightly rough, opaque texture compared to the expected 'perfect' sphere.

Verdict: Both models followed the prompt perfectly. FLUX.1 [dev] produced a cleaner, more artistic image with superior lighting and glass refraction, while Wan 2.7 delivered a more grounded, photorealistic result with exceptional material textures. FLUX.1 [dev] is the likely winner for its more cohesive and aesthetically pleasing composition.

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 2.7

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent bokeh and shallow depth of field as requested
  • + Detailed clothing textures and high cinematic quality
  • + Captures the light rain effect and car light reflections effectively
  • The man is holding the handlebars rather than repairing the bike
  • The background car lacks the requested motion blur effect
  • The bike design looks a bit modern for the intended candid style

Wan 2.7

  • + Successfully captures a truly 'candid' street photography aesthetic
  • + The bike style and man's clothing feel very authentic to a Japanese street scene
  • + Composition feels more 'imperfect' and natural as requested
  • Failed to include motion blur on the passing cars
  • Lower resolution/clarity compared to Model A
  • Depth of field is much deeper than the requested 50mm shallow look

Verdict: FLUX.1 [dev] produced a much more cinematic and high-quality image with the requested shallow depth of field, though it looks somewhat staged. Wan 2.7 nailed the authentic 'candid' and 'no stylization' feel of a Japanese street photo, but ignored technical prompt requirements like shallow depth of field and failed to provide the high resolution seen in the competitor. FLUX.1 [dev] is preferred for its technical adherence and superior visual clarity.

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 2.7

AI Judge Analysis

FLUX.1 [dev]

  • + Exceptional eye realism and skin texture
  • + Strong focus on the lighting and bokeh effect
  • + High photographic clarity
  • Missed the 'braids with small beads' requirement
  • Skin appears too clean and smooth for a 'battle-worn' character
  • Ornate engravings on the armor are very minimal

Wan 2.7

  • + Excellent adherence to the 'battle-worn' aesthetic with visible scars and dirt
  • + Accurately includes small beads in the braided hair
  • + Highly detailed engravings on the plate armor and textured leather straps
  • Lighting is a bit flat compared to the dramatic glow of Model A
  • The background bokeh is slightly less artistic

Verdict: Wan 2.7 followed every detail of the prompt, including the specific requests for beads, scars, and textured leather straps, creating a much more convincing 'battle-worn' character. FLUX.1 [dev] produced a visually striking image with superior eye detail, but failed to include several key descriptor tags like the beads or the grit expected of a paladin.

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 2.7

AI Judge Analysis

FLUX.1 [dev]

  • + Clean, professional minimalist aesthetic
  • + High quality rendering of food photos
  • + Excellent use of white space and modern typography
  • Text is mostly gibberish despite the professional look
  • Failed to include a specific 'Pizza' section header
  • Does not follow the grid layout for photos as requested

Wan 2.7

  • + Perfect adherence to the 'grid' layout for food photos
  • + Highly legible text with clear sections for Appetizers, Pizza, and Mains
  • + Includes requested branding elements like bold sans-serif fonts and vibrant accents
  • The composition is a bit cluttered compared to a true minimalist style
  • Slightly less realistic food rendering in some thumbnails (e.g., the burger and salad)

Verdict: Wan 2.7 followed every aspect of the prompt's structural requirements, including the grid of photos and the specific category headers. While FLUX.1 [dev] produced a more aesthetically pleasing 'minimalist' design, its failure to execute the grid layout and legible text makes Wan 2.7 the superior choice for a functional design task.

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 2.7

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent photorealistic texture on the meat and buns
  • + Clean vertical composition with a realistic fire effect at the base
  • Completely failed to include the primary text 'MAGIC BURGER'
  • Missing the starburst element for the price
  • The mid-air suspension feels static rather than dynamic

Wan 2.7

  • + Perfect adherence to all text requirements including 'MAGIC BURGER' and the starburst price
  • + Extremely dynamic 'exploded' composition with sauce splashes and flying ingredients
  • + Strong creative use of the fiery glowing effect on the typography
  • Lighting on the tomato and cucumber looks slightly more illustrative than photorealistic
  • The background is very busy with many competing glowing elements

Verdict: Wan 2.7 followed every instruction in the prompt, successfully integrating all three text elements with the requested fire effects and creating a truly dynamic exploded view. FLUX.1 [dev] produced a more realistic-looking burger but failed significantly on the text requirements, missing the main title and the starburst element entirely.

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 2.7

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent chalk texture showing realistic pressure and dust particles.
  • + Handwriting has natural slants and variations consistent with a human touch.
  • + Text is perfectly legible and correctly spelled.
  • The font style changes significantly between the header and the body, losing the requested 'same style' consistency.
  • The framing and lighting are a bit more generic compared to the competitor.

Wan 2.7

  • + Successfully maintained a very similar handwriting style throughout the entire board as requested.
  • + The environment lighting and depth of field create a very cozy atmosphere.
  • + Text renders with a nice drop-shadow effect that adds to the visual appeal.
  • The text looks a bit too perfect and consistent, resembling a digital font rather than raw chalk handwriting.
  • The 't' in 'Butter' is slightly malformed compared to other letters.

Verdict: FLUX.1 [dev] excels at the gritty, realistic texture of chalk on a board, making it look authentically handmade, though it fails to keep a consistent handwriting style across the whole menu. Wan 2.7 followed the prompt's instruction for style consistency much better and produced a more aesthetically pleasing café background, even if the text feels slightly more digital. Wan 2.7 is the likely winner for better overall prompt adherence and composition.

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 2.7

AI Judge Analysis

FLUX.1 [dev]

  • + Strong cinematic lighting with a soft glow from the planet below
  • + Dynamic, surreal pose for the horse including a floating aesthetic
  • Failed to follow the core instruction of 'horse on top'
  • Anatomical issues with the horse's back legs looking detached or deformed

Wan 2.7

  • + Crisp details on the space suit and celestial bodies
  • + Good composition with multiple galaxies and planets in the background
  • Failed to follow the core instruction of 'horse on top'
  • The lighting on the horse and astronaut is somewhat flat compared to the background

Verdict: Both FLUX.1 [dev] and Wan 2.7 failed the negative/inverse logic of the prompt, as both placed the astronaut on top of the horse rather than the requested 'horse on top'. FLUX.1 [dev] is slightly preferred for its superior cinematic lighting and more surreal atmosphere, whereas Wan 2.7 feels more like a standard digital composite.

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 2.7

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent soft lighting and high cinematic photorealism
  • + The capybara's expression and anatomy are well-rendered
  • + Atmospheric bokeh in the background captures the New York night feel well
  • The passenger appears to be in the front seat next to the driver rather than the back seat
  • The viewpoint from the hood of the car creates a slightly confusing composition for an 'inside' scene

Wan 2.7

  • + Successfully places the passenger in the back seat as requested
  • + Detailed clothing for both the capybara and the businesswoman
  • + The capybara's paws are correctly positioned on the wheel
  • The capybara's head has a strange, sharp cutout effect where it meets the neck and hat
  • The passenger's hand holding the phone looks distorted
  • The lighting is flat and less realistic compared to Model A

Verdict: Model B (Wan 2.7) followed the spatial instructions of the prompt more accurately by placing the passenger in the back seat, whereas Model A (FLUX.1 [dev]) placed her in the front. However, FLUX.1 [dev] produced a much higher quality image with superior lighting, textures, and a more convincing capybara, making it the more visually appealing result despite the composition error.

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 2.7

AI Judge Analysis

FLUX.1 [dev]

  • + Strong cinematic lighting with a vibrant glowing jack-o-lantern.
  • + Accurate interpretation of 'dark parchment' and 'moody night sky'.
  • Significant text errors including 'Lalloween Ranty' and 'You Tre'.
  • Did not include the spider webs requested in the border.
  • Repeats 'Time: 7pm, 7pm' and contains character artifacts like 'Archzs'.

Wan 2.7

  • + Perfect text rendering for all requested fields including location and date.
  • + Highly detailed border including both thorns and complex spider webs.
  • + Excellent adherence to the 'vintage' aesthetic with a parchment-like texture.
  • The transition between the central image and the parchment background feels a bit like a sticker.
  • The layout is slightly cluttered compared to the simplicity of Model A.

Verdict: Wan 2.7 is significantly better because it successfully rendered all the requested text accurately, whereas FLUX.1 [dev] produced several spelling errors and formatting glitches. Wan 2.7 also followed the specific border instructions for both webs and thorns, creating a more professional invitation layout.

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 2.7

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent soft lighting and dreamy 3D atmosphere
  • + Clean diorama style that feels like a miniature physical model
  • Spelling errors in the text, displaying 'SUSH CATON'
  • Lacks variety in the sushi types shown

Wan 2.7

  • + Accurate text spelling for both 'JAPAN' and 'SUSHI'
  • + High variety in sushi types including rolls and shrimp
  • + Clean, bold graphic design layout
  • Background color is more grey-blue than 'light blue'
  • Composition slightly favors the top left, making it feel less centered than image A

Verdict: Wan 2.7 is the clear winner for its perfect adherence to the text requirements, which FLUX.1 [dev] failed by misspelling 'SUSHI'. While FLUX.1 [dev] has a slightly more aesthetic lighting style, Wan 2.7 provides a much more detailed and accurate variety of sushi on the plate.

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 2.7
0% wins 0% ties 100% wins

AI Judge Analysis

FLUX.1 [dev]

  • + Warm and inviting lighting with a soft atmosphere.
  • + Consistent artistic style across all characters.
  • Failed the prompt by following a highly stylized cartoon/3D animation aesthetic instead of 'hyper-photorealistic'.
  • Missed a specific animal by providing two puppies instead of a tabby kitten.
  • The butterfly scale and positioning feel artificial and flat.

Wan 2.7

  • + Successfully captured the 'hyper-photorealistic' request with realistic fur textures and anatomy.
  • + Correctly included all requested animals: golden retriever, tabby kitten, bunny, and fox kit.
  • + Excellent lighting effects including clear god rays and atmospheric dew sparkles.
  • The cat's front right paw is anatomically incorrect where it touches the bunny.
  • The composition is slightly busy with many overlapping elements.

Verdict: Wan 2.7 is the clear winner as it followed the 'hyper-photorealistic' instruction and correctly included all four specific animals, whereas FLUX.1 [dev] produced a 3D animated style and omitted the kitten. Wan 2.7 also showed much better attention to the specific environmental details like the god rays and dew sparkles requested in 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.”

FLUX.1 [dev]
Wan 2.7

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent vintage typography style
  • + Clean minimalist vector aesthetic
  • + Accurate color palette and subtle texture
  • Significant spelling errors ('Flarilaan', 'Reseaurant')
  • Random numbers included that were not in the prompt

Wan 2.7

  • + Clean circular emblem composition
  • + Accurate typography for the 'Est. 1720' banner
  • + Good inclusion of the cloche dome with steam
  • Small spelling error in the main name ('Florion' instead of 'Florian')
  • Cloche design looks slightly more like a glass lid than a traditional metal dome

Verdict: While FLUX.1 [dev] captures the 'minimalist vintage' aesthetic more successfully, it fails significantly on text rendering, hallucinating extra characters and words. Wan 2.7 provides a much more usable logo with mostly accurate text and a more balanced emblem design, despite a one-letter typo in the main 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 2.7

AI Judge Analysis

FLUX.1 [dev]

  • + Elegant layout with a unified circular design
  • + High quality rendering of icons and background
  • + Excellent color palette consistency
  • Text is largely illegible gibberish
  • The rocket in the center is more of a generic icon than a Saturn V
  • Icons do not clearly follow the requested 6-step logical sequence

Wan 2.7

  • + Legendary text legibility with accurate headings like 'Translunar Injection'
  • + Strictly follows the 6-step hierarchical flow requested in the prompt
  • + Clean, accurate NASA-inspired flat-vector iconography
  • Slight spelling error on 'Descript' instead of 'Descent'
  • The white curve at the top right is a bit distracting in the composition

Verdict: Wan 2.7 significantly outperformed FLUX.1 [dev] on this task by following the specific sequential instructions for the infographic steps and rendering highly legible, contextually accurate text. While FLUX.1 [dev] produced a more artistic layout, it failed to convey any actual information and uses garbled text, making Wan 2.7 the superior choice for an infographic.

Next steps

Explore each model