Head to head
Esc

Models · slot A

to navigate to pick

FLUX.1 Krea [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 Krea [dev]

18.8 arena score

#48 of 62 in Text-to-Image

Skill signature · Text-to-Image

Wan 2.7

20.5 arena score

#38 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.1 Krea [dev]

0%

win rate

Ties

0%

Wan 2.7

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 Krea [dev]
Wan 2.7

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent photorealistic lighting and depth of field
  • + Accurate depiction of glass refraction and reflections
  • + Clean and simple composition that follows all logical spatial constraints
  • The sphere is quite dark, appearing almost black/navy instead of a vibrant blue

Wan 2.7

  • + High level of detail in the textures of the wood and book cover
  • + Clearer visibility of the green plant through the glass
  • + Bright, vibrant blue sphere as requested
  • The glass cube has perspective issues, with some edges appearing like mirrors rather than transparent glass
  • The reflection of the sphere on the left is physically incoherent with the scene

Verdict: Both models followed the complex spatial instructions perfectly. FLUX.1 Krea [dev] produced a more believable, cinematic photograph with superior lighting, while Wan 2.7 excelled in texture detail and color vibrancy but struggled with the geometric logic of the glass reflections.

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 Krea [dev]
Wan 2.7

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent depiction of motion blur from passing cars
  • + Strong adherence to the shallow depth of field and 50mm look
  • + Consistent wet pavement reflections and rainy atmosphere
  • The subject is just standing with the bike rather than actively 'repairing' it
  • Structural issues with the bicycle frame near the pedals

Wan 2.7

  • + Subject is clearly engaged in the act of repairing the handlebars
  • + Highly realistic skin textures and clothing details with wet patches
  • + Brilliant environmental reflections and complex background details
  • Lack of motion blur on the background vehicles as requested
  • Minor anatomical issues with the length of the man's left arm

Verdict: Wan 2.7 delivers a more authentic 'candid' feel with superior textures and a subject actually performing the requested action, though it misses the motion blur requirement. FLUX.1 Krea [dev] captures the requested cinematic motion blur and lens effects perfectly, but the subject's pose is too static and the bike geometry is slightly warped. Wan 2.7 is preferred for its exceptional realism and adherence to the 'repairing' part of the prompt.

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 Krea [dev]
Wan 2.7

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent dramatic lighting with high-contrast shadows
  • + Highly detailed and intricate engraving on the plate armor
  • + Very lifelike eyes and skin texture captured in cinematic lighting
  • Blood splatter looks more like fresh paint than 'faint scars and dirt'
  • The braids are relatively simple compared to the other model

Wan 2.7

  • + Perfect adherence to the 'faint scars and dirt' prompt with realistic facial weathering
  • + The hair braids and beads are more complex and varied
  • + Armor shows more realistic signs of wear and tear alongside the engraving
  • Lighting is somewhat flat and less cinematic than the competing model
  • Background torch is a bit distracting and lessens the 'shallow depth of field' effect

Verdict: Both models followed the prompt exceptionally well, but Wan 2.7 interpreted the 'battle-worn' and 'scars' aspect with much higher realism. FLUX.1 Krea produced a more visually striking and cinematic portrait, though it leaned into blood splatters rather than the requested scars.

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 Krea [dev]
Wan 2.7

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Strong minimalist aesthetic with a clean vertical grid
  • + Excellent use of bold sans-serif headers
  • + High-quality, realistic food photography photography
  • Text is largely illegible gibberish except for headers
  • Repeats the section header 'Appetizers' twice while missing 'Pizza'

Wan 2.7

  • + Successfully includes individual photos for various items in a clear grid
  • + Text is surprisingly legible and descriptive
  • + Better adherence to the specific requested sections (Appetizers, Pizza, Mains)
  • Layout feels a bit crowded and busy for a 'minimalist' prompt
  • Includes several extra non-prompted elements like the pen and garnishes around the paper

Verdict: Wan 2.7 provides a much more functional menu design that correctly implements the requested sections and features legible text, whereas FLUX.1 Krea (dev) has superior typography and photographic quality but fails on textual content and specific section adherence. While FLUX.1 Krea looks more like a high-end design piece, Wan 2.7 is the better realization of a usable restaurant menu.

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 Krea [dev]
Wan 2.7

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent photorealistic texture on the bun and patty.
  • + Clean and legible typography for the main title.
  • + Physically grounded lighting from the fire below.
  • Failed to place the price in a starburst as requested.
  • The burger is barely 'exploded'; it looks mostly stacked.
  • Includes garbled AI text at the bottom of the frame.

Wan 2.7

  • + Perfectly captures the 'exploded' dynamic with separated flying ingredients.
  • + Accurately follows all text instructions, including the fiery font and the starburst price tag.
  • + High sense of motion with sauce splashes and flying embers.
  • Stylistically leans more towards a 3D digital illustration than raw photorealism.
  • The lettuce and tomato look slightly artificial compared to the burger patty.

Verdict: Wan 2.7 followed every detail of the prompt, including complex layout requirements like the starburst price and the 'exploded' burger effect. While FLUX.1 Krea (dev) has superior photorealistic textures, it failed on several specific prompt instructions and provided a much more static composition.

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 Krea [dev]
Wan 2.7

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent chalk-on-board texture with realistic dust and smudges.
  • + Handwriting looks truly organic and manual with natural variations.
  • + Captures a realistic café atmosphere through lighting and framing.
  • Significant text errors including 'Gruffle' and 'Chvcruations'.
  • The bottom text becomes illegible and messy.

Wan 2.7

  • + Perfect spelling adherence for all requested menu items.
  • + Consistent and highly legible text across the entire board.
  • + Includes thoughtful details like 'gluten-free' at the bottom.
  • The text looks like a digital font overlay rather than real hand-drawn chalk.
  • The 'handwritten' style is too uniform and lacks the requested natural variations and texture.

Verdict: Wan 2.7 followed every instruction regarding the specific text and spelling, resulting in a perfectly readable and error-free menu. FLUX.1 Krea (dev) succeeded much better at the artistic prompt of making the chalk look handmade and realistic, but it failed significantly on text accuracy and spelling.

The Reversed Rodeo

Text-to-Image

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

FLUX.1 Krea [dev]
Wan 2.7

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent anatomical detail on the horse and astronaut
  • + Impressive cinematic lighting with realistic shadows
  • + Creative integration of sci-fi tech onto the horse body
  • Failed the specific spatial instruction for the horse to be on top of the astronaut

Wan 2.7

  • + Sharp resolution and vibrant colors
  • + Balanced composition with interesting background elements like galaxies
  • + Clear, high-quality rendering of the space suit
  • Failed the specific spatial instruction for the horse to be on top of the astronaut
  • Front right leg of the horse is anatomically incorrect/clumped

Verdict: Both models failed the complex 'horse on top' logic, defaulting to the common trope of an astronaut riding a horse. FLUX.1 Krea [dev] is the superior image due to its more realistic cinematic lighting and more believable animal anatomy compared to Wan 2.7.

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 Krea [dev]
Wan 2.7

AI Judge Analysis

FLUX.1 Krea [dev]

  • + The capybara's fur and face are rendered with high photorealism.
  • + Correctly placed a passenger in the back seat as requested.
  • + The lighting and blurred city background feel very cinematic and appropriate for a night scene.
  • Included an extra human figure in the passenger seat that was not requested.
  • The 'TAXI' text on the cap is a bit simplistic and looks like a plastic toy helmet.

Wan 2.7

  • + The capybara's paws are clearly visible and correctly positioned on the steering wheel as requested.
  • + The taxi driver cap looks like authentic uniform headwear.
  • + Excellent representation of the bored businesswoman looking at her phone.
  • The passenger is in the front seat instead of the back seat as requested.
  • The capybara's fur texture appears slightly more illustrated/stylized compared to Model A.
  • There is some anatomical weirdness with the passenger's hands and the way she holds the phone.

Verdict: Both models struggled with spatial logic, as FLUX.1 Krea [dev] added an extra person and Wan 2.7 moved the passenger to the front seat despite the prompt specifying the back seat. FLUX.1 Krea [dev] is preferred for its superior photorealistic texture and lighting, making the surreal scene feel more grounded in reality.

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 Krea [dev]
Wan 2.7

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Features a very high-quality, glowing jack-o-lantern
  • + Captures a dark, moody cinematic atmosphere effectively
  • + Ornate border design matches the gothic aesthetic
  • Numerous spelling errors in text (e.g., 'Pasty Halloween', 'nighls Trighl')
  • Text layout is repetitive and cluttered at the bottom
  • Missed some specific text elements requested in the prompt

Wan 2.7

  • + Excellent text rendering with near-perfect spelling of all details
  • + High level of detail in the border including thorns, skulls, and vines
  • + Composition is clear and well-organized for an invitation
  • The lighting is less 'cinematic' and more illustrative/cartoonish
  • The jack-o-lantern face is quite basic compared to the other model

Verdict: Wan 2.7 is the superior choice for this task because it accurately rendered all specific text information, including the date, time, and headers, with minimal errors. While FLUX.1 Krea (dev) has better atmospheric lighting and a more impressive central pumpkin, its severe spelling mistakes and incoherent text placement make it unusable as an actual invitation.

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 Krea [dev]
Wan 2.7

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent adherence to the 'icon' style and simplicity.
  • + Clean, professional typography that fits the cartoon aesthetic.
  • + Superior handling of lighting and shadows on the diorama base.
  • Shows only one piece of sushi, which may feel a bit sparse for the prompt.
  • The 'flag icon' is rendered as a physical object rather than a graphic element as suggested by the text layout instructions.

Wan 2.7

  • + Provides a more detailed and colorful variety of sushi types.
  • + Excellent material rendering on the salmon and tuna textures.
  • + Good placement of the flag icon alongside the text.
  • The text is slightly off-center and feels more like an overlay than integrated into the scene.
  • The chopsticks are inconsistently sized and positioned.

Verdict: FLUX.1 Krea (dev) followed the layout instructions more precisely, creating a perfectly centered, ultra-clean isometric icon with great lighting. While Wan 2.7 provided a more generous and visually interesting tray of sushi, the composition and typography in FLUX.1 Krea felt more professional and better suited for a 'miniature 3D cartoon' asset.

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 Krea [dev]
Wan 2.7

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent soft lighting and atmospheric god rays.
  • + Very expressive and cute facial features on the animals.
  • + High-quality fur textures and realistic depth of field.
  • Missed the rabbit completely, substituting it with a second kitten.
  • Lower variety in flora compared to the other model.

Wan 2.7

  • + Successfully included all four requested animals (dog, cat, rabbit, fox).
  • + Beautiful rendering of dew drops and diverse wildflowers.
  • + Strong adherence to the 'playful chasing' action described.
  • The fox's face looks slightly distorted and less realistic than the other animals.
  • The kitten's pose is a bit awkward with its mouth open.

Verdict: Wan 2.7 is the winner primarily because it successfully included all the requested animals, including the baby bunny which FLUX.1 Krea [dev] replaced with a second kitten. While both models captured the lighting and 'wholesome' vibe well, Wan 2.7 demonstrated better prompt adherence and finer environmental details like the dew sparkles.

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 Krea [dev]
Wan 2.7

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent vintage engraving style with artistic line work
  • + Authentic subtle texture on the background
  • + Strong cloche dome illustration with integrated steam
  • Major spelling errors in the brand name ('FLANDORIN' instead of 'Florian')
  • Cluttered composition where the text overlaps the graphic elements awkwardly

Wan 2.7

  • + Accurate spelling of 'Caffè' and legible 'Est. 1720' banner
  • + Clean, balanced vector emblem composition
  • + Excellent adherence to the 'classic typography' and 'cloche dome' requirements
  • Minor spelling error in the main name ('Florion' instead of 'Florian')
  • The steam lines look a bit thin and detached compared to the rest of the logo

Verdict: While FLUX.1 Krea [dev] captures a more authentic vintage texture and hand-drawn engraving style, it fails significantly on the primary brand name. Wan 2.7 provides a much more professional and balanced logo layout with better legibility, despite a minor one-letter typo.

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 Krea [dev]
Wan 2.7

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Bold, clean typography for the main title.
  • + Crisp vector shapes and consistent color palette application.
  • Fails significant parts of the step-by-step logic, including nonsensical icons for steps 3 and 4.
  • Text is mostly garbled and non-informative.
  • The layout is disorganized with random number placement and nonsensical arrows.

Wan 2.7

  • + Excellent adherence to all 6 requested steps with relevant icons.
  • + High-quality text rendering and inclusion of educational supporting details.
  • + Professional, vertical infographic layout that is easy to follow.
  • One minor spelling error under step 5 ('DESCRIPT' and 'Deccent').
  • Small typo in 'Tranquiliry'.

Verdict: Wan 2.7 is the clear winner as it successfully created a logical, sequential infographic that followed all prompt instructions for icons and steps. FLUX.1 Krea produced a disorganized collection of space-themed graphics that lacked the requested informational structure and coherent iconography.

Next steps

Explore each model