Head to head
Esc

Models · slot A

to navigate to pick

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

Settled by community votes across 17 shared challenges, with an AI judge weighing in on each.

FLUX.1 Kontext [dev]

17.1 arena score

#54 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 Kontext [dev]

0%

win rate

Ties

0%

Wan 2.7

0%

win rate

Shared challenges 17

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 Kontext [dev]
Wan 2.7

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent photographic clarity and clean lines
  • + Accurately represents the blue sphere with realistic reflections from the window light
  • + Very clean composition that matches all spatial prompts correctly
  • The glass cube is missing its front face, appearing more like a glass stand or a three-sided box

Wan 2.7

  • + Successfully renders a full enclosed glass cube
  • + Provides realistic texture on the wooden table and the vintage book cover
  • + Includes accurate secondary reflections on the glass panels
  • The blue sphere's reflection on the left side of the cube appears as a ghostly second object rather than a clean reflection
  • Texture of the blue sphere is a bit matte/grainy compared to the expected smooth glass/sphere look

Verdict: Both models followed the complex spatial instructions perfectly. FLUX.1 Kontext [dev] produced a cleaner, more aesthetically pleasing image with better light handling, but failed to render the cube as a fully enclosed 6-sided object, whereas Wan 2.7 correctly modeled the geometry of the cube despite some minor artifacts in the 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 Kontext [dev]
Wan 2.7

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent handling of wet pavement and lighting reflections
  • + Sharp focus on the subject
  • + Vivid colors and clean rendering
  • The man is posing with the bike rather than repairing it
  • The rain effect looks like a simple filter over the top
  • The composition feels too centered and 'perfect' for a candid prompt

Wan 2.7

  • + Strong adherence to the 'candid' and 'imperfect framing' prompt
  • + Active engagement with the repair task
  • + Extremely realistic skin textures and clothing details
  • The background figures are slightly distorted
  • Less cinematic lighting compared to the opponent

Verdict: Wan 2.7 significantly outperforms FLUX.1 Kontext [dev] in realism and prompt adherence by capturing a truly candid moment of repair with authentic imperfection. While FLUX.1 produces a clean, high-contrast image, the man is simply sitting on the bike, and the 'no stylization' request was ignored in favor of a clean, stock-photo look.

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 Kontext [dev]
Wan 2.7

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Strong dramatic lighting with consistent warm highlights on one side
  • + Highly intricate engraving patterns on the chest plate armor
  • + Clean, high-contrast composition
  • Missed the request for braided hair with beads
  • The skin texture looks slightly smoothed and less 'battle-worn' than requested

Wan 2.7

  • + Excellent adherence to the 'braided hair with small beads' detail
  • + Very realistic skin texture with visible pores, dirt, and lifelike eyes
  • + Clearly visible leather straps and buckles with authentic textures
  • The sparks in the background are somewhat distracting and large
  • The lighting on the face is a bit flat compared to the dramatic armor highlights

Verdict: Wan 2.7 is the superior image as it followed every specific detail of the prompt, including the braided hair with beads and the leather strap textures which FLUX.1 Kontext [dev] omitted. While FLUX.1 has more dramatic lighting, Wan 2.7 provides a much more convincing 'battle-worn' look with superior skin detailing and authentic material rendering.

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 Kontext [dev]
Wan 2.7

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Strong minimalist aesthetic with high-contrast bold typography
  • + Excellent high-resolution food photography with vibrant colors
  • + Clean, balanced grid composition
  • Text is largely gibberish with significant spelling errors
  • Lacks the specific sub-sections requested in the layout

Wan 2.7

  • + Perfect adherence to specific menu sections like appetizers, pizza, and mains
  • + Highly legible typography and structured professional layout
  • + Inclusion of realistic menu elements like pricing, address, and QR code
  • Some small text descriptions are blurry or nonsensical upon close inspection
  • Grid images have softer focus compared to Model A

Verdict: Wan 2.7 followed the prompt's structural requirements much more effectively, creating a functional menu layout with defined sections for appetizers, pizza, and mains. While FLUX.1 Kontext [dev] produced more striking individual food photos and a more 'high-art' minimalist feel, its failure to generate readable or logically structured menu text makes Wan 2.7 the superior choice for this specific design challenge.

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 Kontext [dev]
Wan 2.7

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent photographic rendering of the coals and burger textures.
  • + Clean, bold typography that is very legible.
  • Failed the core prompt instruction for an 'exploded burger' with components suspended in mid-air.
  • Spelling error in the secondary text ('LNHLY' instead of 'ONLY').

Wan 2.7

  • + Perfect adherence to the 'exploded burger' layout with suspended components.
  • + High-quality typography with zero spelling errors and creative fiery effects.
  • + Excellent interpretation of the starburst and ember details requested.
  • The cucumber slice was not explicitly requested (though it fits the theme).
  • Slightly less photorealistic lighting on the lettuce compared to the patty.

Verdict: Wan 2.7 is the clear winner as it successfully executed the complex 'exploded burger' layout which FLUX.1 Kontext [dev] completely ignored. Additionally, Wan 2.7 maintained perfect spelling and better followed the specific stylistic requests for the fiery text and starburst element.

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 Kontext [dev]
Wan 2.7

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Very realistic chalk texture with visible smudging and pressure variations
  • + Captures the authentic look of a hand-drawn chalkboard with a wooden frame
  • Several spelling errors including 'Mashroom', 'Risoktso', and 'Octpus'
  • Repetitive words and garbled text in the date and pricing sections

Wan 2.7

  • + Perfect spelling and text accuracy for all requested items
  • + Consistent and clean handwriting-style typography
  • + Better environmental composition with café background elements
  • The text looks a bit too 'perfect', leaning towards a digital font feel rather than raw chalk
  • Lack of the requested 'elegant cursive' for the title

Verdict: Wan 2.7 is the clear winner because it correctly spelled every complex menu item requested, whereas FLUX.1 Kontext [dev] suffered from significant legibility issues and typos. While FLUX.1 had a more realistic chalk texture, the accuracy and professional layout of Wan 2.7 make it much more useful for the prompt's requirements.

The Reversed Rodeo

Text-to-Image

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

FLUX.1 Kontext [dev]
Wan 2.7

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Successfully followed the difficult logic of placing the horse on top of the astronaut.
  • + High detail on the astronaut's face and suit textures.
  • + Clean, minimalist composition with a professional cinematic feel.
  • The 'riding' aspect is a bit ambiguous as the horse is floating/clinging behind the astronaut rather than sitting on him.
  • Lower background complexity compared to the competitor.

Wan 2.7

  • + Vibrant and detailed background with galaxies and planets.
  • + Well-rendered horse anatomy and tack.
  • Failed the primary negative constraint by showing the astronaut riding the horse.
  • Clichéd composition that ignores the surreal logic requested in the prompt.

Verdict: FLUX.1 Kontext [dev] is the clear winner because it actually attempted and largely succeeded at the 'horse on top' constraint, creating a surreal image as requested. Wan 2.7 ignored the specific directional instruction and produced a standard, unoriginal 'astronaut on a horse' image.

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 Kontext [dev]
Wan 2.7

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent photographic lighting and depth of field
  • + Highly realistic textures for both the capybara fur and the clothing
  • + The human subject appears perfectly integrated with a natural bored expression
  • One 'paw' is resting on its lap instead of both being on the steering wheel as requested
  • The capybara's head is slightly oversized for its body

Wan 2.7

  • + Successfully placed both paws on the steering wheel
  • + Good wide-angle composition showing more of the taxi and city exterior
  • + Accurate representation of a traditional chauffeur-style taxi cap
  • The passenger is sitting in the front seat instead of the back seat as requested
  • The woman's hand holding the phone has significant structural issues
  • The capybara's fur looks somewhat coarse and less photorealistic compared to Model A

Verdict: FLUX.1 Kontext [dev] produced a much higher quality image with superior lighting and anatomical realism, though it missed the specific detail of having both paws on the wheel. Wan 2.7 followed the paw placement instruction but failed the much larger request of placing the passenger in the back seat, and it suffered from notable defects in the rendering of the human hands.

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 Kontext [dev]
Wan 2.7

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Strong cinematic lighting on the central jack-o-lantern
  • + Clean, bold title font that is easy to read
  • Significant spelling errors in the banner and location text
  • Lacks the 'dark parchment' aesthetic, appearing more like a digital poster on a black background
  • The border is very simple and lacks the requested thorns and webs detail

Wan 2.7

  • + Perfect text rendering for all requested fields, including small details
  • + Excellent adherence to the 'vintage gothic' and 'parchment' style with an intricate border
  • + Rich composition featuring all requested elements like twisted trees, bats, and a moody sky
  • The illustration style is slightly more 'storybook' than 'cinematic'
  • The central jack-o-lantern is part of a flat-looking framed illustration rather than a standalone focal point

Verdict: Wan 2.7 is the clear winner as it successfully rendered every piece of text perfectly, which is critical for an invitation prompt. While FLUX.1 Kontext [dev] has nice lighting on the pumpkin, its failure to spell the location correctly and its omission of the vintage parchment aesthetic makes it less effective overall.

Bald man challenge

Image Editing
Edit instruction

“Give the person a full, thick head of natural hair with realistic texture, density, and a natural hairline. Preserve facial features and lighting.”

Before After
FLUX.1 Kontext [dev]
Before After
Wan 2.7

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Fulfilled the prompt by adding a full head of hair.
  • + Maintained the general composition and clothing of the source image.
  • Failed to preserve facial features, making the person look significantly younger and smoothing out skin details.
  • Altered the shape of the glasses and the bridge of the nose.
  • The hair looks slightly artificial and 'helmet-like' compared to the original style.

Wan 2.7

  • + Excellent source preservation, keeping the identical facial features, glasses, and background.
  • + Realistic hair texture and color that blends seamlessly with the existing beard.
  • + Maintains the skin texture and lighting of the original image perfectly.
  • None identified; the edit is highly effective.

Verdict: Wan 2.7 is the clear winner as it successfully added a full head of hair while perfectly preserving the identity, skin texture, and lighting of the man in the original photo. FLUX.1 Kontext [dev] struggled with the 'preserve facial features' instruction, effectively generating a new face that looks much younger and less detailed than the source image.

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 Kontext [dev]
Wan 2.7

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent typography style that matches the 3D aesthetic.
  • + Very clean, minimal, and high-clarity composition.
  • + Accurate soft 3D plastic textures.
  • The flag icon is a strange geometric abstraction rather than a recognizable Japan flag.
  • The sushi piece is very simplified, looking more like a toy than food.

Wan 2.7

  • + Successfully renders a recognizable Japanese flag icon.
  • + Higher level of detail in the sushi variety and garnishes.
  • + Perfect adherence to the 45-degree isometric perspective.
  • The text has slight kerning issues and an unnecessary border around the flag.
  • Includes more garnish and items than the 'minimal' request asked for.

Verdict: Wan 2.7 is the preferred choice because it demonstrates a much better understanding of the requested scene components, including a correct flag, varied sushi types, and a proper isometric base. FLUX.1 Kontext [dev] produced a very clean image but failed on the flag icon and provided an overly simplified single piece of sushi.

Over-the-top cartoon caricature

Editing
Edit instruction

“Create a caricature of me and my job. Make it exaggerated and humorous, incorporating my profession as a tv show anchor and my love for dogs and hockey.”

Source
FLUX.1 Kontext [dev]
Wan 2.7

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Maintains the subject's casual denim outfit from the source image
  • + Clearly incorporates a TV and a dog
  • Completely misses the 'hockey' requirement
  • The caricature style is very basic and flat
  • Includes random floating text 'JOB' which is literal rather than creative

Wan 2.7

  • + Successfully incorporates all prompt elements including hockey (puck, rink, helmet)
  • + Excellent caricature style with exaggerated features while maintaining likeness
  • + Creative scene composition with dogs interacting with the TV anchor setting
  • Changes the subject's clothing from a denim shirt to a news anchor suit (though fits the profession prompt)
  • Minor text artifacts in the speech bubbles ('Rolee')

Verdict: Wan 2.7 is the clear winner as it successfully incorporated every element of the prompt, including the specific 'hockey' request which FLUX.1 Kontext [dev] completely ignored. Wan 2.7 also provided a much more dynamic and high-quality caricature style, whereas FLUX.1 Kontext [dev] produced a flatter, less creative illustration and missed key details.

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 Kontext [dev]
Wan 2.7

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent dynamic motion with the animals appearing to pounce and run
  • + High-quality soft lighting and clean focus on the subjects
  • Failed to include the fox and bunny entirely
  • Anatomical issues with the animals having too many limbs or merged paws

Wan 2.7

  • + Perfect adherence to the prompt by including all four specific animals
  • + Beautiful render of 'god rays' and dew sparkles as requested
  • + Highly detailed fur textures on the tabby kitten and fox
  • The fox's facial structure looks slightly more adult than a 'kit'
  • The cat's front paw placement on the bunny is a bit awkward

Verdict: Wan 2.7 is the clear winner because it correctly provided all four animals requested in the prompt (puppy, kitten, bunny, and fox), whereas FLUX.1 Kontext [dev] only generated three subjects and omitted the fox and bunny entirely. Wan 2.7 also better captured the atmospheric details like god rays and dew sparkles in a lush wildflower meadow.

Studio Ghibli Anime Style

Editing
Edit instruction

“Transform this photo into a Studio Ghibli–inspired illustration. Use soft pastel colors, hand-painted textures, gentle lighting, dreamy backgrounds, and a warm, nostalgic mood”

Source
FLUX.1 Kontext [dev]
Wan 2.7

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent preservation of the original pose and character stances.
  • + Accurately recreates specific clothing details like the plaid pattern on the shirt.
  • + Clean cel-shaded anime aesthetic.
  • The style feels more like a generic modern anime than the specific soft, hand-painted Ghibli style.
  • The expressions are significantly altered, losing the 'shocked' look of the original man.

Wan 2.7

  • + Strong adherence to the 'hand-painted textures' and 'soft pastel colors' request.
  • + Better captures the Ghibli aesthetic through watercolor-like washes and line work.
  • + Preserves the nuanced facial expressions of the original subjects more accurately than Model A.
  • The plaid pattern on the shirt is slightly simplified compared to the source.
  • Slightly less clarity in the edges of the foreground character.

Verdict: Both models successfully transformed the meme into an illustration while keeping the composition intact. FLUX.1 Kontext [dev] produced a clean, modern digital anime look, but Wan 2.7 much more effectively captured the specific Ghibli-esque watercolor texture and nostalgic atmosphere requested in the prompt.

Golden Hour Stroll

Image Editing
Edit instruction

“Add dynamic motion to this photo: make hair blow in the wind, add leaves flying, energetic and lively feel.”

Before After
FLUX.1 Kontext [dev]
Before After
Wan 2.7

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent preservation of the subject's face and the background scenery
  • + Subtle wind effect on the hair that looks natural
  • The 'flying leaves' are very small, sparse, and look more like green specks than leaves
  • Lacks a truly 'energetic' feel compared to the other model

Wan 2.7

  • + Successfully added a large number of dynamic, autumnal flying leaves throughout the scene
  • + Significant hair motion that feels much more lively and energetic
  • + Good preservation of the original composition and character identity
  • Some leaves appear slightly blurred or poorly integrated with the background depth
  • Minor lighting changes on the subject's denim jacket compared to the original

Verdict: Wan 2.7 followed the instructions much more effectively, providing a high volume of flying leaves and significant hair movement that creates a genuine sense of motion. FLUX.1 Kontext [dev] was too subtle with its edits, with leaves that are barely visible and hair that is only slightly tousled.

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 Kontext [dev]
Wan 2.7

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent typography and spelling accuracy
  • + True minimalist aesthetic with clean lines
  • + High contrast and professional vector finish
  • The dome illustration is slightly abstract and looks more like a building or cupcake than a cloche
  • Missing the requested 'banner' element
  • Lacks the subtle background texture mentioned in the prompt

Wan 2.7

  • + Successfully incorporates the banner and circular emblem style
  • + Detailed and recognizable cloche dome with steam
  • + Excellent use of warm brown tones and subtle paper texture
  • Slight misspelling of the name as 'Florion'
  • The composition is quite busy, leaning away from the 'minimalist' requirement
  • Line weights in the illustration are inconsistent with the typography

Verdict: FLUX.1 Kontext [dev] delivers a much better 'minimalist' logo with perfectly rendered text, though it misses the specific request for a banner. Wan 2.7 follows more of the detailed prompt instructions (banner, steam, texture) but fails on the primary name spelling and the minimalist style. FLUX.1 Kontext [dev] is the likely winner for its superior typography and professional design quality.

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 Kontext [dev]
Wan 2.7

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Successfully uses the base NASA-inspired color palette.
  • + Includes dynamic icons that suggest movement.
  • Serious spelling errors in the main title ('Apolo') and almost all body text.
  • Iconography is cluttered, confusing, and does not clearly follow the requested 6-step sequence.
  • Composition is disorganized and fails to look like a professional infographic.

Wan 2.7

  • + Excellent adherence to the sequential 6-step structure requested.
  • + High-quality vector aesthetic with crisp lines and consistent iconography.
  • + Legible text and logical information flow that mimics a real educational poster.
  • One minor typo in the 'Descent' step label ('Descript').
  • The background stars are somewhat clustered rather than evenly distributed.

Verdict: Wan 2.7 is the clear winner as it perfectly follows the requested infographic structure, sequence of steps, and flat-vector style. While FLUX.1 Kontext [dev] struggled with basic legibility and organization, Wan 2.7 produced a coherent, professional-looking poster with accurate icons for each mission phase.

Next steps

Explore each model