Head to head
Esc

Models · slot A

to navigate to pick

FLUX.1 Kontext [pro] 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 [pro]

20.3 arena score

#41 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 [pro]

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 [pro]
Wan 2.7

AI Judge Analysis

FLUX.1 Kontext [pro]

  • + Excellent adherence to lighting instructions with a clear soft light from the left.
  • + Very clean, modern aesthetic with highly realistic glass refraction.
  • + The blue sphere has a fine felt-like texture that shows high detail resolution.
  • The plant is more in the background than 'behind' and visible through the glass.
  • The glass cube looks more like a frame or acrylic box rather than a solid or thick glass object.

Wan 2.7

  • + Successfully places the plant behind the cube, visible through the glass with realistic distortion.
  • + The book has high textural detail and realistic weathering.
  • + The wooden table has a rich, rustic texture that adds character to the composition.
  • Confused geometry inside the glass cube with extraneous reflections and odd internal planes.
  • The lighting is a bit flat compared to the requested 'soft window light' from a specific direction.

Verdict: Both models followed the complex spatial instructions well. FLUX.1 Kontext [pro] produced a much cleaner and more aesthetically pleasing image with superior lighting, though it missed the specific detail of the plant being seen through the glass. Wan 2.7 succeeded in the plant placement and had more realistic object textures (like the aged book), but it struggled with the internal consistency and physics of the glass cube.

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 [pro]
Wan 2.7

AI Judge Analysis

FLUX.1 Kontext [pro]

  • + Excellent shallow depth of field with a true 50mm lens look.
  • + High-quality skin textures and realistic rain effects.
  • + Perfectly captures the 'candid' and 'cinematic' mood requested.
  • The red bicycle is only partially visible due to the tight framing.
  • Lower amount of environmental detail compared to the competitor.

Wan 2.7

  • + Successfully captures the full red bicycle and a wider street context.
  • + Provides excellent wet pavement reflections and a realistic urban setting.
  • + Includes motion blur on the background car as requested.
  • Faces of background pedestrians are distorted or unfinished.
  • The lighting feels a bit flat and less 'cinematic' than Model A.
  • Lacks the shallow depth of field specified in the prompt.

Verdict: FLUX.1 Kontext [pro] captures the requested mood and photographic style much better, providing a beautiful shallow depth of field and realistic skin textures that feel cinematic. While Wan 2.7 succeeded in showing more of the bicycle and street environment, it failed to deliver a shallow depth of field and suffered from messy details on background figures.

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 [pro]
Wan 2.7

AI Judge Analysis

FLUX.1 Kontext [pro]

  • + Excellent soft lighting and atmospheric depth of field
  • + High-quality skin texture and lifelike eyes
  • + Intricate engraving on the metal armor
  • Fails to include the requested small beads in the hair
  • Scaring and 'battle-worn' effects are very subtle

Wan 2.7

  • + Perfect adherence to specific details like hair beads and multiple scars
  • + Strong textural contrast on leather straps and metal
  • + Clearly visible torchlight and bokeh sparks
  • Skin texture is slightly over-sharpened
  • The engraving on the pauldron feels a bit flat compared to the metal texture

Verdict: While FLUX.1 Kontext [pro] produces a more cinematic and naturally lit portrait, Wan 2.7 followed the specific prompt instructions much more accurately, particularly regarding the hair beads and the 'battle-worn' scars. Wan 2.7 is preferred for its attention to every detail of the request, although FLUX.1 has a slight edge in photorealistic lighting and skin 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 [pro]
Wan 2.7

AI Judge Analysis

FLUX.1 Kontext [pro]

  • + Excellent typography with clean, bold sans-serif fonts
  • + Balanced professional layout that exactly follows the requested section headers
  • + High image clarity with vibrant color accents
  • The food items are incorrectly placed under headings, such as a pizza being under 'Mains' instead of 'Pizza'
  • Significant spelling errors in the body text

Wan 2.7

  • + Successfully creates a grid layout for food photos
  • + Includes creative branding elements and a professional graphic design feel
  • + Better text legibility and spelling for menu item names
  • Failed to create separate distinct sections for Appetizers, Pizza, and Mains as requested
  • The background is busy with props like pens and rosemary instead of a clean white background
  • Does not follow the minimalist requirement as well as the competitor

Verdict: FLUX.1 Kontext [pro] creates a much more authentic minimalist menu that fits the requested professional aesthetic, despite some dish logic errors. Wan 2.7 provides a more complete 'marketing' image with better item descriptions, but it fails the primary prompt instruction to organize the layout into specific sections for appetizers, pizza, and mains.

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 [pro]
Wan 2.7

AI Judge Analysis

FLUX.1 Kontext [pro]

  • + Excellent photorealistic lighting and texture on the food.
  • + Clean and legible primary typography.
  • + Atmospheric integration of embers and glowing effects.
  • Missed the 'starburst' requirement for the price.
  • Failed to separate the burger components into a truly 'exploded' view; it looks like a stacked burger.
  • Repeated the price text twice in a confusing layout.

Wan 2.7

  • + Perfectly captured the 'exploded' view with suspended components.
  • + More creative 'fiery' typography that fits the ad theme.
  • + Strictly adhered to the including the starburst for the price.
  • Texture on the meat and bun looks slightly more illustrated/CGI than photorealistic.
  • Random floating seeds/nuts on the left side of the frame feel out of place.
  • Text rendering on 'MAGIC BURGER' is a bit busy with the flame effect tops.

Verdict: While FLUX.1 Kontext [pro] offers superior photorealism and lighting, Wan 2.7 is the winner for its superior prompt adherence regarding the exploded burger layout and the specific starburst graphic requested. Wan 2.7 managed to include every required text element and compositional detail, whereas FLUX.1 Kontext [pro] failed the primary architectural request of an exploded view.

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 [pro]
Wan 2.7

AI Judge Analysis

FLUX.1 Kontext [pro]

  • + Excellent chalk texture that looks authentically dusty and hand-drawn.
  • + Perfect adherence to the prompt's request for natural variations in letter size and slant.
  • + Highly legible text with a realistic wooden frame.
  • The cursive for the title is quite blocky rather than 'elegant'.
  • Includes spelling errors in the footer text like 'ous' and 'tree'.

Wan 2.7

  • + Beautifully composed with warm cafe lighting and decorative elements.
  • + The handwriting style is elegant and consistent across the board.
  • + Flawless spelling for all requested menu items and the footer information.
  • The text looks more like a digital font overlay or a clean decal than actual chalk.
  • Missing the requested chalk texture and natural variations in the lettering.

Verdict: FLUX.1 Kontext [pro] creates a much more realistic chalk effect with convincing textures and human-like imperfections, though it suffers from minor spelling errors at the bottom. Wan 2.7 produces a visually stunning scene with perfect spelling, but the text lacks the requested chalk texture and appears too digitally perfect to be a real handwritten chalkboard.

The Reversed Rodeo

Text-to-Image

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

FLUX.1 Kontext [pro]
Wan 2.7

AI Judge Analysis

FLUX.1 Kontext [pro]

  • + Perfectly followed the unconventional instruction of having the horse on top of the astronaut.
  • + Very high level of cinematic detail in both the astronaut's suit and the horse's coat.
  • + Included a clever 'surreal' detail where the astronaut's human legs end in hooves.
  • A second, smaller astronaut is inexplicably riding the horse, creating a confusing hierarchy.
  • The horse's hind legs are somewhat awkwardly positioned near the astronaut's shoulder.

Wan 2.7

  • + Clean, vibrant composition with high clarity.
  • + Excellent background details featuring multiple galaxies and planets.
  • + Good rendering of the horse's anatomy and the space suit textures.
  • Failed the primary prompt constraint; the astronaut is riding the horse instead of vice versa.
  • Lacks the requested 'surreal' quality, opting for a standard sci-fi interpretation.

Verdict: FLUX.1 Kontext [pro] is the clear winner because it successfully followed the complex and counter-intuitive prompt to place the horse on top of the astronaut. Wan 2.7 defaulted to a standard trope of an astronaut riding a horse, completely ignoring the specific instruction 'horse on top, not vice versa.'

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 [pro]
Wan 2.7

AI Judge Analysis

FLUX.1 Kontext [pro]

  • + Natural, cinematic lighting and color grading
  • + High-quality fur texture and realistic animal rendering
  • + Fits the 'taxi driver' character look well with the cap and jacket
  • The passenger is on a call rather than looking at her phone as requested
  • Only one paw is clearly visible on the steering wheel
  • Passenger placement feels slightly cramped compared to a real taxi

Wan 2.7

  • + Excellent adherence to the 'bored passenger on phone' instruction
  • + Shows both paws on the steering wheel as requested
  • + Clearer background city environment highlighting the Manhattan setting
  • The capybara's fur has a somewhat artificial, spiky quality
  • Anatomical issues with the capybara's paws looking more like human fingers/claws
  • Slightly less realistic lighting compared to Image A

Verdict: Both models followed the complex prompt well, but they succeeded in different areas. FLUX.1 Kontext [pro] created a more photorealistic image with superior textures and lighting, while Wan 2.7 adhered more strictly to the specific actions requested, such as showing both paws and the passenger's bored expression while on her phone. Wan 2.7 is the likely winner for capturing all the narrative elements of the prompt simultaneously despite its slightly lower texture quality.

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 [pro]
Wan 2.7

AI Judge Analysis

FLUX.1 Kontext [pro]

  • + Excellent atmospheric lighting with a high-contrast cinematic feel
  • + Impressive detail on the spiderweb border that matches the gothic theme perfectly
  • + High text legibility for the primary title and date
  • Includes extraneous gibberish text in the event details section
  • The overall look is a bit more modern/digital than 'vintage dark parchment'

Wan 2.7

  • + Perfectly captures the vintage parchment and illustrative poster aesthetic
  • + Flawless text rendering across all fields with no gibberish
  • + Rich composition with extra thematic elements like ravens and skulls
  • The lighting is a bit flatter and more like an illustration than cinematic
  • The jack-o-lantern is placed inside a sub-frame rather than being central to the whole poster

Verdict: Wan 2.7 is the clear winner here for its exceptional ability to handle all text fields accurately while perfectly capturing the 'vintage parchment' aesthetic requested. While FLUX.1 Kontext [pro] offers more moody, cinematic lighting, it fails on text accuracy by adding a line of gibberish in the middle of the event details.

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 [pro]
Before After
Wan 2.7

AI Judge Analysis

FLUX.1 Kontext [pro]

  • + Successfully added a thick, full head of hair that matches the beard texture.
  • + Effectively preserved the clothing and background context.
  • Substantially altered the face and forehead structure, making the man look younger and like a different person.
  • The hairline integration at the temples looks slightly unnatural and disconnected from the original ear placement.

Wan 2.7

  • + Excellent source preservation, keeping the facial identity, skin texture, and skull shape nearly identical to the original.
  • + The hair texture and style look extremely natural and appropriate for the age and character of the man.
  • Minor loss of detail in the background vegetation compared to the original, though barely noticeable.

Verdict: Wan 2.7 performed significantly better on this task because it followed the instruction to preserve facial features, whereas FLUX.1 Kontext [pro] essentially generated a new face that merely resembled the original. Wan 2.7 successfully integrated a realistic, age-appropriate hairstyle while maintaining the man's identity, lighting, and environmental details.

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 [pro]
Wan 2.7

AI Judge Analysis

FLUX.1 Kontext [pro]

  • + Excellent 3D cartoon typography that feels integrated into the scene.
  • + Effective use of PBR materials with a tactile pearl-like rice texture.
  • + Perfect adherence to the single raised diorama base requirement.
  • The flag icon is stylized as a square piece of paper rather than a standard flag.
  • The rice grains are oversized, appearing more like bubbles than rice.

Wan 2.7

  • + High variety of sushi types modeled with great detail.
  • + Very clean layout and professional graphic design for the flag and text.
  • + Accurate representation of sushi rice textures and garnish.
  • The text is not 'large bold' relative to the scale, appearing smaller and more like a logo in the corner.
  • The shrimp sushi's head/eye detail is slightly unsettling in a cartoon style.

Verdict: FLUX.1 Kontext [pro] creates a more cohesive 3D miniature scene with playful, chunky typography that fits the 'cartoon' prompt perfectly. Wan 2.7 provides a much better variety of sushi and superior realism in materials, but the composition feels more like a product render than a stylized 3D diorama. FLUX.1 Kontext [pro] is the winner for better matching the isometric miniature aesthetic and font requirements.

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 [pro]
Wan 2.7

AI Judge Analysis

FLUX.1 Kontext [pro]

  • + Excellent preservation of the source subject's clothing and pose.
  • + Translates the facial features into a stylized illustration while maintaining recognizable identity.
  • Completely ignored the prompt instructions regarding the job, dogs, and hockey.
  • No attempt at a caricature format beyond a simple cartoon filter.

Wan 2.7

  • + Successfully incorporated all prompt elements: TV anchor blazer, newsroom background, dogs, and hockey gear.
  • + High level of creativity with humorous details like the dog in a hockey helmet and the tiny rink.
  • + Clearly understands the 'caricature' style with exaggerated expressions and set design.
  • Text in speech bubbles contains minor misspellings ('Rolee').
  • The face, while stylized, loses some of the specific likeness of the source image compared to model A.

Verdict: FLUX.1 Kontext [pro] failed the editing task entirely by ignoring all specific instructions about the profession, dogs, and hockey, simply recreating the original photo in a cartoon style. Wan 2.7 followed every part of the prompt, creating a humorous and busy scene that integrates all requested themes into a coherent caricature. While Wan 2.7 has a few minor text errors, it is the clear winner for actually performing the requested edit.

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 [pro]
Wan 2.7

AI Judge Analysis

FLUX.1 Kontext [pro]

  • + Excellent soft lighting and glow effects
  • + Highly detailed and fluffy fur textures
  • Failed to include a distinct bunny, creating a weird hybrid cat-bunny instead
  • The animals are sitting still rather than chasing or tumbling as requested

Wan 2.7

  • + Successfully included all four distinct animal species (puppy, kitten, bunny, fox)
  • + Captured the movement and action of chasing/tumbling
  • + Strong adherence to the 'dew sparkles' and 'god rays' lighting effects
  • The kitten's front paws look slightly anatomicaly awkward
  • The lighting is a bit harsh compared to the 'warm sunset' vibe of the first image

Verdict: While FLUX.1 Kontext [pro] produced a more aesthetically soft and professional photograph, it failed the prompt's count requirement by merging the kitten and bunny into one hybrid creature. Wan 2.7 followed the prompt much more accurately, depicting all four animals in active motion with clear species differentiation, making it the more successful image for this specific challenge.

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 [pro]
Wan 2.7

AI Judge Analysis

FLUX.1 Kontext [pro]

  • + Excellent adherence to the Studio Ghibli art style with characteristic line work and facial features.
  • + Perfectly captures the hand-painted watercolor texture requested.
  • + Accurately replicates the composition and poses of the iconic meme while stylizing them.
  • The character in the foreground loses some of the original's blurring/depth of field effect.

Wan 2.7

  • + Good preservation of the original facial likenesses compared to the source image.
  • + Soft, pleasing watercolor textures and pastel color palette.
  • + Maintains the structural integrity of the background elements well.
  • The art style is more generic Western watercolor than the specific Studio Ghibli anime style requested.
  • The man's hair is rendered with too much realistic detail for the Ghibli aesthetic.

Verdict: FLUX.1 Kontext [pro] is the clear winner as it successfully translated the image into the specific Studio Ghibli art style requested, including the iconic facial geometry and simplified line work. Wan 2.7 created a high-quality watercolor illustration that preserved the original actors' likenesses better, but it failed to capture the specific aesthetic hallmarks of a Ghibli production.

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 [pro]
Before After
Wan 2.7

AI Judge Analysis

FLUX.1 Kontext [pro]

  • + Excellent adherence to the hair motion request
  • + Preserves the subject's facial identity perfectly
  • + Realistic interaction between the added leaves and the depth of the scene
  • The leaf rendering is slightly sparse compared to Model B

Wan 2.7

  • + Strong presence of flying leaves throughout the scene
  • + Good preservation of the background and dog
  • + Dynamic hair motion effectively captures the wind direction
  • Slight alteration of the woman's facial features and eye alignment
  • Noticeable artifacts where hair meets the background

Verdict: Both models successfully interpreted the prompt, but FLUX.1 Kontext [pro] is the superior choice because it preserved the exact identity and facial structure of the subject from the source image. While Wan 2.7 added a nice volume of leaves, it slightly modified the woman's face and created minor clarity issues around the hair edges.

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 [pro]
Wan 2.7

AI Judge Analysis

FLUX.1 Kontext [pro]

  • + Perfect adherence to the minimalist vector style requested.
  • + Follows the text prompt exactly including the accent mark in 'Caffè'.
  • + Subtle texture gives it a high-quality letterpress feel.
  • Includes a minor typo 'EEST' instead of 'EST' on the banner.

Wan 2.7

  • + Excellent layout composition with a professional emblem seal.
  • + Accurate text rendering for both name and date.
  • + Good use of the warm brown and cream color palette.
  • Misspelled the name as 'Florion' instead of 'Florian'.
  • The inclusion of stars and wheat makes it less 'minimalist' than requested.
  • The cloche handle is slightly off-center.

Verdict: FLUX.1 Kontext [pro] captured the 'minimalist' and 'vector emblem' aesthetic much better, though it suffered from a small typo in the establishing date. Wan 2.7 created a more complex, ornate badge that looks professional but misspelled the primary brand name 'Florian' as 'Florion' and missed the requested minimalism.

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 [pro]
Wan 2.7

AI Judge Analysis

FLUX.1 Kontext [pro]

  • + Excellent vector illustration style for the main rocket.
  • + Captures the high-contrast navy and white palette well.
  • + Good use of subtle gradients in the lunar surface.
  • Nonsensical diagram logic with Saturn-like rings around the Earth and Moon.
  • Contains major text errors and mislabeled steps.
  • Fails to follow the requested 6-step infographic structure.

Wan 2.7

  • + Follows the 6-step chronological sequence perfectly.
  • + Accurately represents NASA-inspired icons and typography.
  • + Includes relevant supplementary details like mission dates and crew names.
  • Minor spelling errors such as DESCRIPT instead of DESCENT.
  • Iconography for the lunar module is slightly abstract.
  • Small typo in Tranquility Base (Tranquiliry).

Verdict: Wan 2.7 significantly outperforms FLUX.1 Kontext [pro] by adhering to the complex multi-step infographic prompt and maintaining logical consistency. While FLUX.1 Kontext [pro] produced a high-quality illustration, its failure to organize the steps and its addition of scientific inaccuracies (like rings on Earth) makes it a poor infographic. Wan 2.7 provides a complete, readable, and well-organized vertical layout that fulfills the educational intent of the prompt.

Next steps

Explore each model