Head to head
Esc

Models · slot A

to navigate to pick

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

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

FLUX.1 Kontext [max]

23.7 arena score

#23 of 62 in Text-to-Image

Skill signature · Text-to-Image

Wan 2.5 (Preview)

23.4 arena score

#27 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.1 Kontext [max]

0.0%

win rate

Ties

0.0%

Wan 2.5 (Preview)

100.0%

win rate

0.0% 0.0% ties 100.0%
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 [max]
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.1 Kontext [max]

  • + Excellent depiction of glass refraction and reflections
  • + Highly realistic lighting and shadows on the wooden surface
  • + Perfect adherence to all spatial requirements
  • The sphere has a slightly textured/glittery appearance rather than a smooth finish

Wan 2.5 (Preview)

  • + Strong composition and vibrant color palette
  • + Good focus and depth of field
  • + Accurate representation of the requested objects
  • The glass cube has physically impossible geometry where the book rests on the top edge
  • Contains excessive floating dust particles/artifacts in the air

Verdict: FLUX.1 Kontext [max] produced a superior image with highly realistic ray-tracing of the glass cube and consistent lighting. Wan 2.5 (Preview) managed the colors well but struggled with the structural integrity of the glass cube's edges and introduced distracting digital artifacts.

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 [max]
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.1 Kontext [max]

  • + Excellent handling of lighting and reflections on the wet pavement.
  • + Realistic skin textures and clothing folds.
  • + Captures a gritty, cinematic atmosphere that feels like a genuine candid photo.
  • The anatomy of the bicycle is a bit confused, with the chain and frame merging strangely.
  • Rain effects appear as heavy vertical streaks that can look digital.

Wan 2.5 (Preview)

  • + Excellent depiction of an elderly Japanese man with realistic facial features.
  • + Strong mechanical detail with actual tools on the ground.
  • + Accurate shallow depth of field and beautiful bokeh in the background.
  • The bicycle kickstand and rear assembly have some structural clipping issues.
  • The lighting on the man's shirt feels a bit flat compared to the dramatic background.

Verdict: Both models followed the prompt well, but Wan 2.5 (Preview) produced a more convincing subject and captured the 'Japanese' ethnicity more accurately than FLUX.1 Kontext [max]. While FLUX.1 Kontext [max] had superior atmospheric 'grit' and reflection quality, Wan 2.5 (Preview) provided a cleaner composition with logical props like tools, making it the more coherent image overall.

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 [max]
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.1 Kontext [max]

  • + Exceptional skin texture and facial detail
  • + Ornate engraving on the armor is intricate and clean
  • + The glowing eyes provide a strong fantasy paladin aesthetic
  • Missed the request for beads in the hair
  • The 'battle-worn' aspect is very subtle, lacking visible scars or dirt

Wan 2.5 (Preview)

  • + Perfect adherence to all prompt elements including beaded braids, scars, and specific clothing layers
  • + Excellent rendering of weathered leather and frayed cloth
  • + Includes the physical torch, emphasizing the warm light source
  • Face lacks the ultra-high-resolution skin pore detail seen in the competitor
  • The engraving on the armor is slightly less delicate than in Model A

Verdict: While FLUX.1 Kontext [max] produces a striking and high-fidelity portrait with superior skin textures, Wan 2.5 (Preview) captures the essence of the prompt much more accurately. Wan 2.5 successfully includes the specific beads, visible scarring, and detailed layers of leather and cloth that define the 'battle-worn' look requested.

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 [max]
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.1 Kontext [max]

  • + Excellent photographic quality and realistic food rendering
  • + Professional and balanced layout structure
  • + Clean white space usage typical of high-end casual dining
  • Failed to include a diverse variety of food, showing mostly pizza
  • Mixed use of fonts including a script style that wasn't requested

Wan 2.5 (Preview)

  • + Strong adherence to the requested grid layout containing specific sections
  • + Successfully included different food items for appetizers, pizza, and mains
  • + Better use of vibrant color accents as requested
  • Text rendering is messy and nonsensical
  • Food photography looks slightly more artificial/CG compared to Model A

Verdict: Wan 2.5 (Preview) followed the structural instructions much better by creating distinct sections for appetizers, pizza, and mains with a variety of food types, whereas FLUX.1 Kontext [max] mostly showed multiple variations of pizza. However, FLUX.1 Kontext [max] produced much higher quality, realistic food photography and a more polished layout despite the lack of variety.

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 [max]
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.1 Kontext [max]

  • + Excellent photographic texture on the meat patty and fresh vegetables.
  • + Accurate rendering of the requested price text with a clean, professional font style.
  • + Strong sense of scale and presence for the central burger.
  • Failed the 'exploded burger' requirement; the main burger is intact while separate bun halves orbit it.
  • Missing the 'starburst' element for the price, placing it in a plain ember area instead.
  • Text rendering is slightly less creative than the competitor.

Wan 2.5 (Preview)

  • + Perfectly captured the 'exploded burger' layout with vertically separated components.
  • + Successfully integrated all text elements including the fiery starburst for the price.
  • + Creative typography with the 'MAGIC BURGER' title appearing to drip like molten sauce or cheese.
  • The '€6.99' text is slightly less polished in its integration compared to the top title.
  • The meat patty texture is a bit more generic compared to the high-end photorealism of the other model.

Verdict: Wan 2.5 (Preview) provided a much better interpretation of the 'exploded' concept, showing clear separation of all burger components as requested. While FLUX.1 Kontext [max] has superior photorealistic textures on the food itself, it failed to explode the layers and missed the starburst requirement, making Wan 2.5 (Preview) the more accurate and dynamic advertisement.

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 [max]
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.1 Kontext [max]

  • + Excellent text rendering with no spelling errors.
  • + Realistic chalk texture with smears on the board and varying pressure in the strokes.
  • + Full adherence to all requested menu items and prices.
  • The 'elegant cursive' request for the title was not fully met, as it is a print/script hybrid.

Wan 2.5 (Preview)

  • + Dynamic angle and composition with a nice shallow depth of field for the background.
  • + Natural chalk texture and believable handwriting variations.
  • Missing the word 'Herbs' from the second menu item.
  • Repeating the price '$9' twice on the cookie item.
  • Text at the bottom becomes slightly illegible and cramped toward the right edge.

Verdict: FLUX.1 Kontext [max] produced a much more accurate result, following the text prompt perfectly without any spelling or price errors. While Wan 2.5 (Preview) offered a more cinematic photographic angle, it failed on several text details including missing words and duplicated price tags.

The Reversed Rodeo

Text-to-Image

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

FLUX.1 Kontext [max]
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.1 Kontext [max]

  • + Excellent anatomical clarity of the horse in white lighting
  • + High-quality texture on the space suit
  • + Clean composition with subtle lens flare
  • Failed the specific spatial instruction (horse on top of astronaut)
  • The horse is missing space gear which breaks the internal logic of the prompt's surrealism

Wan 2.5 (Preview)

  • + Dynamic composition with a sense of motion
  • + Vibrant colors and detailed background nebula
  • + Realistic leather and fabric textures
  • Failed the specific spatial instruction (horse on top of astronaut)
  • Artifacts in the dust/debris area at the bottom
  • A leg appears to be emerging awkwardly from the dust

Verdict: Both models failed the specific prompt instruction to place the 'horse on top' of the astronaut, instead providing the standard 'astronaut on horse' trope. FLUX.1 Kontext [max] provides a cleaner, more realistic image with better lighting, whereas Wan 2.5 (Preview) is more visually busy and has some minor artifacts in the foreground element.

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 [max]
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.1 Kontext [max]

  • + Excellent photorealistic fur texture and lighting
  • + Captures a professional, calm expression on the capybara
  • + High quality cinematic depth of field
  • The passenger is holding a phone to her ear like a call instead of 'looking at her phone'
  • The capybara's paw placement on the wheel is slightly awkward and less visible

Wan 2.5 (Preview)

  • + Perfect adherence to the passenger's expression and action (looking at her phone)
  • + Shows both paws clearly on the steering wheel as requested
  • + Excellent composition showing both the interior and exterior NYC environment
  • Text on the taxi sign is garbled/nonsensical
  • The capybara's paws look slightly more like human hands in texture than animal paws

Verdict: Both models performed exceptionally well, but Wan 2.5 (Preview) takes the lead by adhering more strictly to the prompt details, specifically the businesswoman's bored expression while looking at her phone and the clear placement of both paws on the wheel. FLUX.1 Kontext [max] produced a more aesthetically pleasing and photorealistic capybara, but failed to show the passenger actually looking at her phone.

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 [max]
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.1 Kontext [max]

  • + Excellent typography style that matches the gothic aesthetic
  • + Atmospheric and moody lighting that feels cinematically dark
  • + Intricate spiderweb border is well-integrated into the frame
  • The date contains redundant commas (30, 10, 2026)
  • Repetitive location text at the bottom
  • The scroll banner is slightly broken/fragmented around the edges

Wan 2.5 (Preview)

  • + Perfect text rendering with high legibility and no spelling errors
  • + Followed the small scroll banner instruction very accurately
  • + Excellent use of the thorns and webs border requested in the prompt
  • Lighting is a bit too bright and vibrant for a 'dark parchment' request
  • The pumpkin eyes have some slightly messy internal flame artifacts

Verdict: Wan 2.5 (Preview) produced a superior invitation overall, following every text instruction perfectly and including all requested decorative elements like thorns and the scroll banner. While FLUX.1 Kontext [max] captured the 'moody' and 'dark' atmosphere better, its text formatting was messy with redundant commas and repeated lines.

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 [max]
Before After
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.1 Kontext [max]

  • + Excellent addition of thick, textured hair.
  • + Maintains the facial expression and overall lighting accurately.
  • Significantly alters the person's face, specifically narrowing the eyes and changing the bridge of the nose.
  • The hair looks slightly like a wig due to the very uniform texture at the hairline.

Wan 2.5 (Preview)

  • + Excellent source preservation of facial features, head shape, and background.
  • + Realistic hair texture and natural integration with the sideburns.
  • + Very natural-looking hairline.
  • Small artifact where the hair meets the top edge of the glasses frames.

Verdict: Wan 2.5 (Preview) is the clear winner as it successfully adds the requested hair while perfectly preserving the subject's identity and facial structure. FLUX.1 Kontext [max] provides a good head of hair but fails significantly at source preservation, noticeably changing the subject's eyes and nose during the process.

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 [max]
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.1 Kontext [max]

  • + Excellent 3D miniature styling with soft, toy-like textures.
  • + Clear, well-rendered text font that complements the cartoon aesthetic.
  • + Includes more detailed sushi 3D models like wasabi, soy sauce, and chopsticks.
  • Missed the small flag icon request.
  • The plate is slightly off-center on the diorama base.

Wan 2.5 (Preview)

  • + Accurately included the flag icon as requested.
  • + Strong adherence to the 'isometric' perspective on a circular diorama base.
  • + High-clarity lighting and very clean textures.
  • Text rendering is a bit more generic compared to the 3D-styled text in Image A.
  • The '45° top-down' angle is slightly lower than what is traditionally expected for isometric views.

Verdict: Both models followed the prompt well, but Wan 2.5 (Preview) adhered more strictly to all prompt elements by including the Japanese flag icon. FLUX.1 Kontext [max] delivered a more cohesive '3D cartoon' aesthetic with better secondary assets like chopsticks, but Wan 2.5 (Preview) is the winner for better composition and completing all text/icon instructions.

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 [max]
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.1 Kontext [max]

  • + Excellent preservation of the subject's outfit from the source image.
  • + Strong caricature style with exaggerated features that still resemble the original person.
  • + The dog and newsroom background are well-integrated into the scene.
  • The hockey stick is awkward and poorly rendered as a floating element in the background.
  • The addition of glasses was not requested and changes the subject's likeness.

Wan 2.5 (Preview)

  • + Successfully incorporates all prompt elements including multiple dogs, an anchor desk, and a clear hockey theme.
  • + High quality caricature of the face that maintains a very strong likeness to the source.
  • + Great composition that clearly identifies the profession and hobbies.
  • The microphone is slightly detached from the hand's grip.
  • The subject's body is very small in proportion to the head, border-lining on bobblehead style rather than a traditional caricature.

Verdict: Wan 2.5 (Preview) provided a much more complete and cohesive interpretation of the prompt, including a clear news desk, multiple dogs, and a well-rendered hockey stick and screen. While FLUX.1 Kontext [max] did a better job of preserving the specific clothing from the source, it failed to integrate the hockey element effectively, resulting in a floating stick that lacks context.

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 [max]
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.1 Kontext [max]

  • + Excellent fur texture and soft lighting coherence
  • + Captures an adorable, cohesive scene with natural-looking anatomy
  • + Strong interpretation of a 'lush wildflower meadow' with a dreamy bokeh
  • The animals are sitting still rather than 'chasing and tumbling' as requested
  • Butterflies appear a bit repetitive in color and shape

Wan 2.5 (Preview)

  • + Successfully captures the action of 'chasing and tumbling' with dynamic poses
  • + Strong adherence to 'dew sparkles' and clear 'god rays'
  • + Very distinct butterfly rendering
  • The fox's eyes appear unnaturally bright and slightly demonic
  • Small anatomical errors, such as the kitten's front left paw looking distorted
  • Floating dew droplets look a bit like digital artifacts rather than natural moisture

Verdict: Wan 2.5 (Preview) better followed the action-oriented parts of the prompt, showing the animals in motion, but suffered from anatomical uncanny valley effects and jarring eye rendering on the fox. FLUX.1 Kontext [max] produced a much more polished, photorealistic masterpiece with superior fur textures and lighting, despite the animals being in a static pose rather than chasing. Although Wan 2.5 is more dynamic, FLUX.1 Kontext [max] is the better image due to its consistent high quality and lack of disturbing artifacts.

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 [max]
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.1 Kontext [max]

  • + Excellent hand-painted texture that mimics watercolor and paper grain.
  • + Stronger Ghibli art style with characteristic line work and facial features.
  • + Accurately replicates the character expressions and poses from the original meme.
  • The woman in the foreground has slight blurriness compared to the rest of the image.
  • The background is slightly less detailed than Model B's.

Wan 2.5 (Preview)

  • + Beautiful dreamy lighting and atmospheric effects like floating leaves.
  • + Very clean digital illustration with smooth gradients.
  • + Good preservation of character likeness while translating to anime style.
  • Feels more like modern digital anime than the specific Ghibli 'hand-painted' request.
  • The man's expression is slightly more neutral than the original 'distracted' look.

Verdict: Both models did an exceptional job of preserving the composition and characters of the original meme while translating it into an illustration. FLUX.1 Kontext [max] wins because it better captured the specific 'hand-painted' textures and watercolor aesthetic characteristic of Studio Ghibli, whereas Wan 2.5 (Preview) produced a higher-fidelity but more generic modern digital anime look.

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 [max]
Before After
Wan 2.5 (Preview)
0% wins 0% ties 100% wins

AI Judge Analysis

FLUX.1 Kontext [max]

  • + Successfully added both blowing hair and flying leaves.
  • + Maintained the subject's pose and character likeness well.
  • Introduced a significant artifact with a third hand appearing near the dog's head.
  • The flying leaves are very small and sparse compared to the background.

Wan 2.5 (Preview)

  • + Excellent hair-blowing effect that feels natural and dynamic.
  • + Leaves are more visible and vibrant, enhancing the lively feel.
  • + Better preservation of the original pose and anatomy without adding extra limbs.
  • The leaf rendering is slightly painterly/flat compared to the realistic background.

Verdict: Both models followed the instructions well, but FLUX.1 Kontext [max] failed significantly on source preservation by generating a third hand on the right side of the image. Wan 2.5 (Preview) produced a higher quality hair effect and added the requested leaves while keeping the rest of the image intact and anatomically correct.

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 [max]
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.1 Kontext [max]

  • + Excellent typography with a period-accurate serif font and correct accent mark
  • + Strong minimalist vector aesthetic suited for a logo
  • + Perfect adherence to the requested warm brown and cream color palette
  • The 'Est.' banner is slightly less detailed than Model B's

Wan 2.5 (Preview)

  • + Elegant layout with well-integrated banners
  • + Smooth, professional vector shading on the cloche dome
  • + Authentic vintage paper texture background
  • Missed the accent mark ('è') in the typography
  • The overall look leans more towards an illustration than a minimalist logo

Verdict: Both models followed the prompt details closely, including the cloche and 'Est. 1720' text. FLUX.1 Kontext [max] is the winner because it correctly included the accent mark in 'Caffè' and produced a cleaner, more minimalist logo design that aligns better with the 'vector emblem' part of the prompt. Wan 2.5 produced a beautiful image, but failed on the specific character detail and was slightly less minimalist.

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 [max]
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.1 Kontext [max]

  • + Artistically interesting composition with a scenic lunar foreground.
  • + Captures the muted NASA-inspired color palette effectively.
  • + Detailed illustration of the lunar module on the surface.
  • Nonsensical infographic flow with text labels pointing to incorrect objects (e.g., Earth labeled as 'Moon').
  • Severe spelling errors in labels such as 'LAARTH' and 'MODULLE'.
  • Includes a random ringed planet (Saturn) that was not part of the requested Apollo 11 steps.

Wan 2.5 (Preview)

  • + Highly accurate infographic structure with a logical flow from step 1 to 6.
  • + Excellent text rendering for steps and the crew members' names.
  • + Adheres strictly to the flat-vector style and Saturn V icon request.
  • The astronaut icons look somewhat inconsistent, particularly the one wearing a helmet/hat.
  • Less use of the requested red in the palette compared to Model A.

Verdict: Wan 2.5 (Preview) produced a superior infographic that is actually functional, with readable text, logical flow, and correct labeling of the Apollo mission stages. FLUX.1 Kontext [max] failed significantly on coherence, mislabeling the Earth as the moon and including nonsensical satellite/planet elements that cluttered the design.

Next steps

Explore each model