Head to head
Esc

Models · slot A

to navigate to pick

FLUX.2 [dev] Flash fal Wan 2.5 (Preview) Alibaba

Settled by community votes across 19 shared challenges, with an AI judge weighing in on each.

FLUX.2 [dev] Flash

27.1 arena score

#5 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.2 [dev] Flash

0%

win rate

Ties

0%

Wan 2.5 (Preview)

0%

win rate

Shared challenges 19

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.2 [dev] Flash
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [dev] Flash

  • + Excellent adherence to the 'plant behind the cube visible through the glass' instruction
  • + Very realistic glass and water-like refractions
  • + Spine of the red book features legible-looking texture and gold leaf details
  • The sphere is slightly towards the front rather than perfectly centered

Wan 2.5 (Preview)

  • + Strong directional lighting and cast shadows
  • + Vibrant colors and high contrast
  • The plant is mostly above/behind the cube but the visual transparency through the glass is less convincing
  • Floating dust/artifact particles are a bit excessive
  • The red book looks slightly more weathered compared to a cohesive modern set

Verdict: FLUX.2 [dev] Flash delivered a more technically accurate and photorealistic result, particularly in how the glass cube distorts the green plant positioned behind it. Wan 2.5 (Preview) produced a visually striking image with great light and shadow, but it felt slightly more digital and struggled with the refractive realism seen in the other model.

Man and Car in California

Editing
Edit instruction

“Make a photo of the man driving the car down the California coastline”

Source
FLUX.2 [dev] Flash
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [dev] Flash

  • + Excellent preservation of the subject's appearance, clothing, and hairstyle.
  • + Realistic interior merging that keeps the car's aesthetic from the source.
  • + High cinematic quality with natural lighting and depth of field.
  • The car is in a right-hand drive configuration, which is unusual for a US coastline setting.
  • The steering wheel logo doesn't perfectly match the Rolls Royce branding from the source.

Wan 2.5 (Preview)

  • + Successfully places the car in a convincing California coastline environment.
  • + Preserves the full exterior of the original car faithfully.
  • + Captures motion blur on the road and wheels effectively.
  • The man is barely visible and loses almost all characteristic detail from the source image.
  • The subject is shrunken and lacks the clothing/features of the provided person.

Verdict: FLUX.2 [dev] Flash is the clear winner as it successfully merges the two source images, keeping the specific man's face, hair, and clothing intact while placing him inside the car. Wan 2.5 (Preview) ignores the specific identity of the man, rendering a generic small figure in the driver's seat that does not resemble the source subject.

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.2 [dev] Flash
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [dev] Flash

  • + Excellent depiction of motion blur from passing cars
  • + High realism in skin textures and clothing fabrics
  • + Accurate representation of an 'imperfect' street photography aesthetic
  • The man's hands are slightly merged with the bicycle frame
  • The bicycle's rear structure is physically impossible

Wan 2.5 (Preview)

  • + Beautiful reflections on the wet pavement
  • + Clean, high-quality subject focus
  • + Strong cinematic lighting and color
  • Lacks the requested motion blur from passing cars
  • Background cars look too static and clean for the prompt
  • Minor anatomical issues with the fingers on the bike handle

Verdict: FLUX.2 [dev] Flash followed the complex prompt requirements much better, specifically capturing the 'motion blur from passing cars' and the 'imperfect framing' of a candid street photo. Wan 2.5 (Preview) produced a higher-quality aesthetic image, but it missed several key technical descriptors and felt more staged than candid.

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.2 [dev] Flash
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [dev] Flash

  • + Excellent depiction of multiple colorful beads in thin braids.
  • + Highly detailed engraving on the plate armor with realistic metal texture.
  • + Strong adherence to the 'torchlight' prompt with symmetrical background lighting.
  • The scars look a bit more like surface blood/paint than actual physical scarring.

Wan 2.5 (Preview)

  • + Fantastic texture on the frayed cloth underlayer and leather stitching.
  • + Stronger 'battle-worn' appearance with grimy skin and realistic redness around the eyes.
  • + Beautiful lighting contrast across the face from the torch.
  • The beads in the hair look a bit like shiny bubbles or metal spheres rather than variety beads.
  • The armor engraving is slightly less intricate than Image A.

Verdict: FLUX.2 [dev] Flash produces a very clean, symmetrical, and high-fidelity image with particularly intricate armor engraving and accurate hair beads. However, Wan 2.5 (Preview) captures a more visceral 'battle-worn' atmosphere through superior textures on the cloth and more realistic grime and facial fatigue, making it feel more like a character in a story.

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.2 [dev] Flash
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [dev] Flash

  • + Excellent grid layout that creates a structured, professional feel.
  • + Vibrant color-coded borders that add a modern flair to the design.
  • + Good adherence to the specific headers requested.
  • The food photos are repetitive, showing multiple very similar pizzas under different categories.
  • Text and spelling are highly garbled, even for common words.

Wan 2.5 (Preview)

  • + Features a wider variety of food photography that better represents a full menu.
  • + Cleaner minimalist aesthetic with more white space and professional alignment.
  • + Better font clarity for the main headers like 'Pizza' and 'Mains'.
  • The grid is slightly inconsistent as it merges headers and photos into vertical columns.
  • Missing price tags which were present in Image A.

Verdict: Wan 2.5 (Preview) produced a superior design by offering a diverse range of high-quality food photography and a cleaner, more minimalist layout that feels like a real menu. While FLUX.2 [dev] Flash had better structural elements like price columns and color coding, the repetitive pizza images and messy text rendering make it less effective overall.

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.2 [dev] Flash
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [dev] Flash

  • + Excellent photographic realism in the burger textures and lighting
  • + Highly accurate text rendering with a consistent glowing fire effect
  • + Well-composed starburst sticker that integrates naturally with the scene
  • The 'exploded' effect is slightly compact compared to Model B

Wan 2.5 (Preview)

  • + Dynamic 'shattered' composition with ingredients spread further apart
  • + Creative dripping lava/fire effect applied to the main title text
  • + Vibrant colors and strong sense of motion with flying embers
  • Slightly less realistic burger textures than Model A
  • Text is somewhat warped and includes minor artifacts around the 'G' and 'R'

Verdict: Both models followed the prompt exceptionally well, producing high-impact advertising visuals. FLUX.2 [dev] Flash is the winner due to its superior photographic detail on the burger and cleaner, more professional text rendering, whereas Wan 2.5 (Preview) has a slightly more exciting composition but suffers from minor text distortion.

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.2 [dev] Flash
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [dev] Flash

  • + Excellent chalk texture with realistic dusty smudging on the board surface.
  • + Perfect text accuracy, including the complex third menu item that was cut off in the prompt.
  • + Highly realistic handwriting style that looks authentically handwritten rather than templated.
  • The 'Today's Specials' title is less 'elegant cursive' and more of a stylized print compared to the prompt's request.

Wan 2.5 (Preview)

  • + Strong cursive elements in the title text.
  • + Good sense of depth and perspective with the chalkboard frame.
  • The text looks more like a digital brush font than actual chalk on a board.
  • Missing the word 'Herbs' in the second item (renders 'Lemon & $28').
  • Inconsistent chalk texture, appearing too smooth and solid in some letters.

Verdict: FLUX.2 [dev] Flash is the clear winner as it successfully rendered all text accurately despite the prompt being cut off, while maintaining a very realistic chalk texture. Wan 2.5 (Preview) failed on the text accuracy for the second menu item and the text lacks the tactile, dusty quality of real chalk seen in FLUX.2.

The Reversed Rodeo

Text-to-Image

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

FLUX.2 [dev] Flash
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [dev] Flash

  • + Excellent anatomical details on the horse's head and mane
  • + Sophisticated cinematic lighting and a moody atmospheric color palette
  • + High level of detail in the astronaut's suit textures
  • Failed to follow the specific spatial instruction (horse on top of astronaut)

Wan 2.5 (Preview)

  • + Vibrant cosmic colors and dynamic composition
  • + Good sense of motion with the blurred foreground elements
  • + Clean rendering of the space suit and helmet reflections
  • Failed to follow the specific spatial instruction (horse on top of astronaut)
  • The back legs of the horse appear slightly distorted and blended poorly into the background

Verdict: Both FLUX.2 [dev] Flash and Wan 2.5 (Preview) failed the core challenge of the prompt, which was the surreal 'horse on top of the astronaut' arrangement, instead providing the standard astronaut-on-horse trope. FLUX.2 [dev] Flash is the preferred output due to its superior lighting, more realistic horse anatomy, and more cohesive cinematic atmosphere.

Outfit Transfer Challenge

Editing
Edit instruction

“Use Image 1 as the base person. Dress them in the exact elaborate outfit from Image 2 (including all layers, accessories, jewelry, and shoes). Carefully adapt the clothing to the body shape and pose in Image 1 while maintaining realistic fabric behavior, correct proportions, and perfect lighting/shadow matching. Keep the person’s exact face, hair, and background completely unchanged.”

Source
FLUX.2 [dev] Flash
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [dev] Flash

  • + Successfully captured the specific scarf and coat style from Image 2.
  • + Included more elaborate jewelry as requested by the prompt.
  • Catastrophic failure in facial rendering, creating a distorted, multi-faced artifact.
  • Failed to preserve the original person's face and hair as instructed.

Wan 2.5 (Preview)

  • + Successfully applied the coat and scarf with clean integration.
  • + Maintained high visual quality and coherent anatomy.
  • Completely failed to preserve the person from Image 1, replacing him entirely with the person from Image 2.
  • Ignored the instruction to keep specific skin features (vitiligo) and hair unchanged.

Verdict: Both models failed the core challenge of identity preservation. FLUX.2 [dev] Flash attempted to merge the images but resulted in a disturbing, distorted 'monster' face, while Wan 2.5 (Preview) produced a clean image but simply swapped the person out for the one in the second reference. Wan 2.5 is the preferred output only because it is a coherent image, whereas FLUX.2 produced a corrupted result.

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.2 [dev] Flash
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [dev] Flash

  • + Excellent adherence to the 'bored expression' prompt for the passenger
  • + Realistic lighting and texture on the capybara's fur
  • + Accurate depiction of a dark jacket and yellow cap as requested
  • The passenger appears to be in the front seat or middle, rather than clearly in the back seat
  • The taxi light on top of the car is partially obscured by the frame

Wan 2.5 (Preview)

  • + Strong composition with the passenger clearly in the back seat and the driver in front
  • + High level of detail on the car's exterior including raindrops and blurred Manhattan lights
  • + Paws are positioned naturally on the steering wheel
  • The female passenger's face is slightly blurry/low resolution compared to the driver
  • The steering wheel appears to be floating or disconnected from a dashboard

Verdict: Both models followed the complex prompt with high accuracy. FLUX.2 [dev] Flash captured the 'bored' emotion of the passenger much better, but Wan 2.5 (Preview) provided a superior composition by correctly placing the passenger in the back seat and creating a more immersive New York atmosphere with better background details.

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.2 [dev] Flash
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [dev] Flash

  • + Excellent text legibility and accuracy
  • + Atmospheric and cohesive color palette with a dark, moody feel
  • + Well-integrated border containing thorns, webs, and parchment elements
  • Includes some hallucinatory text/characters in the event details section
  • The jack-o-lantern rendering is a bit flat compared to the other model

Wan 2.5 (Preview)

  • + High visual quality with dynamic cinematic lighting inside the pumpkin
  • + Clean text rendering for both the title and the event details
  • + Beautiful scroll banner design and parchment texture
  • The parchment is a bit too bright for a 'dark parchment' request
  • The border feels slightly detached from the central circular composition

Verdict: Both models followed the prompt exceptionally well, producing high-quality invitations with correct text. FLUX.2 [dev] Flash captures the 'moody' and 'dark' atmosphere better, while Wan 2.5 (Preview) produces a more vibrant, polished image with superior lighting effects on the jack-o-lantern.

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.2 [dev] Flash
Before After
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [dev] Flash

  • + Excellent preservation of the original face, foreground, and background assets.
  • + High density and volume as requested in the prompt.
  • The hairline is overly straight and looks artificially stamped onto the forehead.
  • The hair texture is slightly generic and lacks fine, integrated flyaway strands.

Wan 2.5 (Preview)

  • + Features a very natural, integrated hairline with realistic skin-to-hair transitions.
  • + Superior hair texture with realistic sheen, waves, and individual hair detail.
  • Slightly alters the shape of the face/forehead area compared to the source.
  • Slightly less 'full' in terms of volume compared to the other model's interpretation.

Verdict: Both models successfully added hair while preserving the identity and surroundings of the subject. FLUX.2 [dev] Flash followed the request for 'thick' hair more literally with an afro-textured style, but Wan 2.5 (Preview) produced a significantly more realistic result with a natural hairline and better texture integration.

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.2 [dev] Flash
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [dev] Flash

  • + Excellent text rendering with clean, sharp typography.
  • + Higher level of detail in the food textures and wooden base.
  • + Accurate miniature diorama aesthetic with a realistic isometric perspective.
  • The lighting is a bit flat compared to the requested soft refined cartoon look.

Wan 2.5 (Preview)

  • + Vibrant, appealing cartoon-style lighting and soft textures.
  • + Clean and bold text presentation with a good flag icon.
  • + Strong adherence to the soft 3D cartoon style requested.
  • The perspective is closer to a low eye-level shot than a 45° top-down isometric view.
  • Text has slight font-weight inconsistencies in the word 'SUSHI'.

Verdict: FLUX.2 [dev] Flash perfectly captured the 45° isometric perspective and provided more detailed, realistic PBR-style textures for the rice and fish. While Wan 2.5 (Preview) produced a more appealing 'soft cartoon' aesthetic, it failed to provide the specific top-down isometric angle requested in the prompt.

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.2 [dev] Flash
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [dev] Flash

  • + Excellent preservation of the subject's facial features in a caricature style.
  • + High level of detail in the background including a full rink, audience, and TV monitors.
  • + Very creative integration of the dog and hockey themes with the anchor desk.
  • The hands on the desk are a bit small and generic compared to the head size.
  • The text 'TV SHOW' is slightly generic and plain.

Wan 2.5 (Preview)

  • + Successfully captures the requested themes in a clean, vector-style caricature.
  • + Preserves the subject's specific denim jacket from the source image.
  • + Good use of color and a balanced layout.
  • The facial resemblance is significantly weaker than Model A, appearing more like a generic cartoon woman.
  • The composition is less ambitious, using a simple flat background instead of an immersive environment.

Verdict: FLUX.2 [dev] Flash is the clear winner as it maintains a much stronger facial resemblance to the source image while fulfilling all caricature requirements. It creates a rich, detailed scene that blends the TV studio with a hockey rink, whereas Wan 2.5 (Preview) provides a more generic cartoon output with less environmental detail.

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.2 [dev] Flash
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [dev] Flash

  • + Excellent fur textures and lighting integration.
  • + Better species representation with natural features.
  • + Beautiful composition that captures a cohesive group moment.
  • The animals are more static/posing rather than 'chasing' and 'tumbling'.
  • Duplicate animals (two foxes and two rabbits) deviate from the singular list in the prompt.

Wan 2.5 (Preview)

  • + Successfully captures the movement and action of 'chasing'.
  • + Contains exactly one of each requested animal species.
  • + Vibrant lighting and dynamic depth of field.
  • The fox's eyes appear unnaturally glowing and stylized.
  • Floating water droplets look physically disconnected from the environment.
  • Artifacting on the cat's tail and the dog's right paw.

Verdict: Wan 2.5 (Preview) does a better job of following the specific action and counts within the instructions, capturing the sense of 'chasing'. However, FLUX.2 [dev] Flash produces a much more realistic image with superior fur textures and natural anatomy, making it more aesthetically pleasing despite the extra animals.

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.2 [dev] Flash
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [dev] Flash

  • + Excellent adherence to the 'hand-painted textures' and 'dreamy background' instruction.
  • + Maintains the compositions and facial expressions of the source image while transforming them into a soft aesthetic.
  • + Colors are beautifully muted and consistent with the requested pastel palette.
  • Changes the urban background to a meadow, which deviates from source preservation.
  • The pencil sketch lines might be a bit heavy for some interpretations of 'Ghibli'.

Wan 2.5 (Preview)

  • + Successfully captures a modern anime/Ghibli-lite art style.
  • + Preserves the street background from the source image more accurately than Model A.
  • + Clean lines and smooth coloring create a professional look.
  • The character in the red dress has a slightly distorted jawline.
  • Misses the specific 'hand-painted' and 'dreamy' texture request in favor of a flatter digital style.

Verdict: FLUX.2 [dev] Flash much more effectively captured the specific atmosphere and texture requested in the prompt, creating a truly dreamy, hand-painted Ghibli feel, even though it changed the background location. Wan 2.5 (Preview) provided a more accurate source preservation of the background but looked like a standard digital anime filter rather than a textured illustration. FLUX is the winner for its superior artistic execution and adherence to the 'nostalgic' and 'hand-painted' keywords.

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.2 [dev] Flash
Before After
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [dev] Flash

  • + Successfully added a large volume of flying leaves
  • + Hair is clearly blowing in the wind as requested
  • + Preserved the original composition and lighting well
  • The wind direction appears conflicting, with hair blowing outward from both sides symmetrically
  • Some leaves appear sharp and stationary rather than dynamic

Wan 2.5 (Preview)

  • + Wind effect on hair looks more natural and directional
  • + The leaves have a slight motion blur that feels more energetic
  • + Maintains high fidelity to the source image's character face
  • Added fewer leaves compared to the other model
  • The dog's tail loses some definition compared to the original

Verdict: Both models followed the instructions well, but Wan 2.5 (Preview) is slightly preferred for its more natural rendering of wind direction in the hair and the motion-blurred leaves which create a more 'dynamic' feel. FLUX.2 [dev] Flash added more leaves, but the hair blowing symmetrically outward felt less realistic than an actual breeze.

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.2 [dev] Flash
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [dev] Flash

  • + Perfect font rendering with a classic, high-end feel.
  • + Excellent use of texture and shading that matches the vintage aesthetic better.
  • + Strong composition where the cloche and banner feel integrated as a single emblem.
  • The steam graphic is a bit simplistic compared to the rest of the logo.

Wan 2.5 (Preview)

  • + Unique interpretation of the cloche as transparent glass, adding visual interest.
  • + Clean vector-style execution with high contrast.
  • + Follows all prompt elements including the specific date and accent marks.
  • The banner structure is a bit disorganized with overlapping pieces.
  • The transition between the main logo and the crumpled paper background is slightly harsh.

Verdict: Both models followed the prompt instructions very well, including correct spelling and accents. FLUX.2 [dev] Flash is the winner because its composition feels like a genuine professional logo with superior typography and better handling of the vintage 'subtle texture' request. Wan 2.5 (Preview) produced a good result, but the banner geometry is slightly awkward and messy compared to the polished look of FLUX.

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.2 [dev] Flash
Wan 2.5 (Preview)

AI Judge Analysis

FLUX.2 [dev] Flash

  • + Excellent adherence to the color palette requested.
  • + Detailed lunar module icons that accurately reflect various stages of descent and landing.
  • + Logical flow from top to bottom representing the progression of time.
  • Includes significant text artifacts and garbled letters under the Saturn V and near the Moon labels.
  • Redundant elements like two separate 'Lunar Orbit' sections and multiple 'Descent' labels create clutter.

Wan 2.5 (Preview)

  • + Features very clean, sharp typography with no spelling errors.
  • + The Saturn V and lunar module icons are high-quality, professional vector designs.
  • + Composition is more balanced and easier to read as a single infographic.
  • Fails to include distinct visual icons for the 'Descent' phase, leaving it as just text.
  • Includes a nonsensical shuttle-like craft pointing toward the landing site.

Verdict: Wan 2.5 (Preview) produces a much cleaner and more professional-looking infographic with perfect text rendering and high-quality vector assets, though it misses the specific 'Descent' icon. FLUX.2 [dev] Flash follows the instructional steps more closely but suffers from significant text corruption and a messy, repetitive layout. Wan 2.5 is the preferred choice for its visual clarity and design consistency.

Next steps

Explore each model