Black Forest Labs' compact, open-source image generation model with sub-second inference, optimized for production and near real-time applications with multi-reference support
Settled by community votes across 20 shared challenges, with an AI judge weighing in on each.
FLUX.2 [klein] 4B
#32 of 62 in Text-to-Image
Wan 2.7 Pro
#36 of 62 in Text-to-Image
Where the votes landed
FLUX.2 [klein] 4B
0%
win rate
Ties
0%
Wan 2.7 Pro
0%
win rate
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.”
AI Judge Analysis
FLUX.2 [klein] 4B
- + Excellent photographic realism in the glass texture and reflections.
- + Accurate interpretation of 'small blue sphere' relative to the cube size.
- + Soft, natural bokeh on the background plant.
- − The plant is barely visible through the cube glass, more so in the background surrounding it.
Wan 2.7 Pro
- + Perfect adherence to the instruction for the plant to be visible through the glass.
- + High level of detail on the wooden table texture and the red book.
- + Consistent lighting direction from the window.
- − The glass cube appears slightly greenish or thick-edged compared to a standard clear glass cube.
- − The sphere is a bit large relative to the prompt 'small sphere'.
Verdict: Both models followed the complex spatial prompt exceptionally well. FLUX.2 [klein] 4B produced a cleaner, more aesthetically pleasing photographic image, but Wan 2.7 Pro better captured the specific detail of the plant being seen through the transparency of the glass cube.
Man and Car in California
Editing“Make a photo of the man driving the car down the California coastline”
AI Judge Analysis
FLUX.2 [klein] 4B
- + Excellent preservation of the subject's identity, hairstyle, and clothing.
- + The car is kept very close to the source model with appropriate motion blur on the wheels.
- + Correct positioning of the driver in a right-hand drive car (common for Rolls-Royce models) or leaning out as requested.
- − The driver's proportions seem slightly large for the car seat.
Wan 2.7 Pro
- + Beautiful lighting and scenic coastline composition.
- + The car model is well-integrated into the environment.
- − Completely failed to preserve the man from the source image, replacing him with a different person.
- − The driver is barely visible and does not reflect the subject provided in the input.
Verdict: FLUX.2 [klein] 4B is the clear winner because it successfully followed the core instruction to use the specific man from the source image, maintaining his unique hairstyle and clothing. In contrast, Wan 2.7 Pro replaced the subject with a generic man, failing the identity preservation aspect of the image editing task.
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.”
AI Judge Analysis
FLUX.2 [klein] 4B
- + Excellent depiction of heavy rainfall and splashing ground effects.
- + Highly realistic skin textures and atmospheric lighting.
- + Beautiful shallow depth of field with realistic bokeh.
- − The bicycle anatomy is physically impossible, with the rear wheel appearing to pass through the frame.
- − The man's right hand position does not clearly show an act of repair.
Wan 2.7 Pro
- + Bicycle structure is much more coherent and believable than the competitor.
- + The pose clearly illustrates a 'repair' action as requested.
- + Good lighting and high-quality reflections on the wet asphalt.
- − Failed to include the requested 'motion blur' from passing cars.
- − The rain effect is very subtle compared to the 'light rain' prompt.
- − The background cars look static and parked rather than passing.
Verdict: FLUX.2 [klein] 4B wins on photographic atmosphere and skin realism, perfectly capturing the rain and motion blur requested, though it fails significantly on the structural logic of the bicycle. Wan 2.7 Pro produces a better-realized subject and bike, but feels more like a staged photo than a candid shot with motion blur. FLUX.2 [klein] 4B is preferred for its superior adherence to the 'cinematic but realistic' street photography aesthetic.
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.”
AI Judge Analysis
FLUX.2 [klein] 4B
- + Excellent symmetrical engraving on the breastplate
- + Clean and sharp facial features with distinct scars
- + Good implementation of the bokeh sparks in the background
- − The braids look a bit too neat and modern
- − The torchlight in the background has a slightly artificial, synthetic glow
- − Overall appearance looks a bit more like a cosplayer than a battle-worn soldier
Wan 2.7 Pro
- + Superb skin texture with realistic dirt and weathering
- + The hair braiding with beads is much more intricate and matches the medieval aesthetic
- + Dynamic lighting with believable reflections and atmospheric depth
- − The engraving on the pauldron looks slightly messy compared to the chest plate
- − The bokeh sparks are a bit large and potentially distracting
Verdict: Wan 2.7 Pro is the clear winner for its superior realism and atmospheric quality, capturing the 'battle-worn' aspect with impressive skin textures and gritty lighting. While FLUX.2 [klein] 4B produces a very clean and symetrical image, it lacks the cinematic weight and detail found in the hair and leather materials of the Wan 2.7 Pro output.
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.”
AI Judge Analysis
FLUX.2 [klein] 4B
- + Excellent grid layout with clear spacing
- + High-quality food photography and lighting
- + Strong adherence to the modern minimalist aesthetic
- − Nonsense text throughout the design
- − Section headings like MDAINS and FRAZZA are misspelled
- − The layout feels more like a flyer than a functional menu
Wan 2.7 Pro
- + Highly legible text with actual menu item names and prices
- + Includes functional elements like a QR code and address
- + Well-organized sections for Appetizers, Pizza, and Mains
- − Small spelling errors in dish names (e.g., Alferdo, Calarriri)
- − The food photos are small and slightly less detailed than Image A
- − The 'Mains' category contains a burger and nachos, which is slightly inconsistent
Verdict: Wan 2.7 Pro is the clear winner for this task as it produces a functional, realistic menu with legible text and accurate sections. While FLUX.2 [klein] 4B has slightly superior photo quality and a sleek aesthetic, its text is completely illegible and full of errors, making it unusable as a design template.
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.”
AI Judge Analysis
FLUX.2 [klein] 4B
- + High photorealistic texture on the burger bun and meat.
- + Excellent use of a starburst element for the price tag.
- + Clean, vibrant lighting and embers effect.
- − The main title text 'MAGIC BURGER' is significantly garbled and unreadable.
- − The burger is slightly tilted but not 'exploded' with suspended components as requested.
Wan 2.7 Pro
- + Perfectly follows the 'exploded' composition with individual suspended ingredients.
- + Excellent text rendering for 'MAGIC BURGER' and 'LIMITED TIME ONLY'.
- + Creatively integrates the fiery, glowing effect onto the lettering.
- − The 'starburst' for the price tag is more of a decorative seal than a dynamic burst.
- − The lettuce and tomato look slightly more like clip-art compared to the realistic burger in the other image.
Verdict: Wan 2.7 Pro is the clear winner as it accurately fulfilled the 'exploded burger' requirement and rendered the text perfectly, whereas FLUX.2 [klein] 4B failed to spell the product name and provided a standard burger stack. Wan 2.7 Pro also successfully applied the fiery theme to the typography as requested.
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.”
AI Judge Analysis
FLUX.2 [klein] 4B
- + Excellent realistic chalk texture with dusty smudges on the board.
- + Authentic handwritten aesthetic with natural variations.
- + Realistic frame and lighting.
- − Numerous spelling errors in almost every word (e.g., 'Truffel Musheram', 'Otrpous').
- − Text layout is a bit cramped at the top.
Wan 2.7 Pro
- + Perfect spelling and legibility for all requested menu items.
- + Very clean and organized composition.
- + Consistent handwriting style that still looks hand-rendered.
- − The 'chalk' textures on the letters look a bit like a digital brush rather than physical chalk.
- − The handwriting is almost too uniform to feel authentically human-written.
Verdict: Wan 2.7 Pro is the clear winner due to its perfect spelling and adherence to the menu text, whereas FLUX.2 [klein] 4B struggled significantly with character recognition and spelling. While FLUX.2 offered a more convincing physical chalk texture and environment, the legibility failures make it unusable for the specific prompt.
Pose & Character Mashup
Editing“Use Image 1 as the exact pose reference and Image 2 as the character reference. Recreate the person/character from Image 2 in the exact dynamic pose and body position from Image 1. Keep the exact face, hair, clothing style/details, and expression from Image 2. Match the lighting and environment of Image 1. The final image must show the character from Image 2 performing the precise action/pose from Image 1 with perfect anatomy and natural integration.”
AI Judge Analysis
FLUX.2 [klein] 4B
- + Excellent adherence to character reference, including the face, sunglasses, and scarf.
- + Successfully replicates the complex dynamic pose from the pose reference.
- + Matches the clothing style and color from the character reference (black sweater vs red).
- − The hair length is a mix of both models rather than strictly adhering to Image 2's shorter cut.
- − Visible artifacts on the hands and fingernails (red polish from Image 1 remains on a male character).
Wan 2.7 Pro
- + Perfectly preserves the environment and source image quality.
- − Completely failed the edit instruction by returning a slightly modified version of Image 1.
- − None of the character details from Image 2 were incorporated.
Verdict: FLUX.2 [klein] 4B successfully performed the complex task of merging the character from Image 2 into the pose of Image 1, including specific accessories like the scarf and sunglasses. Wan 2.7 Pro failed the task entirely, effectively ignoring the character reference and providing only a slightly altered version of the original pose image.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
AI Judge Analysis
FLUX.2 [klein] 4B
- + Excellent visual clarity and cinematic lighting across both characters.
- + Strong technical details in the horse's musculature and the astronaut's suit.
- − Completely failed the negative constraint/subverted prompt by placing the astronaut on top.
- − Minor artifacts where the horse's hooves meet the dust clouds.
Wan 2.7 Pro
- + Better sense of 'surrealism' with floating planets of varying sizes.
- + Clean composition with a clear view of the Earth's curvature below.
- − Failed the core prompt instruction of 'horse on top' of the astronaut.
- − One of the horse's legs is visually mangled/disconnected near the hoof.
Verdict: Both FLUX.2 [klein] 4B and Wan 2.7 Pro failed to follow the specific spatial instruction for the horse to be on top of the astronaut, instead defaulting to the cliché of an astronaut riding a horse. FLUX.2 [klein] 4B is slightly better due to its superior lighting and realistic rendering of the horse, whereas Wan 2.7 Pro includes a significant anatomical error in the horse's front leg.
Outfit Transfer Challenge
Editing“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.”
AI Judge Analysis
FLUX.2 [klein] 4B
- + Excellent adherence to the specific clothing items in Image 2, including the exact scarf pattern and coat style.
- + Near-perfect preservation of the face and hair details from Image 1.
- + Convincing placement of hands in pockets that respects the new garment geometry.
- − The model omitted the shirt from Image 2, leaving the chest bare.
- − Significant changes to the background elements, including the removal of the wooden pillar the man was leaning on.
Wan 2.7 Pro
- + Successfully preserved the original pose and background structure, including the wooden pillar.
- + Maintained the subject's unique skin patterns and facial features accurately.
- − Completely failed to use the outfit from Image 2, generating a gold-patterned blazer instead of a navy pea coat and plaid scarf.
- − The clothing details look like a flat texture overlay rather than realistic fabric layers.
- − Changed the blue jeans to black trousers.
Verdict: FLUX.2 [klein] 4B is the clear winner for its superior ability to replicate the specific items and patterns from Image 2, even though it failed to preserve the background and omitted the shirt. Wan 2.7 Pro preserved the background better but completely ignored the core instructional requirement to use the specific outfit provided, generating an entirely different set of clothes.
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.”
AI Judge Analysis
FLUX.2 [klein] 4B
- + Perfect composition showing the driver and passenger in the back seat as requested.
- + Realistic capybara features and fur texture.
- + Accurate rendering of a businessman look and a bored smartphone expression.
- − The vehicle interior looks more like a small vintage car than a standard NYC taxi.
- − The capybara's paws are a bit chunky and lack definition.
- − The perspective makes the car look unusually narrow.
Wan 2.7 Pro
- + Excellent photorealism in the skin and fabric textures.
- + The taxi driver cap style is more authentic to traditional uniforms.
- + High clarity and sharp details on the background lights.
- − The passenger is in the front seat instead of the back seat as requested.
- − The capybara has primate-like hands instead of paws.
- − The framing cuts off half of the passenger.
Verdict: FLUX.2 [klein] 4B followed the spatial instructions much better, correctly placing the passenger in the back seat and rendering actual capybara paws. While Wan 2.7 Pro has higher skin and texture detail, it failed the prompt's layout requirements by placing the passenger in the front seat and giving the animal human-like 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.”
AI Judge Analysis
FLUX.2 [klein] 4B
- + Atmospheric cinematic lighting with a moody color palette
- + Professional-grade texture on the jack-o-lantern and trees
- + Clean border integration with thorns and cobwebs
- − Major spelling errors in the main title
- − Inaccurate date and location spelling in the footer text
- − Text is crowded and overlaps the background elements poorly
Wan 2.7 Pro
- + Perfect text rendering for all requested fields
- + Intricate illustration style with highly detailed secondary elements
- + Clean, balanced composition that follows all layout instructions
- − Illustration feels more like a modern vector art style than a vintage parchment poster
Verdict: While FLUX.2 [klein] 4B captures a superior 'vintage gothic' mood and lighting, its failure to render any of the requested text correctly makes it unusable as an invitation. Wan 2.7 Pro followed every specific text instruction perfectly and maintained a very clean, organized layout, even if the art style is slightly more illustrative than cinematic.
Bald man challenge
Image Editing“Give the person a full, thick head of natural hair with realistic texture, density, and a natural hairline. Preserve facial features and lighting.”
AI Judge Analysis
FLUX.2 [klein] 4B
- + Excellent preservation of the original image's lighting and background
- + Seamless blend of the voluminous hair with the existing sideburns and beard
- + High level of detail in individual hair strands and texture
- − The hair volume is slightly stylized, bordering on a 'wig' look due to the extreme thickness
Wan 2.7 Pro
- + Natural and realistic hairstyle that matches the character's rugged aesthetic
- + Excellent preservation of facial features and skin texture
- + Realistic hairline integration
- − Introduces a slight blur or softening at the top edges of the hair
- − Minor loss of the original sharp grain/texture in the edited hair area compared to the rest of the image
Verdict: Both models performed exceptionally well at preserving the source image. FLUX.2 [klein] 4B provided more volume and sharper detail in the hair strands, while Wan 2.7 Pro created a more grounded, realistic hairstyle that felt character-appropriate. FLUX.2 [klein] 4B is slightly preferred for its superior texture matching with the original grain of 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.”
AI Judge Analysis
FLUX.2 [klein] 4B
- + Excellent high-clarity PBR textures on the fish
- + Clean and simple composition
- + Accurate isometric perspective
- − Spelling error in 'SUSHI' (rendered as 'SUSH')
- − Incorrect flag icon representation
- − The diorama base is missing, rendering only a standard plate flat on the background
Wan 2.7 Pro
- + Perfect text rendering for 'JAPAN' and 'SUSHI'
- + Includes a correct Japanese flag icon
- + Followed the request for a small raised diorama base perfectly
- − Texture of the salmon is slightly less realistic than Model A
- − Added extra elements like chopsticks and a soy sauce bowl not explicitly requested
Verdict: Wan 2.7 Pro is the clear winner as it followed all complex instructions, including the raised diorama base, correct text spelling, and the specific flag icon. FLUX.2 [klein] 4B produced high-quality materials but failed on the text spelling and the diorama platform requirement.
Over-the-top cartoon caricature
Editing“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.”
AI Judge Analysis
FLUX.2 [klein] 4B
- + Excellent caricature style that maintains the subject's likeness while exaggerating features
- + Highly detailed news studio environment with a professional desk and monitors
- + Includes clear, well-rendered dogs that are well-integrated into the scene
- − Completely misses the hockey component of the prompt
- − Text on the monitors is nonsensical and garbled
Wan 2.7 Pro
- + Successfully incorporates all elements: tv anchor, dogs, and hockey (via jerseys and stick)
- + Legible and humorous speech bubbles that add to the caricature feel
- + Cleverly combines a broadcast microphone with a hockey stick
- − The facial likeness to the original subject is less accurate than Model A
- − Anatomical error with the hand holding the hockey stick/microphone
Verdict: While FLUX.2 [klein] 4B provides a much better caricature of the woman's face and a more detailed studio, it fails to include the requested hockey theme entirely. Wan 2.7 Pro is the overall winner for successfully integrating all prompt requirements—professional anchor, dogs, and hockey—in a creative and cohesive way, despite minor anatomical issues.
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.”
AI Judge Analysis
FLUX.2 [klein] 4B
- + Excellent soft lighting and god rays that feel magical.
- + Higher level of fur detail for a 'hyper-photorealistic' look.
- + Very vibrant and colorful wildflower field.
- − Missed the baby bunny entirely, providing two kittens instead.
- − Anatomical issues with the fox's front paw and the smaller kitten's structure.
Wan 2.7 Pro
- + Followed all prompt instructions, including the golden retriever, kitten, fox, and bunny.
- + The composition feels more dynamic and cohesive for a 'playful chasing' vibe.
- + Accurate representation of the requested god rays and sunrise lighting.
- − The fox has an extra black paw emerging from its chest area.
- − Butterfly wings are slightly simplified compared to Image A.
Verdict: Wan 2.7 Pro is the clear winner for prompt adherence as it successfully included all four requested animals, whereas FLUX.2 [klein] 4B replaced the bunny with a second kitten. Although both images have minor anatomical artifacts in the animal limbs, Wan 2.7 Pro's scene composition and overall execution of the 'playful' atmosphere are superior.
Studio Ghibli Anime Style
Editing“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”
AI Judge Analysis
FLUX.2 [klein] 4B
- + Excellent adherence to the 'soft pastel colors' and 'dreamy' aspect of the prompt.
- + Perfectly captures the Studio Ghibli cel-shaded character design style.
- + Successfully reimagined the background into a lush, anime-style garden/streetscape.
- − Completely lost the 'jealous' facial expression of the girl on the right, making her look happy.
- − Colors are significantly desaturated compared to the original red dress.
Wan 2.7 Pro
- + Perfectly preserves the iconic facial expressions of all three characters from the original meme.
- + Excellent watercolor texture that feels hand-painted.
- + Maintains the structural integrity and composition of the source image while applying the requested style.
- − The style feels more like a general western watercolor illustration than specific Studio Ghibli anime style.
- − Background is slightly messy and less 'dreamy' than the prompt requested.
Verdict: FLUX.2 [klein] 4B followed the stylistic instructions better, creating a genuine Studio Ghibli aesthetic, but it failed the edit by changing the fundamental emotions of the characters. Wan 2.7 Pro is the superior edit because it retained the essential 'distracted boyfriend' energy and facial expressions while applying a beautiful hand-painted texture.
Golden Hour Stroll
Image Editing“Add dynamic motion to this photo: make hair blow in the wind, add leaves flying, energetic and lively feel.”
AI Judge Analysis
FLUX.2 [klein] 4B
- + Successfully added a large volume of leaves with motion blur.
- + Maintains character consistency and facial details well.
- + Successfully applied a side-wind effect to the hair.
- − The leaves appear somewhat floating and disconnected from the depth of the scene.
- − The hair rendering is slightly stringy compared to the original.
Wan 2.7 Pro
- + The hair motion is very dynamic and voluminous, creating a high-energy feel.
- + The placement of leaves feels more integrated into the environment's space.
- + Excellent lighting consistency maintained from the source image.
- − The dog's face is slightly altered and less crisp than the original.
- − Fewer flying leaves compared to Model A.
Verdict: Both models followed the instructions well, but Wan 2.7 Pro produces a more natural and 'energetic' feel through the dramatic hair movement, whereas FLUX.2 [klein] 4B focuses more on adding a high density of leaves. Wan 2.7 Pro is preferred for the superior integration of the wind effect and better overall visual appeal despite minor softening of the dog's features.
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.”
AI Judge Analysis
FLUX.2 [klein] 4B
- + Clean vector aesthetic suitable for a real logo
- + Accurate representation of a cloche dome
- + Excellent handling of paper texture background
- − Significant spelling error in the main brand name ('FLAXTION')
- − Redundant repetition of 'Est. 1720' text
Wan 2.7 Pro
- + Beautiful vintage woodcut illustration style
- + Almost correct brand name spelling with only one minor character error
- + Rich, balanced composition with professional typography
- − Minor misspelling in brand name ('Florion' instead of 'Florian')
- − Included unnecessary decorative elements around the corners that break the minimalist requirement
Verdict: Wan 2.7 Pro is the superior choice because it captures the 'vintage' and 'classic typography' requirements much more effectively than Flux.2 [klein] 4B. While Flux offers a cleaner vector look, its failure to spell the primary brand name correctly and the redundant text elements make it less usable than Wan's more artistic and nearly-correct execution.
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.”
AI Judge Analysis
FLUX.2 [klein] 4B
- + Features a clean, modern flat-vector aesthetic.
- + Good use of the requested color palette.
- − Poor text rendering with many gibberish characters.
- − Incorrect layout that fails to follow a clear chronological step-by-step path.
- − The rocket design is inaccurate and looks more like a modern generic capsule than a Saturn V.
Wan 2.7 Pro
- + Excellent prompt adherence, following all 6 steps in clear chronological order.
- + Superior text rendering with accurate spelling of 'ARMSTRONG', 'ALDRIN', and 'COLLINS'.
- + Highly professional composition that perfectly captures a NASA-style infographic.
- − The word 'DESCENT' is slightly misspelled as 'DESCRIPT'.
- − The number of stars in the background might be a bit cluttered for a 'clean' vector style.
Verdict: Wan 2.7 Pro is the clear winner as it successfully follows the structured 6-step infographic layout requested in the prompt with highly accurate text and iconography. In contrast, FLUX.2 [klein] 4B produces an unorganized layout with significant spelling errors and fails to represent the specific iconography requested for each stage.
Explore each model
Alibaba's Wan 2.7 Pro image generation and editing model with higher-quality outputs and support for 4K image generation