Black Forest Labs' flagship image generation model delivering state-of-the-art quality with exceptional realism, precision, and consistency for both text-to-image and advanced image editing
Settled by community votes across 20 shared challenges, with an AI judge weighing in on each.
FLUX.2 [max]
#10 of 62 in Text-to-Image
Wan 2.7
#39 of 62 in Text-to-Image
Where the votes landed
FLUX.2 [max]
0.0%
win rate
Ties
0.0%
Wan 2.7
100.0%
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 [max]
- + Excellent photorealistic texture on the red book cover.
- + Accurately represents soft lighting and subtle reflections.
- + Clean, modern aesthetic with sharp glass edges.
- − The glass cube has a mirrored base which wasn't explicitly requested and slightly complicates the visual.
- − The plants in the background are very blurry, losing some 'partial visibility through the glass' detail.
Wan 2.7
- + Stronger adherence to the prompt regarding the plant being visible through the glass.
- + The wooden table has realistic distressed texture and grain.
- + Excellent composition that feels like a natural interior photograph.
- − The blue sphere has a slightly rough, non-spherical texture up close.
- − Minor glass refraction artifacts where the cube edges meet the plant.
Verdict: Both models followed the prompt perfectly, including the complex spatial arrangement of objects. FLUX.2 [max] produced a cleaner, more stylized image with superior material textures, while Wan 2.7 created a more realistic, believable setting where the plant is more clearly visible through the glass medium. Wan 2.7 is slightly preferred for its more natural lighting and better execution of the background transparency.
Man and Car in California
Editing“Make a photo of the man driving the car down the California coastline”
AI Judge Analysis
FLUX.2 [max]
- + Excellent preservation of the man's facial features, hair, and clothing.
- + The car's details and reflections are maintained with high fidelity.
- + Highly realistic integration of the subjects into the new environment.
- − The position of the steering wheel and driver's seat is on the wrong side for a standard car in the US (California).
Wan 2.7
- + Dynamic composition with a sense of motion on the road.
- + Captures the 'California coastline' aesthetic well.
- − Completely fails to preserve the identity of the man from the source image, replacing him with a distorted figure.
- − The car's interior details become messy and incoherent around the driver area.
- − Heavy distortion and artifacts on the driver's face.
Verdict: FLUX.2 [max] is the clear winner as it successfully performs the complex task of merging two source images while maintaining the identity of both the person and the vehicle. In contrast, Wan 2.7 fails significantly on source preservation, resulting in a distorted, unrecognizable person that does not match the provided reference photo.
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 [max]
- + Excellent adherence to technical prompts like motion blur and shallow depth of field.
- + Highly realistic skin textures and wet surfaces.
- + Superior composition that feels more cinematic and professional.
- − The 'imperfect framing' prompt is less apparent as the composition feels very deliberate.
Wan 2.7
- + Successfully captures the 'imperfect framing' and 'candid' feel requested.
- + Good reflection quality on the wet pavement.
- + Natural positioning of the subject within a street scene.
- − Fails to incorporate the 'motion blur' requested for passing cars.
- − Lower detail in skin texture and clothing compared to the competitor.
- − The bicycle handles appear slightly distorted and physically illogical.
Verdict: FLUX.2 [max] is the clear winner for its superior technical execution of the prompt, specifically the motion blur on the cars and the tactile realism of the wet bike and skin. While Wan 2.7 captures a more believable 'imperfect' snapshot, it misses key prompt instructions and lacks the visual polish and depth of FLUX.2 [max].
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 [max]
- + Sublime leather and cloth texture detailing.
- + Excellent representation of ornate engravings on the plate mail.
- + Very realistic skin texture with dirt and scars that look embedded rather than painted on.
- − The beads are small and somewhat generic compared to the detailed braids in Model B.
- − The lighting transition on the cheek is slightly harsh.
Wan 2.7
- + Superb adherence to the braided hair with beads requirement.
- + Strong atmospheric lighting from the torch in the background.
- + Good use of depth of field with the background wall and sparks.
- − The metal armor texture looks slightly more like plastic/CG in certain highlights.
- − The scars look like simple surface lines rather than deep battle-worn wounds.
- − The engraving on the armor is less intricate than Model A.
Verdict: FLUX.2 [max] provides a much more lifelike and detailed rendering of the textures, specifically the metal engravings and the rough cloth/leather materials. While Wan 2.7 does a better job of capturing the specific 'braids with beads' look, FLUX.2 [max] creates a more grounded and visually stunning portrait with superior skin and armor quality.
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 [max]
- + Excellent typography rendering with almost perfect spelling in larger headers.
- + Strong contrast with bold, vibrant color accents for different sections.
- + Clean, professional layout that strictly follows the modern minimalist aesthetic.
- − Internal food labels and descriptions contains some gibberish text.
- − The food photos in the grid are repetitive (many similar pizzas).
Wan 2.7
- + Highly organized and appealing 3x4 grid for food photography.
- + Includes realistic supplemental elements like a QR code and social media icons.
- + Greater variety in food photos including pasta, soup, and desserts.
- − The overall image is framed as a mock-up (with a pen and bowl) rather than just the direct digital file requested.
- − Small descriptive text is largely illegible 'lorem ipsum' style scribbles.
Verdict: FLUX.2 [max] produced a cleaner, more direct digital file that excels in font clarity and prompt adherence regarding bold sans-serif fonts. Wan 2.7 provides a more visually diverse menu with better food variety, but it presented the design as a staged photograph with external objects rather than a flat digital graphic.
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 [max]
- + Excellent photorealistic texture on the bun and patty
- + Clean and readable text integration
- + Sophisticated use of lighting and depth of field
- − The 'exploded' view is a bit literal and vertically stacked rather than dynamic
- − The fiery background is somewhat blurry and less vibrant
Wan 2.7
- + Highly dynamic and energetic composition with floating ingredients
- + Creative fiery typography for the main title
- + Includes all requested ingredients plus extra details like pickles and flying seeds
- − The patty looks slightly more graphic/illustrated compared to the bun
- − The starburst for the price is a bit cluttered with the surrounding fire graphics
Verdict: FLUX.2 [max] produces a high-quality, professional food advertisement with superior photorealism, but the composition is a bit static. Wan 2.7 captures the 'exploded' and 'dynamic' aspects of the prompt much more effectively, although it leans slightly more towards a high-end digital illustration style than pure photography. Wan 2.7 is the winner for its superior creativity and adherence to the 'dynamic' motion 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 [max]
- + Excellent chalk texture with realistic dust and smudges.
- + Text is perfectly rendered with hand-drawn variations.
- + Warm, atmospheric lighting matches the 'cozy café' prompt.
- − The 'Brown Butter' item is slightly cut off at the bottom of its line, though the text is still legible.
Wan 2.7
- + Clean, highly legible text rendering.
- + Good composition with decorative chalk lines.
- + Accurately included the full prompt text for the bottom item.
- − The text looks like a digital font overlay rather than real chalk on a board.
- − Strong drop shadows behind the letters break the realism of handwritten chalk.
- − The lighting on the board is inconsistent with the light sources in the background.
Verdict: FLUX.2 [max] is the clear winner for its superior realism, capturing the specific texture and unevenness of real chalk handwriting that the prompt requested. While Wan 2.7 has accurate spelling and neat layout, its text appears as a digital font with artificial drop shadows, failing the 'no printed or digital fonts' requirement of the 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 [max]
- + Successfully integrated character features from Image 2 including sunglasses, scarf, and facial hair.
- + Maintained the high-contrast yellow lighting and red stool from Image 1.
- + Accurately replicated the difficult leaning pose and arm positions.
- − The feet on the stool look distorted and lack realistic anatomical detail.
- − The tilt of the head is slightly less extreme than the original pose in Image 1.
Wan 2.7
- + Perfectly preserved the background and stool from Image 1.
- − Completely failed the character transfer, retaining the woman from Image 1 instead of the man from Image 2.
- − Failed to include any and all clothing details from Image 2 such as the black sweatshirt, scarf, and sunglasses.
Verdict: FLUX.2 [max] successfully performed the complex task of merging the character details from Image 2 with the precise pose and environment of Image 1. In contrast, Wan 2.7 failed to execute the edit instruction entirely, essentially returning the source image with no character changes.
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 [max]
- + Excellent cinematic lighting and atmosphere
- + Creative inclusion of the asteroid as a grounded platform
- + Higher level of fine detail in the space suit and horse's coat
- − The horse's front legs look slightly unnatural in their stance on the uneven surface
Wan 2.7
- + Copes well with the 'floating' aspect of the prompt
- + Clean character and animal silhouettes
- + Accurate depiction of the astronaut's face within the visor
- − Failed the specific instruction 'horse on top' (showing a human on a horse instead of the inverse)
- − Composition feels a bit flatter and less 'surreal' than requested
- − Generic space background with many repetitive planetoids
Verdict: Both models failed the specific logic trap of the prompt which requested the horse to be 'on top' (an astronaut riding a horse is the standard, requested was a horse riding an astronaut). However, FLUX.2 [max] produced a much more cinematic and detailed piece of art with superior lighting, whereas Wan 2.7 felt like a standard stock-style interpretation.
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 [max]
- + Excellent adherence to the clothing in Image 2, including the specific plaid scarf and navy pea coat.
- + Perfect preservation of the person's facial features and distinctive vitiligo patterns.
- + Very high image quality and realistic lighting integration.
- − The pose is slightly altered from a lean to a more upright stance.
- − The background is cropped differently compared to the original source.
Wan 2.7
- + Successfully maintains the full body pose and lean of Image 1.
- + Resizes the entire image to include the requested shoes and floor.
- − Failed to use the correct outfit from Image 2, generating a generic black and gold coat instead.
- − Significant distortion of the person's hands and face, losing the original likeness.
- − The clothing looks flat and doesn't match the beach lighting as well.
Verdict: FLUX.2 [max] is the clear winner because it correctly identified and applied the specific clothing from Image 2, whereas Wan 2.7 generated a completely different outfit. FLUX.2 [max] also perfectly preserved the distinctive features of the person in the source image, while Wan 2.7 distorted their appearance significantly.
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 [max]
- + Excellent photorealistic lighting and depth of field
- + Natural integration of the capybara's head onto the human-like body
- + Accurate depiction of a modern car interior with realistic dashboard lighting
- − The capybara is wearing gloves, obscuring the requested 'paws on the steering wheel' detail
Wan 2.7
- + High adherence to the 'front paws' requirement
- + Capybara's expression is very calm and fits the prompt well
- + Clear inclusion of both primary subjects with good focus
- − The capybara's fur texture appears slightly plastic or synthetic compared to Model A
- − Perspective issues where the steering wheel appears disconnected from the dashboard
Verdict: FLUX.2 [max] creates a more cinematically realistic image with superior lighting and texture, though it adds gloves to the driver. Wan 2.7 follows the specific 'paws' instruction better but suffers from slightly less realistic fur textures and a more cluttered composition. Overall, FLUX.2 [max] is the preferred image due to its professional photographic quality and better technical execution of the scene.
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 [max]
- + Excellent cinematic lighting and atmosphere.
- + High-fidelity textures on the pumpkin and parchment.
- + Clean, professional layout that feels like a modern movie poster.
- − The parchment texture is only visible on the outer edges.
- − The layout is a bit simple compared to the 'vintage' request.
Wan 2.7
- + Excellent 'vintage' aesthetic with an ornate, detailed border.
- + Includes many extra thematic elements like ravens, skulls, and a cauldron.
- + Perfectly captures the scroll banner and parchment style.
- − Illustration style is more 'book-like' than 'cinematic'.
- − Image has a slightly cluttered feel compared to the sleekness of Model A.
Verdict: FLUX.2 [max] creates a more physically realistic and atmospheric image with impressive lighting, making it feel like a professional invitation. However, Wan T2I better captures the 'vintage' and 'parchment poster' aesthetic requested by the prompt, incorporating a denser set of thematic details and a more traditional invitation layout. FLUX.2 is preferred for its superior visual quality and polish.
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 [max]
- + Excellent adherence to the 'thick head of hair' request with high volume.
- + Perfectly preserves all background elements and foreground clothing.
- + Highly realistic texture that blends well with the existing beard.
- − The forehead area looks slightly smoothed or altered compared to the original skin texture.
Wan 2.7
- + Natural, believable hair growth pattern and styling.
- + Very effective preservation of the original facial features and lighting.
- + Integration with the ears and glasses is handled cleanly.
- − Slightly less volume than Model A, though still fits the prompt.
Verdict: Both models performed exceptionally well on this edit, successfully adding realistic hair while perfectly preserving the jacket, background, and lighting of the original image. FLUX.2 [max] provided a more voluminous 'full' head of hair, while Wan 2.1 produced a slightly more natural-looking style and hairline that integrated better with the original head shape.
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 [max]
- + Excellent adherence to the 'small raised diorama base' prompt with a multi-tiered platform.
- + Very clean and bold text rendering with a well-integrated flag icon.
- + Achieves a perfect matte cartoon 3D aesthetic with soft lighting.
- − The sushi models are slightly more simplified compared to the texture detail in Model B.
- − Chopsticks are floating or placed awkwardly on the tray without a rest.
Wan 2.7
- + Features more detailed PBR material textures, especially on the fish and rice grains.
- + Includes more variety in the sushi types and garnishes like soy sauce.
- + Clean and stylish typography with a nice stroke effect.
- − The diorama base is very simple and flat compared to the tiered request.
- − The chopsticks are slightly warped/bent and lack the 'ultra-clean' precision of the rest of the image.
Verdict: Both models followed the prompt instructions exceptionally well, including the specific text and flag requirements. FLUX.2 is the winner because its composition better captures the 'miniature 3D diorama' feel with its tiered base and perfectly balanced isometric scale, whereas Wan 2.7 feels more like a standard product render on a thick plate.
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 [max]
- + Excellent scene composition combining a news desk with a hockey rink
- + High-quality vector art style with clear, expressive characters
- + Clear visual representation of all three prompt elements: TV anchor, dogs, and hockey
- − The caricature's facial likeness to the source image is slightly generic
- − Text on the scoreboards and desk is garbled
Wan 2.7
- + Stronger preservation of the source subject's facial features in caricature form
- + Maintains the 'selfie' pose of the original image
- + Humorous additions like the dog in a hockey helmet
- − The TV anchor aspect is less obvious, looking more like a standard living room
- − Visual quality is a bit cluttered with chaotic speech bubbles
- − The tiny hockey rink model feels a bit detached from the scene
Verdict: FLUX.2 [max] creates a more cohesive and professional-looking caricature by fully committing to the scene, placing the subject at a news desk on an ice rink. Wan 2.7 maintains better facial likeness and the original selfie pose, but the overall composition is messy and the 'TV anchor' profession is poorly represented compared to the environment in the first image.
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 [max]
- + Excellent adherence to the 'tumbling/chasing' movement specified in the prompt.
- + Perfect rendering of four distinct animals with correct anatomy and expressive eyes.
- + Subtle and realistic integration of god rays and morning dew sparkles.
- − The fox kit has a slightly generic facial structure compared to a real fox.
- − Butterflies are a bit small and faint compared to the rest of the composition.
Wan 2.7
- + Highly detailed fur and crisp rendering of the flowers in the foreground.
- + Strong, dramatic god rays that create a vibrant morning atmosphere.
- + Beautifully detailed butterflies with distinct patterns.
- − The kitten has an anatomical error with a small extra limb or paw visible near its chest.
- − The animals feel more like they are standing in a row rather than 'tumbling together'.
- − The bunny's face looks slightly repetitive or static.
Verdict: FLUX.2 [max] captures the movement and joyful interaction of the animals much better, showing them in mid-stride and active play as requested. While Wan 2.7 has slightly sharper foreground details and vibrant lighting, it suffers from a significant anatomical artifact on the kitten and lacks the dynamic 'tumbling' composition of FLUX.2 [max].
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 [max]
- + Excellent adherence to the Studio Ghibli art style with characteristic facial features.
- + Strong use of soft, warm, pastel colors as requested.
- + The texture and lighting create a nostalgic, hand-painted feel.
- − The facial expressions are slightly softened, losing a bit of the intense 'distracted' and 'outraged' emotions of the original meme.
Wan 2.7
- + Successfully preserves the specific facial expressions and likenesses of the people in the original meme.
- + Clear watercolor-inspired texture that feels hand-painted.
- − The style leans more toward a realistic watercolor sketch than the specific Studio Ghibli anime aesthetic.
- − The lighting is flat compared to the dreamy atmosphere requested.
Verdict: FLUX.2 [max] is the winner as it successfully reimagined the source image into the specific requested art style, capturing the essence of a Studio Ghibli film through its character design and soft lighting. While Wan 2.7 did a better job of preserving the exact facial expressions of the subjects, its output felt more like a generic watercolor filter rather than a true stylistic transformation.
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 [max]
- + Excellent depiction of hair blowing in the wind with significant movement.
- + High preservation of the woman's facial features and the dog's appearance.
- + Leaves look crisp and integrated into the scene naturally.
- − The leash handle has been slightly altered/extended compared to the source.
Wan 2.7
- + Successfully adds both flying leaves and wind-blown hair.
- + Maintains the overall composition and colors of the original scene well.
- − The hair effect is more horizontal and looks slightly less natural than Model A.
- − Some leaves appear as brown blurs or artifacts (e.g., the one near her right hand).
- − The dog's face is slightly softened/changed compared to the source.
Verdict: FLUX.2 [max] is the winner as it creates a more convincing sense of motion, particularly with the way the hair flows naturally in one direction. While both models followed the instructions, Wan 2.7 produced slightly more artifacts among the falling leaves and altered the dog's facial features more than FLUX.2 [max].
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 [max]
- + Perfectly adheres to the requested name spelling 'Caffè Florian'
- + Strong minimalist vector aesthetic that perfectly matches the requested theme
- + Excellent integration of the 'Est. 1720' banner within the circular emblem
- − Steam lines are a bit thin and could be more pronounced
- − Subtle texture on the background is very faint
Wan 2.7
- + Nice use of secondary design elements like the stars and wheat to create a vintage feel
- + Good use of contrast between the brown and cream tones
- − Misspelled the primary brand name as 'Florion' instead of 'Florian'
- − The design is quite busy, leaning away from the requested 'minimalist' style
- − The cloche looks slightly more like a glass dome than a traditional metal cloche
Verdict: FLUX.2 [max] is the winner because it followed the spelling of the brand name correctly and stayed true to the 'minimalist' requirement. While Wan 2.7 has a more intricate and classic design, the typo in the main text and the busier composition make it less successful as a professional brand logo.
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 [max]
- + Excellent vector art style with clean, modern illustrations and consistent iconography.
- + Legible, well-rendered text for most labels and crew names.
- + Creative inclusion of the crew silhouettes with matching uniforms.
- − Repeats labels like 'Earth Orbit' across different panels incorrectly.
- − The Saturn V rocket illustration looks more like a shuttle or stylized rocket than the actual Apollo hardware.
- − Confuses the sequence of events within the panels.
Wan 2.7
- + Follows the logical flow of the requested steps much more accurately.
- + Excellent adherence to the NASA-inspired color palette and typographic style.
- + Includes impressive detail like specific times, altitudes, and mission dates.
- − Contains several spelling errors like 'Descript', 'Deccent', and 'Tranquiliry'.
- − The icons are smaller and slightly less polished than the other model's vector work.
- − The text at the very bottom is slightly distorted and contains 'Aaroenutics'.
Verdict: Wan 2.7 is the superior infographic because it correctly follows the logical sequence of the Apollo 11 mission steps and maintains a professional layout that feels like a real educational poster. While FLUX.2 [max] has cleaner vector illustrations and fewer spelling errors, it fails as an infographic by repeating labels and confusing the mission stages.
Explore each model
Alibaba's Wan 2.7 image generation and editing model for text-to-image, reference-guided generation, and instruction-based image edits