Distilled version of Black Forest Labs' FLUX.2 [dev] outperforming it at a cheaper price. Developed by fal.ai.
Settled by community votes across 19 shared challenges, with an AI judge weighing in on each.
FLUX.2 [dev] Turbo
#3 of 62 in Text-to-Image
Wan 2.5 (Preview)
#27 of 62 in Text-to-Image
Where the votes landed
FLUX.2 [dev] Turbo
100.0%
win rate
Ties
0.0%
Wan 2.5 (Preview)
0.0%
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 [dev] Turbo
- + Excellent realism in the glass texture and reflections
- + Very convincing wooden table texture with natural imperfections
- + Perfect adherence to the 'partially visible through glass' instruction for the plant
- − The sphere is slightly dark and lacks the vibrant blue tone implied
Wan 2.5 (Preview)
- + Strong adherence to the spatial arrangement of the prompt
- + Vibrant colors on the red book and blue sphere
- − Unintentional floating particles/dust artifacts in the air
- − Physics of the book resting on the glass edge look slightly unnatural
- − Reflection of the sphere at the top and bottom of the cube is inconsistent with the lighting
Verdict: FLUX.2 [dev] Turbo produced a much more photorealistic and cohesive image, particularly in how it handled the refractions of the plant behind the glass cube. While Wan 2.5 (Preview) followed the prompt well, it suffered from unrealistic floating artifacts and less convincing lighting/reflection logic.
Man and Car in California
Editing“Make a photo of the man driving the car down the California coastline”
AI Judge Analysis
FLUX.2 [dev] Turbo
- + Excellent preservation of the man's facial features and specific hairstyle.
- + Maintains the unique pattern and texture of the jacket and scarf from the source image.
- + High dynamic realism in the interior car details and lighting.
- − The car color shifted from bright white to a light metallic silver/grey.
- − Narrower field of view makes it harder to see the full coastline context.
Wan 2.5 (Preview)
- + Perfectly preserves the white color and exterior design of the car from the source.
- + Great composition showing the full car and the iconic California coastal environment.
- + Good motion blur on the road and wheels.
- − The man's face and specific clothing are almost entirely lost due to scale and shadows.
- − The character's hairstyle is simplified and lacks the detail of the source image.
Verdict: FLUX.2 [dev] Turbo succeeded much better at preserving the identity of the person, effectively 'pasting' his likeness and specific outfit into the cab. Wan 2.5 (Preview) did a better job of preserving the original car's color and providing a classic cinematic composition, but it failed to maintain the details of the subject from the second source image.
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 [dev] Turbo
- + Excellent adherence to the 'motion blur from passing cars' prompt
- + Very realistic skin texture and facial features
- + Highly detailed bicycle and tools scattered on the pavement
- − The man's scale relative to the bicycle feels slightly off, appearing quite large
- − The bicycle kickstand and frame alignment have some minor geometric inconsistencies
Wan 2.5 (Preview)
- + Natural and aesthetically pleasing shallow depth of field
- + Good lighting and atmospheric rain droplets on the bike seat
- + Cleaner composition and a more convincing 'candid' posture
- − The cars in the background lack the specific motion blur requested
- − Some structural artifacts where the man's hands interact with the bike components
- − Texture on the clothes and skin is slightly smoother than the requested 'no stylization'
Verdict: FLUX.2 [dev] Turbo captures the motion blur and grittiness of the street scene effectively, providing a more detailed and 'unfiltered' look. Wan 2.5 (Preview) produces a more beautiful, cleaner image with excellent lighting, but misses the specific motion blur prompt and the high-fidelity skin texture found in FLUX.
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 [dev] Turbo
- + Excellent realization of 'battle-worn' with realistic skin texture, grime, and open wounds.
- + Superior intricate engraving and weathering on the plate armor.
- + Complex and natural hair braiding with colorful bead integration.
- − The torch in the background is slightly blurry while sparks are very sharp, creating a slight depth mismatch.
- − The hair texture looks a bit dry/frizzy compared to the face.
Wan 2.5 (Preview)
- + Strong cinematic lighting with vibrant warm tones hitting the armor and face.
- + Includes detailed chainmail and tattered cloth underlayers as requested.
- + Very lifelike eye reflection and moisture.
- − The 'braided' hair looks more like rows of pearls or studs attached to the scalp rather than hair woven with beads.
- − The armor engraving, while good, looks less like heavy plate and more like decorative filigree.
Verdict: FLUX.2 [dev] Turbo delivers a more convincing 'battle-worn' aesthetic with superior armor detailing and realistic grit. While Wan 2.5 (Preview) has beautiful cinematic lighting and great textural contrast in the clothing, its interpretation of the braided hair and beads feels more artificial. FLUX.2 is the winner for its grounded realism and adherence to the specific character details.
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 [dev] Turbo
- + Excellent typography with very clean, readable English text.
- + Layout realistically mimics a professional printed menu with pricing.
- + High-quality realistic photography of the food items.
- − The grid is slightly irregular with images of different aspect ratios.
- − Some pricing logic is nonsensical ($250 for a pizza).
Wan 2.5 (Preview)
- + Perfect adherence to the grid layout request.
- + Strict organization of sections for appetizers, pizza, and mains.
- + Consistent lighting and minimalist style across all food images.
- − Text is largely nonsensical and features many spelling errors.
- − The 'Pizza' section features images that aren't all pizzas.
- − Fonts are somewhat inconsistent and messy compared to Model A.
Verdict: FLUX.2 [dev] Turbo produces a much more professional result with superior typography and realistic design elements, though it struggles slightly with the structural grid. Wan 2.5 (Preview) follows the layout prompt more literally but fails significantly on text legibility and logical categorization. FLUX.2 is the clear winner for its polish and usability 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 [dev] Turbo
- + Excellent, crisp photorealistic detail on the meat and bun textures.
- + Flawless text rendering with a consistent fiery texture across all three elements.
- + Integrated the starburst element cleanly in the layout.
- − The 'exploded' effect is a bit static; the components are neatly stacked rather than dynamically scattered.
- − The sauce droplets look slightly repetitive in shape.
Wan 2.5 (Preview)
- + Superior sense of motion with diagonal orientation and scattered ingredients.
- + Creative typography with a melting, sauce-like effect that fits the food theme.
- + High contrast and vibrant colors that make the ad 'pop'.
- − The text in the starburst is a plain white font, failing the 'fiery, glowing effect' prompt for that specific part.
- − The lettuce texture looks slightly more plastic/artificial compared to Model A.
Verdict: Both models performed exceptionally well, following all complex text and layout instructions. FLUX.2 [dev] Turbo provides a more photorealistic and grounded image with perfectly consistent fiery text effects, while Wan 2.5 (Preview) captures the 'dynamic' and 'exploded' aspect of the prompt much more effectively through better composition and motion. FLUX.2 is the winner due to its superior realism and more faithful execution of the glowing effect on the price tag.
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 [dev] Turbo
- + Excellent chalk texture with realistic dusty residue and varying opacity
- + Precise adherence to the date and price requests
- + Layout looks more natural and less computer-generated
- − The word 'Herbs' is partially cut off on the line break
- − Formatting of the third item price is slightly repetitive
Wan 2.5 (Preview)
- + Perfect text rendering with high legibility
- + Complete and accurate text for all items including 'Herbs' and 'Cookies'
- + Strong background bokeh creating a professional café feel
- − Text appears slightly too smooth and digital, lacking authentic chalk grain and texture
- − Handwriting is too consistent for a natural chalkboard
Verdict: FLUX.2 [dev] Turbo provides a much more authentic chalk texture that truly feels handwritten on a blackboard, whereas Wan 2.5 (Preview) has a cleaner, more digital look to its text rendering. While Wan 2.5 (Preview) managed to fit the word 'Herbs' more successfully and followed the prompt's implied list more cleanly, FLUX.2 [dev] Turbo is the winner for capturing the requested 'chalk texture' and 'natural variations' much better.
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 [dev] Turbo
- + Excellent high-frequency detail in the space suit and horse's mane.
- + Dramatic cinematic lighting and realistic Earth atmospheric perspective.
- + Great anatomical accuracy for the horse's legs and hooves in a galloping pose.
- − Failed to follow the contradictory instruction 'horse on top, not vice versa'.
Wan 2.5 (Preview)
- + Strong vibrant colors with a very 'cinematic' sci-fi art style.
- + Clean rendering of the galaxy and nebula in the background.
- + Dynamic pose with a sense of motion through the dust trail.
- − Failed to follow the contradictory instruction 'horse on top, not vice versa'.
- − The astronaut's hand/glove appears slightly mangled around the reigns.
Verdict: Both models completely ignored the clarifying instruction 'horse on top, not vice versa', likely due to the strong semantic association of the phrase 'horse riding astronaut'. FLUX.2 [dev] Turbo is the winner as it provides significantly higher detail in the textures of the space suit and a more believable cinematic composition compared to the softer, more digital look of Wan 2.5 (Preview).
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 [dev] Turbo
- + Successfully merges the outfit elements including the scarf, coat, and jewelry.
- + Maintains the background lighting and environment of Image 1.
- − Failed to preserve the subject from Image 1, replacing him entirely with the person from Image 2.
- − Over-embellished with excessive jewelry not present in either source image.
Wan 2.5 (Preview)
- + Matches the clothing from Image 2 accurately and adapts it to the leaning pose of Image 1.
- + Retains the background and general lighting of the source scene.
- − Failed to keep the person from Image 1, completely replacing him with the man from Image 2.
- − Missing the scarf texture details and specific accessories requested.
Verdict: Both models failed the primary instruction of the image editing task, which was to keep the person from Image 1 (with his specific face, hair, and vitiligo) and dress him in the clothes from Image 2. Instead, both FLUX.2 [dev] Turbo and Wan 2.5 (Preview) simply transplanted the person from Image 2 into the background of Image 1, though FLUX.2 adhered better to the 'elaborate' description by adding extra jewelry.
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 [dev] Turbo
- + Excellent photorealism with shallow depth of field
- + Accurately places the passenger in the back seat as requested
- + Strong adherence to facial expressions for both the capybara and the businesswoman
- − The passenger appears to be in the front passenger seat rather than behind the driver
- − The steering wheel grip looks slightly anatomicaly awkward for the capybara paws
Wan 2.5 (Preview)
- + Successfully positions the woman in the back seat more convincingly
- + Vibrant colors and lighting that capture the Times Square night vibe
- + High level of detail on the capybara's fur and the taxi's exterior rain droplets
- − The passenger's face is quite blurry and lacks the 'bored' detail requested
- − The text on the taxi sign is garbled compared to the clear text in Model A
- − The capybara's head is strangely large relative to the car interior
Verdict: FLUX.2 [dev] Turbo delivers a much more convincing photorealistic image with better textures and clearer expressions, though it struggled slightly with the spatial positioning of the passenger. Wan 2.5 (Preview) managed the back-seat perspective better but failed on clear facial details for the human and produced messy text and proportions. FLUX.2 is the winner for its superior clarity and realistic lighting.
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 [dev] Turbo
- + Excellent layout that feels like a coherent vintage poster.
- + Perfect text rendering with high-quality gothic font choice.
- + Moody, atmospheric color palette that fits the 'vintage gothic' request.
- − The jack-o'-lantern glow is a bit flat compared to the other model.
Wan 2.5 (Preview)
- + Vibrant lighting and impressive flame details inside the jack-o'-lantern.
- + Great use of depth with the foreground thorns and background silhouette.
- − The curved title text is slightly misaligned at the top.
- − The blue-and-yellow color scheme feels more like a modern digital illustration than a 'vintage' parchment poster.
- − The scroll banner text is basic and lacks the gothic character of the rest of the image.
Verdict: FLUX.2 [dev] Turbo produces a much more authentic 'vintage' result with superior typographical integration and a consistent gothic aesthetic. While Wan 2.5 (Preview) has more dynamic lighting in the pumpkin, its overall composition feels like a modern graphic layered over an image rather than a unified parchment invitation.
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 [dev] Turbo
- + Excellent preservation of the background and clothing.
- + The hair texture is realistic for the style chosen.
- + Successfully integrates the new hair with the existing beard.
- − The choice of an afro-textured hair style is a mismatch for the person's beard texture and ethnicity.
- − The hairline integration on the forehead is a bit harsh.
Wan 2.5 (Preview)
- + Perfectly matches the hair texture and color to the existing beard.
- + Maintains the exact facial features and background of the source image.
- + The style and hairline appear very natural and logically consistent for the subject.
- − Slightly smoother texture in the hair compared to the sharp grain of the original image.
Verdict: Wan 2.5 (Preview) provided a much more plausible and high-quality edit by matching the new hair texture to the subject's existing beard, whereas FLUX.2 [dev] Turbo chose a style that looks like a wig. Both models did an excellent job of preserving the source image's pose, lighting, and background.
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 [dev] Turbo
- + Excellent texture work with realistic rice grains and salmon marbling.
- + Precise adherence to the 45-degree isometric perspective and diorama base request.
- + High-quality text rendering and clean layout.
- − Lighting is slightly less 'soft' compared to the 3D-cartoon vibe mentioned.
Wan 2.5 (Preview)
- + Captures the 'soft refined textures' and 3D cartoon aesthetic perfectly.
- + Very clean typography and flag icon representation.
- + Simple, pleasant color palette.
- − The base is circular rather than a traditional isometric diorama platform.
- − The text is slightly cut off at the very top of the frame.
Verdict: Both models followed the complex text-heavy prompt very well. FLUX.2 [dev] Turbo produced a more detailed, realistic miniature that felt like a tactile object, while Wan 2.5 (Preview) better captured the '3D cartoon' stylistic request with softer shapes. FLUX.2 is the winner for its superior texture detail and perfect adherence to the isometric diorama framing.
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 [dev] Turbo
- + Excellent caricature style that maintains a strong facial likeness to the source person
- + Richly detailed background combining a news desk, dogs, and a live hockey arena
- + High-quality rendering with professional lighting and composition
- − Text on the news desk is nonsensical gibberish
Wan 2.5 (Preview)
- + Successfully incorporates all elements: microphone, news desk, dogs, and hockey stick
- + Preserves the denim jacket from the source image in the caricature
- − The facial likeness is weak and looks generic compared to the source
- − The composition is much simpler and lacks the immersive detail of the competitor
Verdict: FLUX.2 [dev] Turbo produced a superior image by creating a highly detailed scene that seamlessly blended the three requested themes (TV anchor, dogs, and hockey) while maintaining a recognizable facial likeness to the source image. Wan 2.5 (Preview) followed the instructions well but the resulting caricature felt like a more generic clip-art style with less artistic depth.
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 [dev] Turbo
- + Excellent anatomical accuracy across all four animals
- + Beautiful interaction between the kit and kitten with a natural tumbling pose
- + Subtle and realistic dew sparkle effect that enhances the atmosphere
- − The fox kit's face looks slightly more like a kitten/dog hybrid in structure
- − The lighting is a bit flat on the puppy compared to the background
Wan 2.5 (Preview)
- + Dynamic 'running' action that captures the playful chase theme well
- + Vibrant colors and strong 'god rays' from the sunrise
- + Large, expressive eyes on the animals as requested
- − The fox's eyes appear unnaturally blue and glowing, bordering on uncanny
- − Water droplets look like floating glass beads rather than realistic dew
- − The kitten has an anatomical issue where its front paw seems disconnected or poorly proportioned
Verdict: FLUX.2 [dev] Turbo produces a much more coherent and believable image with realistic animal proportions and soft interactions. While Wan 2.5 (Preview) captures a more energetic movement, it suffers from several artifacts, notably the strange glowing eyes of the fox and the floating, oversized water droplets.
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 [dev] Turbo
- + Excellent adherence to the 'hand-painted textures' and 'pastel' instructions.
- + Strong mimicry of Ghibli-style watercolor backgrounds and character watercolor-sketch aesthetics.
- + Retains the iconic composition and facial expressions of the 'Distracted Boyfriend' meme perfectly.
- − Features some minor line noise typical of watercolor filters on high-detail areas.
Wan 2.5 (Preview)
- + Closer to modern digital anime styles with clean line work.
- + Preserves the clear urban background architecture from the original photo more accurately.
- + Successfully adapts the characters' outfits and poses to an illustrated medium.
- − Misses the 'hand-painted watercolor' specific Ghibli aesthetic requested in the prompt.
- − Lighting is a bit flat compared to the dreamy atmosphere requested.
Verdict: FLUX.2 [dev] Turbo is the clear winner as it masterfully captured the specific watercolor 'hand-painted' texture and soft pastel palette that define the Studio Ghibli brand. While Wan 2.5 (Preview) produced a high-quality anime illustration, it felt more like a modern digital cel-shaded work rather than the nostalgic, painterly mood requested by the prompt.
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 [dev] Turbo
- + Excellent adherence to the 'hair blowing in wind' instruction with a symmetrical, dynamic fan effect
- + High density of falling leaves that creates a more energetic and lively atmosphere as requested
- + Near-perfect preservation of the background elements, including the bridge and river
- − Hair looks slightly stiff and unnatural in its outward spread
- − Leaves overlaying the person's body and face appear a bit messy and lack depth
Wan 2.5 (Preview)
- + Natural-looking hair motion that flows realistically in one direction
- + Good preservation of the subject's face and the dog's features
- + Clean integration of leaves into the 3D space
- − Leaf count is very sparse, failing to convey the requested 'lively' and 'energetic' feel
- − Leaves look like neon green digital shapes rather than real foliage matching the environment
Verdict: FLUX.2 [dev] Turbo followed the edit instructions more effectively by providing a significant amount of dynamic leaf motion and a more dramatic change to the hair. While Wan 2.5 (Preview) produced a more realistic hair flow, its leaves were too few and looked like fluorescent green artifacts, which detracted from the energetic feel requested.
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 [dev] Turbo
- + Excellent typography with proper accent placement on 'CAFÈ'
- + Authentic vintage texture on both the logo and the background
- + Strong composition with a clean, vector-style execution
- − The steam elements are slightly detached from the dome
Wan 2.5 (Preview)
- + Good use of the warm brown and cream color palette
- + Creative interpretation of the cloche as a transparent dome
- − The banner structure is cluttered and layered awkwardly
- − Typography is inconsistent in size and alignment
- − The 'Est. 1720' text is slightly warped
Verdict: FLUX.2 [dev] Turbo produced a superior logo that perfectly captures the 'minimalist vector emblem' request with professional-grade typography and subtle texturing. Wan 2.5 (Preview) struggled with the banner composition and text alignment, resulting in a more cluttered and less cohesive design.
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 [dev] Turbo
- + Excellent typography rendering with almost perfect spelling and legibility.
- + Includes a clear labeled sequence of the moon mission that follows the prompt's requested steps.
- + Distinct NASA-inspired color palette and high-quality vector-style illustrations.
- − The layout is a bit cluttered with redundant elements like dual 'Translunar' labels and multiple lunar modules.
- − Some icons include literal text within the icon like 'icon' in 'Saturn Vicon'.
Wan 2.5 (Preview)
- + Clean, professional composition that feels like a cohesive infographic poster.
- + Strong adherence to the flat-vector style with consistent line weights.
- + Creative and clear iconography for the transition from Earth to Moon.
- − The 'Descent' and 'Landing' text labels appear to be floating without associated icons.
- − Text rendering is slightly inconsistent with some illegible symbols in the astronaut portraits.
- − Icon for Collins shows him wearing a helmet that looks more like a military soldier than an astronaut.
Verdict: FLUX.2 [dev] Turbo followed the prompt's checklist more literally and provided superior text rendering, though the layout is less organized. Wan 2.5 (Preview) produced a more visually pleasing and professional-looking infographic, but it failed to associate icons with every requested step and had minor issues with the character portraits. FLUX.2 [dev] Turbo is the winner for better prompt adherence and text accuracy.
Explore each model
Alibaba's text-to-image and image-to-image generation model from the Wan AI suite, offering high-quality visual generation capabilities