Black Forest Labs' distilled 9 billion parameter image generation model with sub-second inference and multi-reference support
Settled by community votes across 20 shared challenges, with an AI judge weighing in on each.
FLUX.2 [klein] 9B
#13 of 32 in Image Editing
Wan 2.7
#39 of 62 in Text-to-Image
Where the votes landed
FLUX.2 [klein] 9B
50.0%
win rate
Ties
0.0%
Wan 2.7
50.0%
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] 9B
- + Excellent depiction of light refraction through the glass and sphere.
- + Realistic texture on the red book and the wooden table.
- + Clean, minimalist composition with accurate scale of the small sphere.
- − The glass object is more of a hollow vase or jar shape than a perfect cube.
- − The blue sphere appears to be floating mid-air inside the glass without support.
Wan 2.7
- + Successfully depicts a sharp, geometric cube structure as requested.
- + High level of detail on the vintage red book and the plant leaves.
- + Complex reflections inside the glass cube adding to the realism.
- − Internal reflections and glass panels are visually confusing, with the sphere appearing in multiple places.
- − The sphere is relatively large compared to the 'small' description.
Verdict: Both models followed the complex spatial instructions well. FLUX.2 [klein] 9B produced a more aesthetically pleasing image with better lighting and sub-surface scattering in the sphere, though the glass container is rounded. Wan 2.7 followed the 'cube' geometry more accurately but struggled with messy internal reflections that make the scene look cluttered.
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] 9B
- + Excellent preservation of the car's original design and details
- + Successfully incorporates the specific hairstyle of the man from the source image
- + High visual quality with realistic motion blur and lighting
- − The man's face is obscured by the car's frame/interior
Wan 2.7
- + Beautiful scenic composition of the California coastline
- + Strong sense of motion and dynamic lighting
- − Completely ignored the physical appearance of the man from the source image
- − The driver's face is distorted and unrecognizable
- − Structural issues with the car's interior pillars
Verdict: FLUX.2 [klein] 9B followed the prompt much more accurately by attempting to place the specific man from the source image (identifiable by his hair) into the vehicle, while maintaining the car's architectural integrity. Wan 2.7 generated a visually pleasing landscape but failed the image editing task by replacing the man with a generic, distorted figure and introducing structural errors to the car's windshield frame.
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] 9B
- + Excellent shallow depth of field that creates a cinematic look.
- + Highly detailed facial skin texture and realistic hands.
- + Strong adherence to the 50mm lens aesthetic and color prompt.
- − The cars in the background lack the requested motion blur.
- − The framing is quite polished despite the 'imperfect framing' request.
Wan 2.7
- + Successfully captures the 'imperfect framing' and 'candid' feel of street photography.
- + More realistic street environment with multiple pedestrians and wet textures.
- + Better inclusion of the 'motion blur' aspect for some background elements.
- − Lower resolution and softer details compared to the other model.
- − The bicycle and the man's interaction with it have some anatomical/structural clipping issues.
- − Weaker bokeh effect, failing to fully capture the 50mm shallow depth of field requested.
Verdict: FLUX.2 [klein] 9B produces an image with superior technical quality, particularly in the rendering of skin textures and the 50mm depth of field, making it look like a high-end film still. Wan 2.7 better captures the spirit of a 'candid street photo' with its broader composition and imperfect framing, but it suffers from lower clarity and structural artifacts in the bicycle. FLUX.2 is the overall winner for its striking realism and detail.
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] 9B
- + Extremely detailed ornate engraving on the plate armor
- + Highly realistic skin textures with convincing grime and minor scars
- + Superb composition with balanced lighting from dual light sources
- − The scars appear slightly more like surface scratches than deep battle wounds
Wan 2.7
- + Excellent depiction of multiple braided hair strands with beads
- + Strong realization of the battle-worn aesthetic with more prominent facial scars
- + Good use of bokeh and environmental lighting
- − Armor engravings are less intricate and slightly inconsistent in some areas
- − The leather straps lack the micro-texture and weathering found in the competitor
Verdict: FLUX.2 [klein] 9B provides a superior level of technical detail, particularly in the intricate engravings of the armor and the high-fidelity skin texture. While Wan 2.7 does an excellent job with the character's hairstyle and facial expression, FLUX.2's lighting and material rendering offer a more polished and professional-looking portrait that perfectly hits every prompt requirement.
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] 9B
- + Successfully included the requested bold sans-serif header.
- + Followed the grid layout instructions for food photos.
- + Included sections for appetizers, pizza, and mains.
- − Text rendering is largely illegible gibberish.
- − The food photos lack variety, showing four very similar pizzas for different categories.
- − Graphic design feels unpolished with overlapping text and strange symbols.
Wan 2.7
- + Excellent visual hierarchy and professional graphic design.
- + High-quality text rendering and realistic food variety across the grid.
- + Sophisticated use of vibrant orange accents and clean whitespace.
- − The grid includes more than just the three requested sections (adds sides and drinks).
- − Composition includes unnecessary background props (pen, salt, rosemary) not requested.
Verdict: Wan 2.7 produced a significantly more professional and realistic menu design with legible text and diverse food photography. While FLUX.2 followed the section requirements more literally, the execution suffered from poor text generation and repetitive imagery.
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] 9B
- + Excellent photorealistic texture on the meat and bun
- + Clean and readable text integration
- + Effective use of atmospheric depth and embers
- − The burger is less 'exploded' and more of an open stack
- − The starburst effect is a bit generic
Wan 2.7
- + Highly dynamic 'exploded' composition with separated ingredients
- + Creative fiery typography for the 'Magic Burger' title
- + Captures the sense of motion with liquid splashes and flying seeds
- − The rendering is more illustrative/digital art than photorealistic
- − Composition feels slightly cluttered compared to Image A
Verdict: Both models followed the prompt instructions very well. FLUX.2 [klein] 9B produced a more professional, photorealistic advertisement that looks ready for print, while Wan 2.7 excelled at the 'exploded' aspect of the prompt with more creative energy and dynamic movement. FLUX.2 [klein] 9B is the preferred choice for its superior realism and polished visual balance.
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] 9B
- + Excellent chalk texture with realistic smudges and erase marks
- + Authentic handwritten variation in letter scale and baseline
- + Followed the elegant cursive style requested for the title
- − Minor spelling error at the bottom ('fress' instead of 'fresh')
- − The text is slightly less legible than a clean digital font
Wan 2.7
- + Perfectly legible text with zero spelling errors
- + Balanced composition with decorative dividers
- + Rich background environment with lights and plants adding to the cafe vibe
- − Text looks like a digital font or vector sticker rather than chalk
- − Fails to provide the 'elegant cursive' style for the title
- − The letters lack the grainy chalk texture requested in the prompt
Verdict: FLUX.2 [klein] 9B followed the stylistic instructions much more closely, delivering a rough, authentic chalk-on-board texture with genuine handwriting variations. Wan 2.7 produced a cleaner and more attractive overall scene, but the text appears to be a digital font overlay, failing the core 'natural chalk texture' and 'cursive' requirements 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 [klein] 9B
- + Excellent adherence to the character reference, including face, hair, sunglasses, and the checkered scarf.
- + Perfectly captures the complex pose and environment from the source image.
- + Maintains the lighting and shadow consistency of the original studio setup.
- − The fingers on the raised hand are slightly merged/stubby.
- − Minor anatomical awkwardness in how the legs connect to the torso under the clothing.
Wan 2.7
- + Successfully preserves the original environment and lighting from Image 1.
- − Completely failed to incorporate the character from Image 2.
- − Output is essentially a slightly lower-resolution copy of the pose reference image.
- − Did not attempt to change the person's gender, ethnicity, or clothing as requested.
Verdict: FLUX.2 [klein] 9B successfully followed the complex instructions, merging the character's identity and specific clothing items from Image 2 into the difficult pose of Image 1. Wan 2.7 failed the task entirely, simply returning the pose reference image without any modifications. FLUX.2 is the clear winner for its ability to synthesize elements from two separate images accurately.
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] 9B
- + Excellent cosmic background with multiple galaxies and light effects
- + High level of detail on the space suit and horse's anatomy
- − Failed the core logical instruction as the astronaut is riding the horse
- − Includes large, nonsensical watermark/text at the bottom
Wan 2.7
- + Natural and clean composition with a cinematic view of Earth
- + Better rendering of the astronaut's visor and suit details
- − Failed the core negative/reverse logic instruction as the astronaut is riding the horse
- − The horse's legs are slightly elongated and look awkward
Verdict: Both models completely failed the specific logic constraint of 'horse on top, not vice versa,' instead generating the classic trope of an astronaut riding a horse. FLUX.2 [klein] 9B has a more vibrant and surreal background, but is marred by significant text artifacts, whereas Wan 2.7 provides a cleaner, more realistic cinematic image despite the anatomical oddities of the horse's legs.
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] 9B
- + Successfully used the exact clothing items from Image 2, including the specific plaid scarf pattern and pea coat style.
- + Preserved the person's face and unique vitiligo patterns with high accuracy.
- + Correctly matched the pose and lighting of the person to the new clothing.
- − Included extra jewelry (long gold beads) that were not present in Image 2.
- − Slightly changed the background details, adding more debris on the beach.
Wan 2.7
- + Successfully changed the person's pose to show full-body attire including shoes.
- + Preserved the person's face and unique hair pattern well.
- − Completely failed to use the outfit from Image 2, instead generating a generic black coat with gold embroidery.
- − Introduction of significant anatomical errors in the hands and feet.
- − Modified the light skin patches to look like gloves or paint rather than preserving the natural vitiligo pattern from Image 1.
Verdict: FLUX.2 [klein] 9B followed the prompt instructions much more accurately, successfully transferring the specific plaid scarf and navy coat from Image 2 onto the person from Image 1 while maintaining their facial features. Wan 2.7 failed to use the reference clothing entirely, generating a different outfit and introducing several anatomical distortions.
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] 9B
- + Excellent photorealism with convincing textures and lighting.
- + Accurately places the passenger in the back seat as requested.
- + High level of detail on the capybara's fur and the passenger's expression.
- − The passenger appears to be in a front-row seat next to the driver instead of the back seat due to the perspective.
- − Text on the cap is slightly garbled.
Wan 2.7
- + Strong composition showing both the interior and the classic yellow taxi exterior.
- + Realistic depiction of the capybara's hands on the steering wheel.
- + Good lighting on the subject's faces.
- − The passenger is clearly in the front passenger seat, failing the 'back seat' part of the prompt.
- − The texture of the capybara's fur looks slightly less natural and more needle-like compared to Model A.
Verdict: Both models struggled with the spatial logic of placing the passenger in the back seat, placing them in the front passenger seat instead. FLUX.2 [klein] 9B is the winner due to its superior photorealistic textures and better handling of the passenger's bored expression, whereas Wan 2.7 felt slightly more like a 3D render and missed the night-time street blur effect through the windows.
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] 9B
- + Excellent typography with clear, legible text that perfectly matches the requested information
- + Sophisticated cinematic lighting and atmospheric foggy background
- + Stronger gothic aesthetic with sharp thorns and a coherent color palette
- − Composition is a bit crowded with the main title overlapping the tree branches
Wan 2.7
- + Ornate and detailed border illustration including extra elements like skulls and books
- + Clean layout that separates the illustration from the text sections
- + Included additional creative touches like the cauldron and ravens
- − Text is slightly less legible due to the thin font weight in the body text
- − The 'Est. 1847' and 'Dress code' text were not requested in the prompt
- − Illustration has a flatter, more cartoon-like style compared to the requested cinematic look
Verdict: FLUX.2 [klein] 9B followed the prompt's aesthetic requirements more closely, providing a moody, cinematic atmosphere and impeccable text rendering. While Wan 2.7 created a more intricate and charming border, its illustration style is more illustrative than cinematic, and it hallucinated extra text fields not found in the prompt.
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] 9B
- + Excellent preservation of the source image's clothing, background, and lighting.
- + Hair texture is highly detailed and realistic.
- + Matches the person's existing facial features perfectly.
- − The curly hair choice might look a bit 'wig-like' due to the high volume relative to the original head shape.
Wan 2.7
- + Natural, believable hair style and density that fits the character well.
- + Perfect preservation of the original image's environment and attire.
- + Seamless integration with the existing beard and glasses.
- − Slightly less fine detail in individual hair strands compared to Model A.
Verdict: Both models performed exceptionally well, demonstrating high-quality image editing with near-perfect preservation of the source image. Wan 2.7 is slightly preferred as the hair style and hairline look more integrated and 'natural' for this specific character, whereas FLUX.2 [klein] 9B provides a more dramatic curly style that feels a bit more like an overlay.
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] 9B
- + Excellent typography with clean, professional font choices.
- + Perfectly captures the requested 45° isometric perspective.
- + Soft, pleasing 3D cartoon textures with realistic wood grain.
- − The flag icon is incorrect, resembling the Yemen flag instead of Japan.
- − The sushi placement on the plate is a bit awkward and cramped.
Wan 2.7
- + Includes a correct Japanese flag icon.
- + Higher variety of sushi types and garnishes which fits the 'miniature scene' description well.
- + Great lighting and shadow work that emphasizes the 3D diorama effect.
- − The text 'JAPAN SUSHI' has slight alignment issues and inconsistent spacing.
- − Includes chopsticks and soy sauce which weren't explicitly requested, slightly cluttering the 'minimal' requirement.
Verdict: While both models followed the prompt closely, Wan 2.7 is the winner due to its superior adherence to the 'Japan' theme by correctly rendering the flag, whereas FLUX.2 [klein] 9B generated a different national flag. Wan 2.7 also provided a more visually interesting variety of sushi models that fit the miniature diorama aesthetic perfectly.
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] 9B
- + Excellent world-building by placing the caricature at a news desk inside a hockey arena.
- + Strong adherence to all prompt elements including profession, dogs, and hockey environment.
- + High-quality caricature style that maintains a recognizable resemblance to the source image's features.
- − The right hand (thumbs up) has an extra finger and some anatomical distortion.
- − Some of the text in the background is gibberish.
Wan 2.7
- + Successfully incorporates humorous elements like a dog in a hockey helmet.
- + Maintains the 'selfie' pose from the original source image.
- + Legible English text in the speech bubbles.
- − The transition between the anchor outfit and the arm is confusingly merged with the background.
- − The hockey representation is a bit cluttered, with a tiny rink and floating puck that feel less integrated than Model A.
- − Facial resemblance to the source image is slightly weaker than Model A.
Verdict: Both models successfully interpreted the request for a caricature, but FLUX.2 [klein] 9B provided a much more cohesive and professional scene by placing the anchor at a desk within a hockey stadium filled with dogs. While Wan 2.7 preserved the selfie pose, the resulting composition feels more like a collection of stickers rather than a fully realized environment. FLUX.2 [klein] 9B is the winner for its superior creativity and better-maintained likeness.
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] 9B
- + Excellent fur texture and lighting effects.
- + Vibrant color palette that enhances the 'wholesome' vibe.
- + Clean composition with large, expressive eyes as requested.
- − Failed to include the baby bunny requested in the prompt.
- − Anatomy of the fox's front leg looks slightly distorted.
Wan 2.7
- + Successfully included all four requested animals (dog, cat, fox, and bunny).
- + Captured the 'god rays' and 'dew sparkles' effect very effectively.
- + Dynamic movement and interaction between the animals.
- − Some anatomy issues, specifically the kitten's front paw morphing into the bunny.
Verdict: Wan 2.7 is the winner because it followed the prompt more accurately by including all four requested animals, including the baby bunny which FLUX.2 [klein] 9B missed entirely. While both images have minor anatomical artifacts, Wan 2.7 better captured the environmental details like dew sparkles and the specific mix of species requested.
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] 9B
- + Excellent capture of the Ghibli anime style, including character features and line work.
- + Strong creative interpretation that transforms the urban background into a pastoral, dreamy Ghibli-esque landscape.
- + Highly aesthetically pleasing color palette and watercolor textures.
- − Loses the specific 'outraged' facial expression of the woman on the right, making her look happy instead.
- − Complete overhaul of the background removes the source context of the city street.
Wan 2.7
- + Excellent preservation of the original source image's layout, background elements, and facial expressions.
- + Effectively applies a hand-painted watercolor texture while keeping the iconic meme recognizable.
- + Maintains the specific emotional narrative of the original photo.
- − The character design looks more like a sketch of real people than the distinct Ghibli anime style.
- − The background remains a blurry city street rather than the requested 'dreamy' Ghibli aesthetic.
Verdict: FLUX.2 [klein] 9B succeeds better at the stylistic transformation, perfectly capturing the Ghibli character design and color palette, though it loses the emotional context of the original meme. Wan 2.7 preserves the source image perfectly and applies a lovely watercolor texture, but fails to actually 'anime-ify' the characters. FLUX.2 is the likely winner for better following the complex stylistic components of 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 [klein] 9B
- + Excellent adherence to the request for blowing hair and flying leaves.
- + High degree of source preservation with almost identical character and background features.
- + Vibrant and dynamic movement created through varied leaf positions.
- − The hair strands are a bit rigid and stylized compared to the source.
Wan 2.7
- + The hair blowing effect looks very natural and integrated with the original lighting.
- + Subtle and realistic leaf distribution that doesn't overwhelm the scene.
- + Maintains the source image composition and character details perfectly.
- − Fewer leaves fly across the foreground compared to Model A, making it slightly less 'energetic'.
Verdict: Both models performed excellently at this image editing task, preserving the source image's integrity while adding the requested elements. FLUX.2 [klein] 9B provides a more dramatic and energetic transformation with a high volume of leaves, while Wan 2.7 offers a more photorealistic interpretation with natural-looking hair motion. Wan 2.7 is slightly preferred for the superior realism of the hair physics.
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] 9B
- + Excellent typography rendering for both the main name and the banner text.
- + Accurately follows the prompt's request for a minimalist vector emblem style.
- + Strong, clean composition that functions well as a professional logo.
- − The steam element is a bit stylized and thick compared to the rest of the lines.
Wan 2.7
- + Elegant border detail and decorative elements suit a vintage theme.
- + Nice use of the light background texture and framing.
- + Correctly followed the banner and date instruction.
- − Spelling error in the main text, rendering it as 'Florion' instead of 'Florian'.
- − The cloche dome design is slightly awkward, looking more like a cake stand with a glass lid than a traditional metal cloche.
- − Less minimalist than requested, leaning towards an intricate badge style.
Verdict: FLUX.2 [klein] 9B is the clear winner because it correctly spelled 'Caffè Florian' and adhered more closely to the 'minimalist' vector style requested. While Wan 2.7 produced a more decorative vintage badge, the misspelling of the primary brand name makes it unsuccessful as a logo output.
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] 9B
- + Clean vector illustration style
- + Includes silhouettes of the three crew members
- + Good use of the requested color palette
- − Numerous spelling errors in text (e.g., AOILLO, EARDHT, TRANSLURAL)
- − Confusing layout with arrows pointing in multiple contradictory directions
- − Does not strictly follow the sequential order of requested steps
Wan 2.7
- + Excellent adherence to the requested infographic layout and steps
- + High-quality text rendering with very few minor spelling errors
- + Superior professional composition that looks like a real educational poster
- − Very small icons for the launch vehicle
- − Label 'DESCRIPT' instead of Descent
Verdict: Wan 2.7 significantly outperformed FLUX.2 [klein] 9i by delivering a coherent, logically organized infographic that followed all six sequential steps of the prompt. While FLUX.2 had a nice vector art style, its spelling was poor and its layout was chaotic, whereas Wan 2.7 produced a professional-grade poster with factual-looking details and readable typography.
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