Head to head
Esc

Models · slot A

to navigate to pick

FLUX.2 [klein] 9B Black Forest Labs Wan 2.7 Pro Alibaba

Settled by community votes across 20 shared challenges, with an AI judge weighing in on each.

FLUX.2 [klein] 9B

20.6 arena score

#13 of 32 in Image Editing

Skill signature · Image Editing

Wan 2.7 Pro

21.0 arena score

#37 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.2 [klein] 9B

66.7%

win rate

Ties

0.0%

Wan 2.7 Pro

33.3%

win rate

66.7% 0.0% ties 33.3%
Shared challenges 20

Challenge by challenge

The strongest take from each model on every shared challenge, with the AI judge's read.

Geometric Composition

Text-to-Image

“A glass cube on a wooden table. Inside the cube is a small blue sphere. On top of the cube sits a red book. A green plant is behind the cube, partially visible through the glass. Soft window light from the left.”

FLUX.2 [klein] 9B
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent adherence to the 'soft window light from the left' instruction, creating realistic shadows and highlights on the table.
  • + Very realistic glass material with high-quality distortion and refractive properties.
  • + Accurate placement of the plant behind the cube as requested.
  • The blue sphere appears to be floating mid-air, which looks slightly unnatural compared to the rest of the realism.
  • The glass object is more of a hollow vase/container than a perfect geometric cube.

Wan 2.7 Pro

  • + Accurately renders a distinct glass cube with sharp edges.
  • + The blue sphere rests naturally on the bottom surface with a visible reflection.
  • + Excellent plant detail and placement behind the glass.
  • The composition feels slightly more 'staged' and less photographically organic than Model A.
  • The lighting is somewhat flatter across the scene compared to the directional light in Image A.

Verdict: Both models followed the prompt instructions perfectly, including the placement of the sphere, book, and plant. FLUX.2 [klein] 9B wins on pure photographic realism and lighting atmosphere, while Wan 2.7 Pro produces a better geometric cube and more natural physical interaction between the sphere and the floor of the cube.

Man and Car in California

Editing
Edit instruction

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

Source
FLUX.2 [klein] 9B
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent preservation of the specific car model and color.
  • + Accurately places the distinctive hairstyle of the man in the second source image in the driver's seat.
  • + Conveys a great sense of motion with realistic motion blur on the road and wheels.
  • The driver's head is quite small and lacks detail within the car.

Wan 2.7 Pro

  • + Beautiful landscape and lighting that fits the 'California coastline' prompt perfectly.
  • + The car's details and reflections are very well-integrated into the environment.
  • Completely fails to include the specific man from the source image, replacing him with a generic white male.
  • The driver is positioned awkwardly too far to the right, appearing to sit in the center console rather than the driver's seat.

Verdict: FLUX.2 [klein] 9B is the clear winner because it successfully identifies and merges both source images, placing the specific man from the second image inside the car from the first. Wan 2.7 Pro fails the core task of image editing by ignoring the subject in the second source image and substituting him with a different person.

Candid Street Photography

Text-to-Image

“A candid street photo of an elderly Japanese man repairing a red bicycle in light rain, reflections on wet pavement, shallow depth of field, 50mm lens, natural skin texture, imperfect framing, motion blur from passing cars, cinematic but realistic, no stylization.”

FLUX.2 [klein] 9B
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent skin texture and detailed elder facial features.
  • + Effective use of shallow depth of field for a cinematic look.
  • + High visual quality with realistic materials on the bicycle and clothing.
  • Lacks the requested motion blur from passing cars.
  • The framing feels a bit too balanced for 'imperfect framing'.

Wan 2.7 Pro

  • + Accurate capture of wet pavement reflections.
  • + Captures a wider street scene with a realistic Japanese city vibe.
  • + Realistic rain effect visibility.
  • Anatomical errors in the hands with cluttered finger rendering.
  • The background cars are static and lack the requested motion blur.
  • Skin texture is slightly smoother and less detailed than Model A.

Verdict: FLUX.2 [klein] 9B is the superior image due to its exceptional detail in skin texture and mechanical components, creating a highly believable scene despite missing the motion blur. Wan 2.7 Pro struggles significantly with the rendering of the hands and has a flatter overall lighting quality compared to the cinematic feel of FLUX.2.

Fantasy Warrior

Text-to-Image

“Close portrait of a battle-worn paladin in ornate engraved plate armor, hair braided with small beads, faint scars and dirt on the skin, warm torchlight reflecting off metal, shallow depth of field, bokeh sparks, lifelike eyes, highly detailed texture on leather straps and cloth underlayer.”

FLUX.2 [klein] 9B
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Extremely high detail on the engraved armor and chainmail underlayer.
  • + Very crisp focus on the facial features and lifelike skin textures.
  • + Stronger contrast and more dramatic lighting that highlights the 'battle-worn' theme.
  • The sparks look a bit like static dots rather than embers.
  • The hair braids are a bit symmetrical and stiff.

Wan 2.7 Pro

  • + Beautiful warm lighting and natural-looking bokeh sparks in the background.
  • + Excellent interpretation of the 'braided hair with beads' prompt with realistic variety.
  • + Good balance of grime and faint scars on the face.
  • The depth of field is a bit muddy compared to Model A.
  • Details on the leather straps and armor engravings are slightly less sharp.

Verdict: Both models followed the prompt exceptionally well, capturing the intricate details of the armor and the specific hairstyle requested. FLUX.2 [klein] 9B wins by a small margin due to the superior clarity of its textures, especially on the metalwork and facial pore details, while Wan 2.7 Pro offers a softer, more cinematic atmosphere with better-rendered lighting effects.

Modern Clean Menu

Text-to-Image

“Modern minimalist restaurant menu design, white background with colorful food photos in grid, sections for appetizers/pizza/mains, bold sans-serif fonts, vibrant accents, clean professional layout for casual dining.”

FLUX.2 [klein] 9B
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Features very bold and legible header font that matches the 'modern minimalist' request.
  • + Strong adherence to the white background and grid layout requirements.
  • + Clean separation between image grid and text sections.
  • The placeholder text is gibberish and visual artifacts appear in the pricing.
  • Poor variety in food photography, as all images look like pizzas regardless of the category.
  • Layout feels slightly unbalanced with the large empty space at the top.

Wan 2.7 Pro

  • + Excellent variety in food photography covering different menu categories correctly.
  • + Much higher text legibility with coherent English and logical pricing.
  • + Sophisticated composition with professional branding elements like a logo and social media icons.
  • Includes background props (pen, salt, rosemary) not explicitly requested in the design layout.
  • The layout is quite dense for a 'minimalist' request compared to Model A.

Verdict: Wan 2.7 Pro is the clear winner as it produces a functional menu with actual English text and diverse food imagery that matches the category labels. While FLUX.2 [klein] 9B achieves a more minimalist aesthetic, it fails on content by showing pizzas for every food category including appetizers and mains.

Magic Burger Explosion: Fiery Photorealism Challenge

Text-to-Image

“Ad for 'Magic Burger'. Dynamic, exploded burger with all components (bun, patty, cheese, lettuce, tomato, sauce) suspended in mid-air. Emphasize photorealistic detail and a sense of motion. Dark, fiery background with glowing embers. Integrate text: 'MAGIC BURGER' as a prominent title, 'LIMITED TIME ONLY' as a secondary message, and '€6.99' in a starburst, all rendered with a fiery, glowing effect.”

FLUX.2 [klein] 9B
Wan 2.7 Pro
0% wins 0% ties 100% wins

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent typography with glowing fire effects
  • + High visual coherence and professional ad layout
  • + Perfect adherence to all text requirements including price and secondary message
  • The 'exploded' effect is less literal, with components still mostly stacked
  • The background is more abstract sparks than a distinct fiery environment

Wan 2.7 Pro

  • + Superb 'exploded' physics with clearly separated components
  • + Dynamic liquid splashes and steam add excellent motion
  • + High-quality texture on the tomato and sesame seed bun
  • Missed significant portions of the prompt's text requirements (missing price and secondary message)
  • Text effects are flat orange rather than the requested fiery/glowing effect
  • Composition feels slightly empty in the center compared to the title

Verdict: FLUX.2 [klein] 9B followed the prompt instructions much more accurately, successfully integrating all three requested text elements with the specific glowing fire theme. While Wan 2.7 Pro provided a more impressive and literal 'exploded' view of the burger ingredients, its failure to include the secondary message and the price starburst makes it a less successful advertisement based on the user's requirements.

Chalkboard Menu

Text-to-Image

“Handwritten-style chalkboard menu in a cozy café, all text rendered in the exact same realistic chalk handwriting style with natural variations in letter size, slight slant, and chalk texture — no printed or digital fonts anywhere on the board. Title at the top in elegant cursive chalk handwriting: ‘TODAY’S SPECIALS – APRIL 30, 2026’. Below it, three menu items also in the same handwritten chalk style: ‘Truffle Mushroom Risotto – $24’, ‘Grilled Octopus with Lemon & Herbs – $28’, ‘Brown Butter Chocolate Chip Cookies – $9’. At the very bottom, smaller text in the identical handwritten chalk style (slightly smaller but still clearly legible with the same handwriting characteristics): ‘All items made fresh daily • Ask about our gluten-free options’. Warm ambient café lighting, visible chalk dust and smudges, realistic handwriting imperfections, no clean printed text anywhere.”

FLUX.2 [klein] 9B
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent chalk texture with realistic smudges and ghosting on the board.
  • + Strong adherence to the requested font style for the majority of the text.
  • + Captures a very realistic café background and natural lighting.
  • Spelling error in 'Mushrroropom'.
  • The text alignment is slightly cramped towards the edges.

Wan 2.7 Pro

  • + Perfect spelling across all menu items including the long cookie description.
  • + Very clean and balanced composition with decorative underlining.
  • + Excellent legibility and font consistency.
  • The text looks a bit too much like a digital font rather than authentic chalk-on-slate.
  • Lacks the realistic chalk dust and smudging effects requested for a 'handwritten' style.

Verdict: FLUX.2 [klein] 9B provides a much more authentic 'chalkboard' feel with realistic smudges and texture, but it suffers from a significant spelling error in the first menu item. Wan 2.7 Pro produces perfectly spelled, legible text with great layout, but the text lacks the gritty chalk texture requested and looks somewhat like a digital overlay. Overall, Wan 2.7 Pro is the winner for following the complex text prompt perfectly without spelling mistakes.

Pose & Character Mashup

Editing
Edit instruction

“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.”

Source
FLUX.2 [klein] 9B
Wan 2.7 Pro
100% wins 0% ties 0% wins

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Successfully replicates the complex pose and body position from Image 1.
  • + Accurately transplants the character, face, sunglasses, scarf, and clothing from Image 2.
  • + Matches the yellow background and lighting of the source pose image.
  • The right hand is clenched into a fist instead of the open-fingered gesture from Image 1.
  • Minor lighting inconsistencies on the character's feet compared to the stool.

Wan 2.7 Pro

  • + Maintains the original Image 1 perfectly.
  • Failed the editing task entirely by providing the original Image 1 without any changes.
  • Did not incorporate the character reference from Image 2.

Verdict: FLUX.2 [klein] 9B successfully completed the image editing task by mapping the character from Image 2 onto the unique pose and environment of Image 1 while maintaining high visual quality. Wan 2.7 Pro failed completely, returning Image 1 without any of the requested modifications.

The Reversed Rodeo

Text-to-Image

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

FLUX.2 [klein] 9B
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [klein] 9B

  • + High visual complexity with cinematic lighting and colors.
  • + Excellent texture on the horse's coat and detailed space background.
  • + Dynamic composition with varied planetary scales.
  • Prompt adherence failure: shows astronaut riding the horse instead of horse riding the astronaut.
  • Nonsensical gibberish text included at the bottom of the frame.
  • Visible face inside helmet looks slightly distorted and inconsistent with the suit.

Wan 2.7 Pro

  • + Natural-looking horse anatomy and clean astronaut suit rendering.
  • + Good depth perception with the horizon of the planet below.
  • + Clean image without artifacting or unwanted text.
  • Prompt adherence failure: shows astronaut riding the horse instead of the requested inverted 'horse on top' role.
  • Composition is a bit static compared to Model A.
  • Horse's back right leg appears to be missing or merged into the body.

Verdict: Both FLUX.2 [klein] 9B and Wan 2.7 Pro failed the core 'trick' of the prompt, which specifically requested the horse to be on top riding the astronaut. While both models produced high-quality standard interpretations, FLUX.2 [klein] 9B is slightly more visually impressive due to its cinematic lighting, despite the inclusion of AI-generated gibberish text.

Outfit Transfer Challenge

Editing
Edit instruction

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

Source
FLUX.2 [klein] 9B
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent adherence to the specific outfit, including the pea coat, plaid scarf, and jeans.
  • + Almost perfect preservation of the original face, hair, and sand textures on the face.
  • + Successfully integrates the pose while maintaining the complex layers of clothing.
  • Adds extra chunky jewelry that was not present in Image 2.
  • Slightly changes the background details under the wooden structure.

Wan 2.7 Pro

  • + Preserved the full-body pose and background structure well.
  • + Maintains the skin vitiligo patterns on the hands and chest.
  • Failed completely to use the outfit from Image 2, providing a gold patterned blazer instead.
  • The facial features were slightly altered and lost some of the unique sand texture details.
  • The proportions of the legs seem slightly elongated compared to the original person.

Verdict: FLUX.2 [klein] 9B followed the prompt much more accurately by transferring the specific navy pea coat, plaid scarf, and denim jeans from Image 2 onto the subject while keeping the face nearly identical to Image 1. Wan 2.7 Pro failed the primary instruction by generating an entirely different, unrelated outfit and losing facial likeness in the process.

The Capybara Taxi Driver

Text-to-Image

“Photorealistic scene inside a yellow New York taxi at night. A capybara is driving, wearing a yellow taxi driver cap and a dark jacket. It has a calm, professional expression and both front paws on the steering wheel. In the back seat sits a human businesswoman in a coat, looking at her phone with a completely normal, bored expression (as if this is just another normal ride). Through the windows you can see the streets of Manhattan at night with blurred lights. Realistic taxi interior, photorealistic, detailed fur and fabric, 35mm lens, night lighting with reflections, shallow depth of field.”

FLUX.2 [klein] 9B
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent photorealism in taxi interior textures and lighting.
  • + Correctly places the businesswoman in the back seat as requested.
  • The passenger is sitting in the middle/left of the back seat rather than behind the driver which looks slightly odd.
  • Gibberish text on the driver's cap.

Wan 2.7 Pro

  • + Natural composition from a side-view perspective.
  • + Good rendering of the capybara's hands/paws on the steering wheel.
  • Fails the spatial prompt requirement by placing the businesswoman in the front passenger seat instead of the back seat.
  • The passenger's hand holding the phone has anatomical issues.

Verdict: FLUX.2 [klein] 9B followed the prompt instructions much more accurately, correctly placing the businesswoman in the back seat to create the intended surreal atmosphere. While Wan 2.7 Pro has good textures, it failed the spatial positioning by placing the woman in the front seat and had more noticeable anatomical artifacts.

The Halloween Invitation

Text-to-Image

“Vintage gothic Halloween party invitation. Dark parchment poster, spooky border with webs and thorns, central glowing jack-o-lantern, bats, twisted trees, moody night sky. Add elegant gothic title text saying "Halloween Party Invitation", a small scroll banner saying "You are invited to a night of frights", and event details at the bottom: Date: 30.10.2026 Time: 7pm Location: The Arches, NYC Spooky but polished, cinematic lighting, square format.”

FLUX.2 [klein] 9B
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent typography with a cohesive gothic font.
  • + Moody, cinematic lighting that creates a strong atmosphere.
  • + Better adherence to the 'dark parchment' and 'twisted trees' prompt.
  • The parchment edges are a bit simple compared to the illustration.

Wan 2.7 Pro

  • + Highly detailed border with additional thematic elements like lanterns and a cauldron.
  • + Clear, legible text for all event details.
  • + Creative interpretation with the 'Est. 1847' and dress code additions.
  • The lighting is less cinematic and feels more like a flat illustration.
  • The jack-o-lantern face is slightly less menacing than requested.

Verdict: FLUX.2 [klein] 9B wins on atmospheric quality, delivering a cohesive 'cinematic' look with superior integration of the twisted trees and moody sky into the layout. Wan 2.7 Pro offers more intricate detail in its border elements, but the overall composition feels more like a digital drawing than the requested vintage dark parchment poster.

Bald man challenge

Image Editing
Edit instruction

“Give the person a full, thick head of natural hair with realistic texture, density, and a natural hairline. Preserve facial features and lighting.”

Before After
FLUX.2 [klein] 9B
Before After
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent texture and volume that looks very natural
  • + Perfectly preserves the facial features and the rest of the original scene
  • + The curly hairstyle matches the beard's texture and color well
  • The hair covers a bit more of the forehead than might be expected from a 'natural hairline' prompt

Wan 2.7 Pro

  • + Successfully adds a full head of hair that looks age-appropriate
  • + Maintains original lighting and background elements perfectly
  • The transition between the hair and the forehead/temples is slightly blurry
  • The hair texture is a bit flatter and less detailed compared to Model A

Verdict: Both models did an excellent job of preserving the source image while adding hair. FLUX.2 [klein] 9B is the winner because the hair it generated has much more realistic volume, curl detail, and lighting integration, whereas Wan 2.7 Pro's hair looks slightly more like a digital overlay with softer edges.

Isometric Miniature Diorama Scenes

Text-to-Image

“Create a clear, 45° top-down isometric miniature 3D cartoon scene of Japan's signature dish: sushi, with soft refined textures, realistic PBR materials, gentle lighting, on a small raised diorama base with minimal garnish and plate. Solid light blue background. At top-center: 'JAPAN' in large bold text, 'SUSHI' below it, small flag icon. Perfectly centered, ultra-clean, high-clarity, square format.”

FLUX.2 [klein] 9B
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent wood grain texture on the diorama base.
  • + Extremely clean and bold typography.
  • + Correct 45-degree isometric perspective.
  • The flag icon is incorrect, resembling the flag of Yemen rather than Japan.
  • The sushi roll structure is slightly messy with overlapping elements.

Wan 2.7 Pro

  • + Beautifully rendered PBR materials with realistic sheen on the salmon and roe.
  • + Includes a correct Japanese flag icon.
  • + Higher level of detail in the miniature food models, including distinct rice grains.
  • The diorama base is less distinct from the plate compared to the prompt's request for a 'raised diorama base'.
  • Includes extra peripheral elements like chopsticks and soy sauce not specified in the prompt.

Verdict: Wan 2.7 Pro is the winner as it accurately rendered the Japanese flag and provided much more sophisticated 3D textures on the food itself. While FLUX.2 [klein] 9B had a stronger diorama base and cleaner typography, its failure to generate the correct national flag for a country-specific prompt makes it less successful overall.

Over-the-top cartoon caricature

Editing
Edit instruction

“Create a caricature of me and my job. Make it exaggerated and humorous, incorporating my profession as a tv show anchor and my love for dogs and hockey.”

Source
FLUX.2 [klein] 9B
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent world-building, combining a hockey arena and a TV news desk seamlessly.
  • + Captures the subject's facial features well within a classic caricature style.
  • + Includes many small details like dogs in the crowd and hockey sticks.
  • The hand holding the microphone/pen hybrid is poorly rendered with garbled fingers.

Wan 2.7 Pro

  • + Translates the request into a very clean, vector-style cartoon.
  • + Good symbolic integration with the paw-print lapel pin and dogs in hockey jerseys.
  • + Clear, legible text in the speech bubbles.
  • The 'hockey stick' held in the hand is actually just a long pole attached to a microphone.
  • The composition feels a bit more generic than Model A's stadium setting.

Verdict: Both models successfully interpreted the request for a caricature involving TV anchoring, dogs, and hockey. FLUX.2 [klein] 9B created a much more immersive and creatively dense scene, placing the anchor in a stadium-themed news desk, whereas Wan 2.7 Pro opted for a simpler studio background with symbolic speech bubbles. FLUX.2 is the winner for its superior composition and more traditional caricature art style, despite a minor issue with hand rendering.

Adorable Baby Animals in Sunny Meadow

Text-to-Image

“Hyper-photorealistic scene of fluffy baby animals—a golden retriever puppy, tabby kitten, baby bunny, and red fox kit—with big expressive eyes and ultra-detailed soft fur, playfully chasing butterflies and tumbling together in a lush wildflower meadow, warm golden sunrise light with god rays and dew sparkles, joyful wholesome vibe, 8K masterpiece.”

FLUX.2 [klein] 9B
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent fur texture rendering and vibrant colors
  • + Captures the 'god rays' and sunrise lighting beautifully
  • + Very high visual clarity and aesthetic appeal
  • Completely missed the baby bunny from the prompt
  • Animals feel slightly more static than 'tumbling'
  • The kitten's pose and anatomy look a bit strained

Wan 2.7 Pro

  • + Successfully included all four requested animals (puppy, kitten, fox, and bunny)
  • + Dynamic poses convey the sense of 'tumbling' and playing better
  • + Effective use of dew sparkles and depth of field in the meadow
  • The fox kit's face looks slightly more mature and less like a 'baby' animal
  • Butterfly anatomy is a bit simplified compared to Model A
  • Slightly less 'hyper-photorealistic' fur detail than the competitor

Verdict: Wan 2.7 Pro is the winner because it successfully followed the prompt by including all four specific animals, whereas FLUX.2 [klein] 9B missed the baby bunny entirely. While FLUX.2 [klein] 9B offered slightly sharper lighting and individual fur strands, Wan 2.7 Pro captured the dynamic interaction and the complete scene description more accurately.

Studio Ghibli Anime Style

Editing
Edit instruction

“Transform this photo into a Studio Ghibli–inspired illustration. Use soft pastel colors, hand-painted textures, gentle lighting, dreamy backgrounds, and a warm, nostalgic mood”

Source
FLUX.2 [klein] 9B
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Perfectly captures the Studio Ghibli art style with clean line work and characteristic facial features.
  • + Strong adherence to the 'dreamy background' request by transforming the city into a scenic countryside.
  • + Excellent color palette using soft, nostalgic pastels.
  • Loses the original emotional context by making the 'jealous' girlfriend look happy and calm.
  • Changes the background significantly from the source image's urban setting.

Wan 2.7 Pro

  • + Excellent source preservation, maintaining the original urban layout and emotional expressions.
  • + Successfully applies a hand-painted watercolor texture across the entire image.
  • + Maintains the specific character likenesses while applying the illustration filter.
  • Style feels more like a general watercolor filter than a specific Studio Ghibli-inspired illustration.
  • The faces maintain too much realism to fit the Ghibli aesthetic requested.

Verdict: FLUX.2 [klein] 9B provides a much more convincing stylistic transformation into the Studio Ghibli universe, although it sacrifices the original characters' expressions and the urban setting to achieve it. Wan 2.7 Pro is far better at preserving the original image's integrity and the iconic 'distracted boyfriend' meme expressions, but its art style is more generic watercolor than Ghibli-specific.

Golden Hour Stroll

Image Editing
Edit instruction

“Add dynamic motion to this photo: make hair blow in the wind, add leaves flying, energetic and lively feel.”

Before After
FLUX.2 [klein] 9B
Before After
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent adherence to the 'windy' hair request.
  • + Adds a large quantity of dynamic flying leaves.
  • + Maintains very high likeness to the source image face and clothing.
  • Some hanging hair strands look slightly unnatural or overly stiff.
  • One or two leaves appear to overlap the woman's hair in a way that looks slightly layered incorrectly.

Wan 2.7 Pro

  • + Natural, flowing hair motion that feels believable.
  • + Subtle lens flare adds to the lively, energetic atmosphere.
  • + Excellent preservation of the dog and background elements.
  • Fewer flying leaves compared to Model A.
  • The facial features changed slightly more than Model A from the source image.

Verdict: Both models successfully interpreted the dynamic motion instructions, but FLUX.2 [klein] 9B is more visually striking due to the high density of flying leaves and a more dramatic wind effect on the hair. Wan 2.1 Pro provides a more subtle and naturalistic edit, but FLUX.2 [klein] 9B preserves the original woman's facial structure slightly better while meeting all prompt criteria more aggressively.

Vintage Cafe Logo

Text-to-Image

“Vintage minimalist restaurant logo for "Caffè Florian", retro cloche dome with steam and "Est. 1720" banner, classic typography, warm brown and cream tones, subtle texture on light background, vector emblem style.”

FLUX.2 [klein] 9B
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent typography rendering including the accent on 'Caffè'
  • + Very clean minimalist vector lines and solid color blocks
  • + Accurate representation of the requested banner and cloche
  • The steam element looks slightly cartoonish and detached from the cloche knob
  • The circular border is quite thin and simple compared to the central elements

Wan 2.7 Pro

  • + Beautiful vintage woodcut/ink illustration style for the cloche
  • + Rich, detailed composition with coherent laurel and border decorations
  • + Incorporates additional relevant context like 'Venezia Italia'
  • Spelling error in the main text ('Florion' instead of 'Florian')
  • The cloche looks more like a cake stand or pedestal bowl due to its base
  • Floating corner decorations (cinnamon, coffee beans) detract from the 'logo' aspect

Verdict: FLUX.2 [klein] 9B followed the prompt more accurately by correctly spelling the name 'Caffè Florian' and maintaining a true minimalist vector emblem style. While Wan 2.7 Pro features more intricate and aesthetically pleasing vintage illustrations, its failure to spell the name correctly and the inclusion of cluttered corner elements make it less effective as a core logo 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.”

FLUX.2 [klein] 9B
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Clean vector illustration style
  • + Includes all requested narrative steps visually
  • Numerous spelling errors including 'AOILLO', 'EARDHT', and 'LANDINING'
  • Non-linear layout that is difficult to follow as an infographic
  • Incorrect colors; uses too much green and vibrant white instead of the muted NASA palette

Wan 2.7 Pro

  • + Excellent adherence to the NASA-inspired color palette and modern infographic style
  • + Superior text rendering with accurate spelling for almost all labels
  • + Coherent vertical timeline layout that follows the actual mission progression
  • Typo in 'DESCRIPT' (likely intended for Descent)
  • Icons for astronauts are generic stick figures compared to the silhouettes in the other image

Verdict: Wan 2.7 Pro successfully captures the requested modern infographic aesthetic with a logical vertical flow and highly accurate text rendering. FLUX.2 [klein] 9B struggles with basic spelling and layout, resulting in a cluttered and confusing presentation. Wan 2.7 Pro is the clear winner for its professional composition and adherence to the specific mission steps.

Next steps

Explore each model