Head to head
Esc

Models · slot A

to navigate to pick

FLUX.2 [dev] Turbo fal Wan 2.7 Pro Alibaba

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

FLUX.2 [dev] Turbo

27.8 arena score

#4 of 62 in Text-to-Image

Skill signature · Text-to-Image

Wan 2.7 Pro

20.7 arena score

#38 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.2 [dev] Turbo

50.0%

win rate

Ties

50.0%

Wan 2.7 Pro

0.0%

win rate

50.0% 50.0% ties 0.0%
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 [dev] Turbo
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent photographic quality with realistic dust and reflections on the glass.
  • + Perfect adherence to spatial instructions including the position of the sphere and book.
  • + Superb representation of light diffraction and distortion through the thick glass edges.
  • The sphere appears slightly dark and semi-translucent rather than a solid blue sphere.

Wan 2.7 Pro

  • + Strong composition with a vibrant green fern providing a clear background.
  • + Accurate placement of all requested elements.
  • + High detail on the wooden table texture.
  • The glass cube appears to have a mirrored base which wasn't requested.
  • The lighting is a bit flat compared to Model A.

Verdict: Both models followed the prompt perfectly in terms of object placement and attributes. FLUX.2 [dev] Turbo is the winner due to its superior rendering of glass materials, including realistic thick-glass distortions and natural 'imperfections' like dust that add to the photographic realism, whereas Wan 2.7 Pro feels slightly more artificial with its mirrored internal base.

Man and Car in California

Editing
Edit instruction

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

Source
FLUX.2 [dev] Turbo
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Perfectly preserves the identity, hair, and clothing of the man from the source image.
  • + Accurately integrates the specific cream interior and wood-grain dashboard of the car.
  • + Excellent sense of motion with the background blur and perspective.
  • The car exterior color appears slightly more silver/champagne than the brilliant white of the source car.

Wan 2.7 Pro

  • + Retains the car's exterior body design and white color with high accuracy.
  • + Beautifully captures the requested California coastline scenery with golden hour lighting.
  • Completely fails to preserve the man's identity, replacing him with a generic figure.
  • The driver is positioned on the wrong side for a standard LHD car, or his scale is significantly off relative to the seat.

Verdict: FLUX.2 [dev] Turbo followed the complex multi-image instruction perfectly, successfully merging the specific man and the specific car into the new coastline environment. It preserved his unique hairstyle and clothing flawlessly, whereas Wan 2.7 Pro completely lost the identity of the person from the 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.”

FLUX.2 [dev] Turbo
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent adherence to the motion blur request for passing cars.
  • + Highly detailed and realistic texture on the skin and clothing.
  • + Effective use of shallow depth of field and ground reflections.
  • The bike's front wheel and fork have noticeable structural glitches.
  • The framing is slightly more centered than an 'imperfect framing' might suggest.

Wan 2.7 Pro

  • + Strong composition with a clear focus on the subject and bicycle.
  • + Colors are natural and fit the requested realistic look well.
  • + Excellent reflection quality on the wet pavement.
  • Failed to include the requested motion blur for passing cars.
  • The bicycle geometry has some inconsistencies near the handlebars.
  • The background cars appear static, contrary to the prompt instructions.

Verdict: FLUX.2 [dev] Turbo followed the technical requirements of the prompt more closely, specifically capturing the motion blur of passing cars which adds to the street photography feel. While Wan 2.7 Pro created a clean and aesthetically pleasing image, it missed the motion blur and suffered from more significant anatomical issues in the bicycle's design.

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 [dev] Turbo
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent depiction of surface details like skin pores and leather texture
  • + High-quality intricate engravings on the armor
  • + Very realistic eye details and lighting
  • The torch in the background is slightly blurry and lacks defined structure

Wan 2.7 Pro

  • + Natural and aesthetically pleasing distribution of hair beads
  • + Warm torchlight is well-integrated and provides a strong sense of ambiance
  • + Solid rendering of the leather straps and buckles
  • Armor engravings are slightly flatter compared to Image A
  • The scars appear more like surface marks than depth-based wounds

Verdict: FLUX.2 [dev] Turbo delivers a more impactful close-up with superior texture on the skin and armor, making the 'battle-worn' aspect feel more grounded. Wan 2.7 Pro offers a great composition with warmer lighting, but it lacks the fine detail and lifelike eye quality found in FLUX.2.

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 [dev] Turbo
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent typography rendering for main headers
  • + High-quality, vibrant food photography
  • + Strong adherence to the requested grid layout for food photos
  • The 'Mains' section is poorly organized with confusing pricing
  • Text in the pizza section is largely gibberish/lorem ipsum

Wan 2.7 Pro

  • + Highly functional layout with contact info and social icons
  • + Clear, legible pricing and menu item names
  • + Consistent lighting and professional presentation with props
  • Small body text becomes slightly blurry/distorted at the bottom
  • Missed the specific requested sections (Appetizers/Pizza/Mains) by including others

Verdict: FLUX.2 [dev] Turbo created a more visually striking aesthetic with excellent large-scale typography and vibrant photos, but the actual content layout for a menu was disjointed. Wan 2.7 Pro delivered a much more realistic and usable menu design that looks like a finished professional product, despite not following the specific category headers as strictly as the competitor.

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 [dev] Turbo
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent photorealistic texture on the meat patty and fresh vegetables.
  • + Subtle and professional integration of the fiery glowing text effects.
  • + Great sense of physics with the sauce droplets suspended in mid-air.
  • The 'exploded' effect is a bit condensed compared to the more dynamic spread in the other model.

Wan 2.7 Pro

  • + Strong dynamic composition with a wider spread of ingredients including onions and pickles.
  • + Perfect adherence to all text requirements including the starburst shape.
  • + Very clear and readable font choices for an advertisement.
  • The lighting on the ingredients feels a bit flatter and more illustrative than photorealistic.
  • The cheese slice looks slightly plastic and lacks realistic texture.

Verdict: Both models followed the prompt exceptionally well, but FLUX.2 [dev] Turbo takes the lead in visual quality due to superior photorealistic textures and more natural integration of the fiery atmosphere. While Wan 2.7 Pro offers a more traditionally 'dynamic' layout for an ad, its rendering is slightly more cartoonish compared to the high-end food photography style of FLUX.2.

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 [dev] Turbo
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Outstanding chalk texture with authentic smudge marks and varying chalk pressure.
  • + Perfectly captures natural, human-like handwriting with slight slants and size variations.
  • + Excellent atmospheric lighting and background depth within the café environment.
  • The layout is a bit cramped, causing one menu item to wrap awkwardly onto multiple lines.
  • Minor repetition in the price rendering of the last item.

Wan 2.7 Pro

  • + Highly legible and clean text with perfect spacing and alignment.
  • + Accurately renders all requested text including the truncated item from the prompt.
  • + Crisp composition that feels very professional and balanced.
  • The handwriting lacks realistic chalk texture, appearing more like a digital font overlay.
  • The strokes are too uniform and lack the natural grit of real chalk on a board.

Verdict: FLUX.2 [dev] Turbo delivers a much more authentic and gritty chalk texture that perfectly matches the requested 'handwritten-style', whereas Wan 2.7 Pro produces text that looks too clean and digital. Although Wan 2.7 Pro has better layout and text accuracy for the final item, FLUX.2 [dev] Turbo is the winner for its superior adherence to the artistic style and realistic material rendering.

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 [dev] Turbo
Wan 2.7 Pro
50% wins 50% ties 0% wins

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Successfully integrated character features from Image 2 such as glasses, scarf, and clothing
  • + Correctly identified the person from Image 2 as the subject for the new pose
  • Serious anatomical failure where the model includes two heads on one body
  • Completely fails to replicate the physical pose from Image 1, creating a generic jump instead
  • Poor hand and foot rendering

Wan 2.7 Pro

  • + Perfectly maintains the environment and background from Image 1
  • Fails the image editing task entirely by returning the source image (Image 1)
  • Zero progress on character replacement from Image 2

Verdict: This was a difficult task that both models failed. FLUX.2 [dev] Turbo attempted to merge the characters but resulted in a nightmarish image with two heads and broken anatomy, losing the specific pose required. Wan 2.7 Pro simply returned Image 1 without any edits at all. FLUX.2 is the technical winner only for attempting the requested changes, despite the poor visual outcome.

The Reversed Rodeo

Text-to-Image

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

FLUX.2 [dev] Turbo
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent cinematic lighting and atmosphere.
  • + High level of detail on the space suit and horse textures.
  • + Dynamic composition with a sense of motion.
  • Failed the negative constraint; the astronaut is riding the horse, not vice versa.

Wan 2.7 Pro

  • + Clean, well-defined subjects against a space backdrop.
  • + Good rendered textures on the saddle and space suit.
  • Failed the negative constraint; the astronaut is riding the horse.
  • The horse's anatomy is slightly awkward, specifically where the front right leg joins the shoulder.

Verdict: Both FLUX.2 [dev] Turbo and Wan 2.7 Pro failed to follow the logical reversal requested in the prompt ('horse on top, not vice versa'), instead providing the standard astronaut-on-horse imagery. FLUX.2 [dev] Turbo is the superior choice because it offers significantly more cinematic lighting, richer textures, and a more immersive background compared to the flatter, more clinical look of Wan 2.7 Pro.

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 [dev] Turbo
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Successfully replicates the outfit from Image 2 almost perfectly.
  • + Maintains the scarf pattern and coat texture accurately.
  • + Correctly places the clothing on a person leaning against a wooden structure.
  • Completely failed to use the person from Image 1, using the person from Image 2 instead.
  • Violated the instruction to keep the person's exact face and hair unchanged.

Wan 2.7 Pro

  • + Successfully preserved the identity, vitiligo pattern, and facial features of the person from Image 1.
  • + Kept the background and original subject's body pose intact.
  • Failed to dress the subject in the outfit from Image 2, instead generating a generic gold-patterned blazer.
  • Missed the specific requested layers like the scarf and dark coat.

Verdict: This is a classic trade-off in image editing: FLUX.2 [dev] Turbo captured the clothing perfectly but ignored the 'source preservation' of the subject's identity, while Wan 2.7 Pro correctly preserved the person but failed to replicate the specific clothing requested. Wan 2.7 Pro is slightly preferred as it followed the complex instruction to keep the base person unchanged, which is the core of an image editing task.

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 [dev] Turbo
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Accurately places the passenger in the back seat as requested.
  • + Excellent photorealism with gritty taxi texture and atmospheric night lighting.
  • + The capybara's expression and posture perfectly match the 'professional' prompt description.
  • The 'TAX' sign on the roof appears to be reversed or mirrored from the camera's perspective.
  • The capybara's paws look slightly more like human/primate hands than capybara paws.

Wan 2.7 Pro

  • + Crisp image quality with vibrant colors and clear New York background bokeh.
  • + Successfully depicts the capybara in a dark jacket with a yellow cap and paws on the wheel.
  • Fails a major spatial prompt instruction by placing the woman in the front passenger seat instead of the back seat.
  • The perspective through the side window makes the car look unusually long or distorted in the interior space.
  • The capybara's fur texture looks slightly more digital/artificial compared to Model A.

Verdict: FLUX.2 [dev] Turbo followed the prompt instructions much more accurately, correctly placing the businesswoman in the back seat to create the intended narrative of a 'normal' taxi ride. Wan 2.7 Pro failed on the spatial arrangement by placing the passenger in the front seat, though both models handled the complex task of a capybara driving quite well. FLUX.2 is the clear winner for its superior composition and more realistic cinematic 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.”

FLUX.2 [dev] Turbo
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent text legibility and font choice
  • + Strong atmospheric lighting and moody color palette
  • + Precise adherence to the thorn and web border description
  • The parchment effect is a bit subtle compared to the dark background
  • Composition is very centered and traditional

Wan 2.7 Pro

  • + Beautifully detailed illustration with multiple layers and elements
  • + Excellent use of the 'scroll' element for the secondary text
  • + Very clean, polished graphic design aesthetic
  • The text for 'Halloween Party Invitation' has slight kerning and structural issues on the 'v'
  • The mood is more 'fairytale spooky' than the requested 'dark gothic'

Verdict: FLUX.2 [dev] Turbo followed the prompt more accurately in terms of mood and border details, providing a very atmospheric and readable invitation. Wan 2.7 Pro created a more complex and visually interesting illustration with great professional polish, though it leaned slightly more toward a whimsical style rather than the requested dark gothic tone.

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 [dev] Turbo
Before After
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent preservation of the source image facial features and glasses
  • + Impressive hair texture and volume that blends well with the existing beard
  • The hairline transition on the forehead is a bit abrupt
  • The choice of an afro style might not be what every user considers 'natural' hair for this specific character profile

Wan 2.7 Pro

  • + Highly realistic and natural-looking hairline and style for the character
  • + Perfectly matches the lighting and texture of the original photo
  • Very slight softening of the forehead details compared to the original

Verdict: Both models performed exceptionally well, preserving the original image's lighting and facial structure. FLUX.2 [dev] Turbo provided a high-volume, curly style that integrates seamlessly with the beard, while Wan 2.7 Pro provided a more conventional, realistic hairstyle that feels slightly more authentic to the subject's established look.

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 [dev] Turbo
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent photographic texture with realistic-looking salmon and rice grains.
  • + Perfectly clean and bold typography that integrates naturally with the flag icon.
  • + Strong adherence to the diorama base request with a solid wooden platform.
  • Lighting is slightly more realistic and less 'cartoon' than requested in the prompt.
  • The ginger garnish on top of the nigiri is a bit unusual in presentation.

Wan 2.7 Pro

  • + Perfectly captures the requested 3D cartoon miniature aesthetic with soft, rounded forms.
  • + Includes more variety of sushi types while maintaining an ultra-clean layout.
  • + Colors are vibrant and fit the 'soft refined textures' prompt very well.
  • Typography contains extra unrequested text ('Authentic Japanese Cuisine').
  • Random small debris/dots in the top corners and bottom area distract from the 'clean' background.

Verdict: FLUX.2 [dev] Turbo excels in realistic PBR materials and clean typography, producing a high-quality product-style render. However, Wan 2.7 Pro better captures the specific '3D cartoon miniature' aesthetic requested while offering a more diverse plate of sushi. Wan 2.7 Pro is the slight winner for its superior interpretation of the cartoon style and composition, despite some minor background artifacts.

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 [dev] Turbo
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent caricature style with exaggerated head and facial features that still clearly resemble the source subject.
  • + Creative and complex composition integrating a news desk, a hockey rink, and numerous dogs seamlessly.
  • + High-quality rendering with detailed background screens showing hockey players and dogs.
  • The text on the news desk is nonsensical gibberish.

Wan 2.7 Pro

  • + Successfully incorporates all elements including the anchor suit, dogs, and hockey references.
  • + Correctly renders legible text within speech bubbles.
  • The facial likeness is significantly weaker than the other model, losing much of the original woman's character.
  • The 'hockey' element is represented by a strange hybrid microphone-stick that looks awkward.
  • The composition is much simpler and lacks the 'big energy' of a professional caricature.

Verdict: FLUX.2 [dev] Turbo produced a superior caricature that maintains a strong likeness to the original subject while perfectly balancing the requested themes of hockey, dogs, and TV news in a vibrant, professional-looking illustration. Wan 2.7 Pro's result feels more generic, with a less accurate facial likeness and a clunky visual metaphor for the hockey stick.

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 [dev] Turbo
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent adherence to the 'tumbling' and 'playful' aspect of the prompt
  • + Beautiful rendering of dew drops and god rays contributing to the atmosphere
  • + Superior facial expressions that look joyful and well-structured
  • The fox kit's fur texture appears slightly over-sharpened compared to the other animals

Wan 2.7 Pro

  • + Strong implementation of god rays and backlight coming through the grass
  • + Good textural detail on the puppy's fur
  • + Includes a nice variety of butterfly colors and types
  • The fox kit has anatomical issues, especially with the placement of its paws and neck
  • The kitten's pose is stiff and less integrated into the scene
  • Lacks the 'tumbling together' interaction requested in the prompt

Verdict: FLUX.2 [dev] Turbo produced a far more cohesive and joyful scene, successfully capturing the interaction between all four animals as they tumble together. Wan 2.7 Pro struggled with animal anatomy, particularly on the fox, and the animals feel like separate elements placed in a field rather than a single interacting group.

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 [dev] Turbo
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Captures the Studio Ghibli art style perfectly with soft linework and expressive eyes.
  • + Includes Ghibli-esque environmental details like cherry blossoms and whimsical background characters.
  • + Excellent texture work that mimics hand-painted watercolor and colored pencils.
  • The color palette is slightly desaturated compared to the source image.

Wan 2.7 Pro

  • + Retains the original facial structures and expressions more accurately.
  • + Successfully applies a watercolor texture across the entire image.
  • + Preserves the original background architecture better than Model A.
  • Does not fully commit to the 'Studio Ghibli' style, looking more like a standard watercolor filter.
  • Lacks the 'dreamy' and 'magical' atmosphere requested in the prompt.

Verdict: FLUX.2 [dev] Turbo followed the 'Studio Ghibli' instruction much more effectively, transforming the scene into a true illustration with stylized features and thematic background elements. Wan 2.7 Pro essentially just applied a watercolor texture to the source image, failing to capture the specific artistic essence of the requested anime style.

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 [dev] Turbo
Before After
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent source preservation, maintaining identical character features and background
  • + Effectively adds a large volume of flying leaves
  • + Clearly shows hair blowing outwards in response to the wind
  • The hair edit looks slightly artificial with very symmetrical movement
  • The quantity of leaves feels a bit overwhelming and uniform in size

Wan 2.7 Pro

  • + More natural, varied hair motion that looks integrated with the original style
  • + Better lighting integration on the flying leaves
  • + Perfectly preserves the woman and dog from the original image
  • Fewer leaves added compared to the edit request for an energetic feel
  • Slightly less dramatic motion in the environment overall

Verdict: Both models performed excellently in terms of source preservation, keeping the woman, dog, and background almost perfectly intact. FLUX.2 [dev] Turbo provided a more literal interpretation of 'lively' by adding many more leaves, but Wan 2.7 Pro achieved a more realistic and aesthetically pleasing motion in the woman's hair.

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 [dev] Turbo
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Perfect text rendering of the name including the grave accent.
  • + Excellent adherence to the minimalist, vector emblem request.
  • + Authentic vintage texture on the background and logo.
  • The cloche design is slightly simplistic compared to the rest of the logo.

Wan 2.7 Pro

  • + Sophisticated illustration style for the cloche and laurel wreath.
  • + Includes additional thematic text such as Venezia Italia that adds to the brand story.
  • + Detailed circular emblem composition.
  • Misses the spelling of the name, rendering it as Caffè Florion.
  • The corners are cluttered with unrelated floating assets like coffee beans and cinnamon sticks.
  • Less minimalist than requested.

Verdict: FLUX.2 [dev] Turbo is the clear winner for its perfect spelling and adherence to the 'minimalist' and 'vector emblem' constraints. While Wan 2.7 Pro offers a beautiful, more detailed illustration, it fails on basic prompt adherence by misspelling the brand name as 'Florion'.

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 [dev] Turbo
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent typography and name spelling for the astronauts.
  • + Highly detailed illustrations of the Saturn V and Lunar Module.
  • + Includes creative extra details like the Sea of Tranquility landing site and astronaut silhouettes.
  • The layout is cluttered and non-linear, making the flow difficult to follow.
  • The iconography is inconsistent, mixing 3D-shaded elements with flat vector styles.
  • Includes redundant labels and floating text elements.

Wan 2.7 Pro

  • + Perfect clean, modern vector aesthetic with consistent iconography.
  • + Strong logical flow in a vertical timeline format.
  • + Highly accurate adherence to the requested NASA-inspired color palette and 'flat-vector' style.
  • Small typo in 'DESCRIPT' instead of 'DESCENT'.
  • The astronaut icons are generic stick figures compared to the detailed silhouettes in the other model.
  • The Lunar Module icon is a bit abstract.

Verdict: While FLUX.2 [dev] Turbo produces much more detailed and accurate illustrations of the actual spacecraft and astronauts, Wan 2.7 Pro is the superior choice for the specific prompt. Wan 2.7 Pro successfully captured the 'clean, modern vector infographic' style with a clear, professional layout and consistent icon sets, whereas FLUX.2 [dev] Turbo created a cluttered collage of high-quality but disjointed images.

Next steps

Explore each model