Head to head
Esc

Models · slot A

to navigate to pick

FLUX.2 [dev] 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 [dev]

24.5 arena score

#18 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]

0%

win rate

Ties

0%

Wan 2.7 Pro

0%

win rate

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]
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent photographic realism and lighting consistency.
  • + Highly accurate glass refraction and reflection on the table.
  • + Perfect adherence to the spatial arrangement of objects.
  • The glass cube has very thick edges that look slightly more like a frame than a solid glass object.

Wan 2.7 Pro

  • + Naturalistic fern rendering with complex visibility through the glass.
  • + The wooden table texture is very detailed and realistic.
  • + Matches all prompt instructions including object placement and lighting.
  • Internal reflections and refractions inside the cube are slightly messy and less physically accurate than Model A.
  • The blue sphere has a slightly matte/stone texture instead of a smooth orb appearance.

Verdict: Both models followed the prompt perfectly, including the complex request for a plant to be visible through a glass cube. FLUX.1 [dev] is the winner due to its superior handling of light, glass transparency, and more coherent object physics, whereas Wan 2.7 Pro's internal glass reflections are a bit cluttered.

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]
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent preservation of the subject's unique clothing and hairstyle from the source.
  • + High interior detail that matches the luxurious aesthetic of the source car.
  • + Dynamic composition with a sense of motion and realistic coastal background.
  • The steering wheel and dashboard details become slightly organic and warped.
  • Loss of the car's exterior profile compared to Model B's wider shot.

Wan 2.7 Pro

  • + Perfectly preserves the exterior of the car from the source image.
  • + Shows the full context of the car driving on the coastline road.
  • Completely fails to use the man provided in the source image, replacing him with a generic figure.
  • The lighting on the car doesn't fully match the warm sunset background.

Verdict: FLUX.2 [dev] is the clear winner because it successfully integrates both source elements—the specific man and the specific car—into a single coherent scene. While Wan 2.7 Pro preserves the car well, it completely ignores the second source image and inserts a random person, failing the primary objective of the edit challenge.

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]
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent adherence to the 'motion blur from passing cars' prompt
  • + Very realistic skin and hand textures with natural aging details
  • + More cinematic lighting and effective use of shallow depth of field
  • The structural complexity of the handlebars is a bit chaotic and physically nonsensical

Wan 2.7 Pro

  • + Clearer depiction of the entire bicycle and its reflection on the wet pavement
  • + Good facial detail and culturally appropriate attire
  • Failed to include the requested motion blur for passing cars
  • The framing feels too centered and tidy for a 'candid' street photo with 'imperfect framing'
  • The lighting is flat compared to the requested cinematic style

Verdict: FLUX.2 [dev] followed the technical requirements of the prompt much better, specifically capturing the motion blur and the atmospheric, imperfect feel of a candid street photograph. Wan 2.7 Pro produced a clean, stationary image that ignored several stylistic instructions and lacked the cinematic depth of the first image.

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]
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent adherence to the request for ornate engraved plate armor with high-contrast floral patterns.
  • + Superior lighting and depth of field, with very distinct bokeh sparks that add movement to the scene.
  • + Highly detailed texture on leather straps, including visible wear and stitch marks.
  • The scars on the forehead look slightly like surface-level paint rather than deep tissue injuries.
  • The braids look a bit thin and contemporary compared to the historical paladin aesthetic.

Wan 2.7 Pro

  • + Very realistic scarring and skin texture that better captures the 'battle-worn' descriptor.
  • + The hair braids with beads are expertly integrated into the hairstyle and look historically grounded.
  • + Solid rendering of the warm torchlight reflecting off the metal surfaces.
  • The plate armor engraving is slightly less detailed and crisp than in Model A.
  • The background bokeh is a bit busier and less clean than Model A's composition.

Verdict: Both models performed exceptionally well on this prompt. FLUX.2 [dev] produced a more visually striking image with superior armor engraving and more dynamic lighting sparks. However, Wan 2.7 Pro delivered a more convincing 'battle-worn' look with superior skin texture, realistic scarring, and better-integrated hair beads, making it slightly more faithful to the spirit of the character.

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]
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent use of grid-based layout for product photography
  • + Strong adherence to section labels like Appetizers, Pizza, and Mains
  • + Vibrant color accents and clean typography
  • Nonsense filler text and misspelled headers like 'Pizzau'
  • Slightly cluttered visual balance on the second page

Wan 2.7 Pro

  • + Highly legible and realistic text rendering
  • + Professional composition featuring mock-up elements like a pen and napkin
  • + Cleanest interpretation of the 'modern minimalist' aesthetic
  • The 'colorful food photos' are not in a strict grid as requested
  • Minor spelling errors in smaller body text
  • The layout is a single-page flyer rather than a traditional menu spread

Verdict: Wan 2.7 Pro produces a significantly more professional and realistic menu with readable text and a cohesive brand identity. While FLUX.2 [dev] follows the grid structure prompt more closely, its failure to generate sensible words and the presence of severe artifacts in the text makes Wan 2.7 Pro the better choice for a design-related task.

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]
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent typography integrated naturally into the fiery atmosphere
  • + Highly realistic textures on the meat patty and fresh vegetables
  • + Superior lighting and glowing effects that enhance the 'magic' theme
  • The burger components are somewhat stacked rather than fully 'exploded' or scattered

Wan 2.7 Pro

  • + Stronger sense of 'exploded' motion with components flying laterally
  • + Includes additional details like cucumbers and herbs not specifically requested but adding to the variety
  • Text rendering is slightly inconsistent with the fire effect looking like a clip-art border
  • The meat patty appears somewhat flat and less appetizing compared to Image A
  • The composition feels a bit cluttered with small floating leaves

Verdict: FLUX.2 [dev] produced a much more professional advertisement with superior lighting, photorealistic textures, and cohesive typography that feels part of the scene. While Wan 2.7 Pro captured the 'exploded' motion better, its visual quality and font integration appear less refined than FLUX.2 [dev].

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]
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev]

  • + Features a highly realistic chalk texture with dusty smudges and varying pressure.
  • + Correctly interprets the 'Brown Butter' item as 'Cookies' even with a truncated prompt.
  • + The handwriting looks organic and authentically hand-drawn.
  • Slightly messy layout with some text overlapping erased-looking areas.
  • The bottom text line has some minor warping in perspective.

Wan 2.7 Pro

  • + Clean, well-balanced composition and clear readability.
  • + Accurately rendered all requested text including the truncated final item.
  • + Excellent focus and lighting in the surrounding cafe environment.
  • The text looks more like a digital font than natural, textured chalk handwriting.
  • Lack of chalk dust and grain makes the board look too sterile and artificial.

Verdict: FLUX.2 [dev] captures the requested chalk texture and authentic handwriting style much better than Wan 2.7 Pro, featuring realistic smudges and varied letterforms. While Wan 2.7 Pro has a cleaner layout, its text appears too clean and digital, failing the 'handwritten-style' and 'chalk texture' requirements of the prompt.

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]
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev]

  • + Successfully integrated the clothing (scarf, black sweater) from Image 2
  • + Accurately captured the face and sunglasses of the character from Image 2
  • Grave anatomical errors, including a floating secondary head and missing limbs
  • The pose is not an exact match, with a leg disconnected from the body

Wan 2.7 Pro

  • + Perfectly preserved the background and pose from Image 1
  • Completely ignored the instruction to use the character from Image 2
  • Failed to make any edits to the original subject

Verdict: This task is a comparison between a model that attempted the edit but failed significantly in execution and one that failed to perform the edit at all. FLUX.2 [dev] managed to bring in the correct character, clothing, and accessories from Image 2, but created a nonsensical composition with floating body parts and two heads; meanwhile, Wan 2.7 Pro simply returned a slightly modified version of Image 1, ignoring the character swap entirely.

The Reversed Rodeo

Text-to-Image

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

FLUX.2 [dev]
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent cinematic lighting and atmospheric integration
  • + High level of detail on the space suit and horse textures
  • + Dynamic pose with a sense of motion
  • The astronaut's feet are poorly positioned relative to the stirrups
  • Anatomical oddity where the horse's back right leg and tail merge

Wan 2.7 Pro

  • + Clear and sharp rendering of all elements
  • + Better grounding of the astronaut on the horse's saddle
  • + Creative depiction of floating planets
  • The composition feels more like a collage than a cinematic scene
  • The horse's front right leg is missing its lower half/hoof
  • Lighting is flat and lacks the 'cinematic' feel requested

Verdict: Both models failed the negative constraint to have the horse on top of the astronaut, instead providing the literal 'astronaut riding a horse' interpretation. FLUX.2 [dev] is the winner due to its superior cinematic lighting and textural detail, whereas Wan 2.7 Pro features a significant anatomical glitch with a missing limb and flatter composition.

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]
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev]

  • + Accurately replicates the outfit, including the specific plaid scarf, blue coat, and sunglasses from Image 2.
  • + Maintains the sand patterns and general look of the source hair.
  • Failed to preserve the source person's face, merging the features of the person in Image 2 onto the base person.
  • Drastically changed the pose and frame of the original image, cropping in significantly.

Wan 2.7 Pro

  • + Preserved the person's original face, body, and overall scene composition much better than the other model.
  • + Correctly applied the full body crop and included shoes as requested.
  • Completely failed to use the outfit from Image 2, instead generating a random gold-patterned jacket.
  • The skin texture on the hand appears distorted and unnatural.

Verdict: Both models failed significantly on key instructions: FLUX.2 [dev] successfully copied the outfit but completely replaced the subject's face and changed the pose, whereas Wan 2.7 Pro preserved the subject's face and scene but failed to use the correct outfit. FLUX.2 [dev] is slightly preferred for adhering to the difficult outfit-matching part of the prompt, despite failing the person-preservation constraint.

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]
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent photographic lighting and depth of field
  • + High resolution texture on the capybara's fur
  • + Character expressions perfectly match the prompt's request for 'calm' and 'bored'
  • The paws are rendered more like human/primate hands than authentic capybara feet
  • The 'T' on the hat looks a bit like a modern logo rather than a classic taxi badge

Wan 2.7 Pro

  • + Strong composition showing both the internal and external environment clearly
  • + Realistic depiction of a city street reflected in the window
  • + Accurate seatbelt and interior taxi details
  • The capybara's head looks somewhat superimposed onto a human body
  • The hands have an unsettling, overly-lengthy primate-like appearance
  • The passenger is looking slightly past her phone rather than directly at the screen

Verdict: FLUX.2 [dev] produces a more convincing and aesthetically pleasing image with superior lighting and fur texture. While Wan 2.7 Pro handles the background geometry well, its blending of the capybara head onto a human-proportioned torso feels less organic than the well-integrated animal figure in FLUX.2 [dev].

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]
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent typography rendering with zero errors in the text.
  • + Strong gothic atmosphere with high contrast and cinematic lighting.
  • + Perfect adherence to the 'dark parchment' and 'webs and thorns' border description.
  • The composition is a bit more simplistic and centered compared to the other model.

Wan 2.7 Pro

  • + Beautifully intricate illustration style with high visual interest.
  • + Great use of color and lighting, especially with the lanterns and twilight sky.
  • + Includes creative extra details like the cauldron and 'Est. 1847' that fit the theme well.
  • The font choice for 'Halloween Party Invitation' is slightly inconsistent across letters.
  • The thorn/web border is less prominent than requested in the prompt.

Verdict: FLUX.2 [dev] followed the text requirements with perfect precision and captured a much more accurate 'gothic' and 'dark' mood as requested. While Wan 2.7 Pro produced a more detailed and colorful illustration, FLUX.2 [dev] is the superior invitation due to its cleaner layout and flawless text rendering.

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]
Before After
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent preservation of the source image background and clothing
  • + High level of hair detail and texture
  • The hair choice (large afro) feels inconsistent with the subject's existing beard and aesthetic
  • The hair is so large it creates a slight mismatch in lightning on the surrounding edges

Wan 2.7 Pro

  • + Natural, realistic hair style that perfectly matches the subject's beard and aged appearance
  • + Flawless integration of the hair with the existing facial features and glasses
  • + Excellent preservation of the original image's lighting and background
  • None notable; the edit is highly seamless

Verdict: While both models successfully added hair while preserving the underlying image, Wan 2.7 Pro provided a much more realistic and aesthetically coherent result. FLUX.2 [dev] opted for a massive afro that, while detailed, looks artificial and mismatched for the subject, whereas Wan 2.7 Pro created a believable, natural hairline and style that looks like it belonged to the original photo.

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]
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev]

  • + Follows the diorama base instruction accurately with a distinct raised platform.
  • + Clean and minimalist layout that matches the prompt's aesthetic.
  • + Excellent text rendering and placement for both words and the flag icon.
  • The sushi textures are a bit soft, leaning more towards clay than PBR materials.
  • The shadow on the base plate is slightly harsh compared to the 'gentle lighting' request.

Wan 2.7 Pro

  • + Outstanding PBR materials with realistic subsurface scattering on the fish and ikura.
  • + High visual appeal with a more polished 3D cartoon/commercial aesthetic.
  • + Includes thoughtful details like chopsticks and soy sauce that add to the scene's completeness.
  • Adds extra text 'Authentic Japanese Cuisine' and floating particles not requested in the prompt.
  • The 'diorama base' is interpreted more as a thick plate rather than a diorama platform.

Verdict: Both models followed the prompt closely, but FLUX.2 [dev] stayed truer to the specific structure of a 'raised diorama base'. However, Wan 2.7 Pro produced significantly higher quality textures and PBR materials, making the sushi look much more appetizing and professional. Wan 2.7 Pro is the winner for its superior visual fidelity and adherence to the 3D toy/miniature style.

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]
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent caricature style with professional-level shading and line work.
  • + Seamlessly integrates all prompt elements including numerous dogs, hockey sticks, a rink setting, and news anchor set.
  • + Strong facial similarity to the source image while maintaining the caricature exaggeration.
  • The text on the anchor desk is garbled and illegible.
  • Includes an extra character in the top left not requested in the prompt.

Wan 2.7 Pro

  • + Successfully captures the requested themes with clear speech bubbles.
  • + Creative 'hockey stick microphone' hybrid tool.
  • + Good preservation of the subject's distinctive smile and facial features.
  • The art style is a basic vector illustration rather than a classic exaggerated caricature.
  • The hockey theme is limited to text bubbles and a jersey on a dog rather than setting the scene.
  • Anatomy issues with the hand holding the stick.

Verdict: FLUX.2 [dev] followed the 'caricature' instruction much more effectively, producing a high-quality, detailed scene that placed the user in a rich environment combining her job and hobbies. While Wan 2.7 Pro correctly identified the key elements, its execution felt more like a flat clip-art illustration and relied on text bubbles to explain its themes rather than visual storytelling.

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]
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent backlighting and rim light effect on fur
  • + Higher level of fine detail in the fur texture and whiskers
  • + More realistic and soft 'god rays' through the background trees
  • Generated an extra animal (two bunnies instead of one)
  • Animals are sitting relatively still rather than 'tumbling together'

Wan 2.7 Pro

  • + Better adherence to the dynamic action of 'tumbling together' and 'playfully chasing'
  • + Correct count of animals as specified in the prompt
  • + Vibrant colors and well-defined dew sparkles on the grass
  • Anatomy issues with the kitten's front paws resting on the puppy
  • The fox's face looks slightly more mature than a 'kit'
  • The golden retriever's back legs looks slightly awkward or disconnected

Verdict: FLUX.2 [dev] produces a more 'masterpiece' quality image with superior lighting and fur texture, though it failed the negative constraint of animal count by adding a second bunny. Wan 2.7 Pro better captured the playful movement and specific animal list, but suffered from minor architectural glitches where animals overlap and slightly less realistic lighting.

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]
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent Ghibli-inspired art style with smooth shading and characteristic eye shapes
  • + Applies the 'dreamy background' instruction by adding flowers and a soft sky
  • + Strong source preservation of the character poses and clothing patterns
  • The change of background from a city to a field reduces the specific 'distracted boyfriend' meme context

Wan 2.7 Pro

  • + Strong hand-painted watercolor texture feeling
  • + Excellent source preservation of the background city layout and lighting
  • + Maintains the specific expressions from the original meme accurately
  • The art style is more generic watercolor than specifically Studio Ghibli-inspired
  • Lower resolution/more fuzzy details on the faces compared to Model A

Verdict: FLUX.2 [dev] followed the aesthetic prompt more precisely, delivering the characteristic linework and soft coloring associated with Studio Ghibli, though it did alter the background to a field. Wan 2.7 Pro better preserved the original scene's urban setting and textures but leans more toward a generic watercolor illustration than the requested Ghibli 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]
Before After
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent preservation of the subject's face and clothing
  • + Highly realistic wind effect on the hair
  • + Detailed and abundant blowing leaves
  • Some leaves appear unnaturally small or look like dirt spots in certain areas

Wan 2.7 Pro

  • + Natural integration of leaves in the foreground and on the grass
  • + Good preservation of the original scene's colors and lighting
  • The hair edit is less convincing and looks slightly more static compared to Model A
  • Occasional artifacting on the leaves where they overlap the subject

Verdict: Both models did an excellent job of preserving the source image while applying the requested edits. FLUX.2 [dev] is the winner because the application of motion to the hair is much more dynamic and realistic, truly capturing the 'wind' effect better than Wan 2.7 Pro.

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]
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent typography that perfectly matches the requested name and accent.
  • + Clean, vector-style execution suitable for an actual logo.
  • + Strong minimalist composition with a well-balanced banner.
  • The 'subtle texture' on the background is very faint.

Wan 2.7 Pro

  • + Beautifully detailed engraving style for the cloche and steam.
  • + Elegant use of gold-toned accent and borders.
  • + Included additional thematic elements like coffee beans and wax seals in the corners.
  • Misspelled the name as 'Florion' instead of 'Florian'.
  • The composition is a bit crowded and less minimalist than requested.
  • The 'EST. 1720' text is slightly off-center within its banner.

Verdict: FLUX.2 [dev] is the clear winner as it followed all prompt instructions perfectly, including the correct spelling of 'Florian' and adhering to a minimalist vector style. While Wan 2.7 Pro offers a more ornate and aesthetically pleasing illustration, the spelling error and lack of minimalism make it less successful as a 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 [dev]
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent detailed illustrations of the Saturn V and Lunar Module.
  • + Good use of the requested color palette.
  • + Crisp text for main headers.
  • The sequence is jumbled and does not follow a logical 1-6 order.
  • Contains significant text gibberish such as 'UAJSIST ORDIT' and 'LTUREST LIAMDIIES'.
  • Includes redundant or misplaced landing icons.

Wan 2.7 Pro

  • + Perfect logical flow of information following the 6 requested steps in order.
  • + Excellent flat vector style that feels like a cohesive professional infographic.
  • + Very accurate text rendering with specific mission details and dates.
  • One 'Descent' label is slightly cut off as 'DESCRIPT'.
  • The Earth icon uses red continents which is a bit non-traditional for a NASA palette.

Verdict: Wan 2.7 Pro followed the instructions perfectly, creating a logical vertical timeline with consistent iconography and highly accurate text. FLUX.2 [dev] produced higher detail individual illustrations but failed on the layout, resulting in a confused grid with multiple spelling errors and no clear sequence.

Next steps

Explore each model