Black Forest Labs' enhanced 12-billion parameter flow transformer with 6x faster generation than FLUX.1 [pro], delivering superior composition, detail, and artistic fidelity
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
FLUX1.1 [pro]
#50 of 62 in Text-to-Image
Wan 2.7 Pro
#37 of 62 in Text-to-Image
Where the votes landed
FLUX1.1 [pro]
0%
win rate
Ties
0%
Wan 2.7 Pro
0%
win rate
Challenge by challenge
The strongest take from each model on every shared challenge, with the AI judge's read.
Geometric Composition
Text-to-Image“A glass cube on a wooden table. Inside the cube is a small blue sphere. On top of the cube sits a red book. A green plant is behind the cube, partially visible through the glass. Soft window light from the left.”
AI Judge Analysis
FLUX1.1 [pro]
- + Features very sharp and clear glass reflections.
- + Excellent lighting consistency on the sphere and surface.
- + High-quality texture on the red book cover.
- − The 'cube' is actually a tall rectangular prism, failing the geometry aspect of the prompt.
- − The sphere is levitating, which might not have been the intended physics.
Wan 2.7 Pro
- + Correctly adheres to the 'cube' shape requested.
- + The plant is clearly visible through the glass as requested.
- + The wooden table texture is very realistic and rustic.
- − The glass has some internal edge artifacts that look slightly messy.
- − The blue sphere has a mottled texture that looks less like a simple 'blue sphere'.
Verdict: Both models followed the complex spatial instructions well. Wan 2.7 Pro is the winner because it correctly interpreted the cube shape, whereas FLUX1.1 [pro] generated a tall rectangular box; Wan 2.7 Pro also provided a more natural-looking environment with a clearly visible window and realistic table texture.
Candid Street Photography
Text-to-Image“A candid street photo of an elderly Japanese man repairing a red bicycle in light rain, reflections on wet pavement, shallow depth of field, 50mm lens, natural skin texture, imperfect framing, motion blur from passing cars, cinematic but realistic, no stylization.”
AI Judge Analysis
FLUX1.1 [pro]
- + Captures the cinematic atmosphere and night-time lighting well
- + Creative use of bokeh and wet pavement reflections
- + Follows the motion blur and 50mm lens prompt cues
- − Serious anatomical and structural failure with the bicycle and subject's lower body
- − The man appears to be floating or merged with a missing bike frame
- − Lack of clear rainy texture
Wan 2.7 Pro
- + Excellent anatomical realism and skin texture
- + High structural integrity for the bicycle and background vehicles
- + Clearly depicts the light rain falling as requested
- − Lacks the motion blur of passing cars requested in the prompt
- − Composition is very clean and centered, missing the 'imperfect framing' requested
- − The pavement is wet, but the light reflections are less cinematic than Image A
Verdict: FLUX1.1 [pro] better captured the moody, cinematic atmosphere and motion blur described in the prompt, but it failed significantly on a technical level with a mangled bicycle and nonsensical character anatomy. Wan 2.7 Pro provided a much more coherent and realistic scene with high physical accuracy, although it ignored the motion blur and imperfect framing requirements. Wan 2.7 Pro is preferred overall because it delivers a usable, high-quality image without the disturbing structural artifacts seen in the FLUX output.
Fantasy Warrior
Text-to-Image“Close portrait of a battle-worn paladin in ornate engraved plate armor, hair braided with small beads, faint scars and dirt on the skin, warm torchlight reflecting off metal, shallow depth of field, bokeh sparks, lifelike eyes, highly detailed texture on leather straps and cloth underlayer.”
AI Judge Analysis
FLUX1.1 [pro]
- + Intense, high-fidelity skin textures and lifelike iris detailing
- + Dynamic close-up crop that emphasizes the warrior's expression
- + Exceptional use of bokeh sparks and warm lighting highlights
- − Hair braiding and beads are less distinct than requested
- − Armor engraving is partially obscured by the framing
Wan 2.7 Pro
- + Excellent adherence to hair details including braids and colored beads
- + Highly detailed and clear engraving on the plate armor
- + Shows more variety of materials including clear leather straps and cloth layers
- − Lighting feels slightly more flat and studio-like compared to the intense atmosphere of A
- − The skin texture and eyes are less lifelike than the competitor
Verdict: FLUX1.1 [pro] excels in raw visual impact and photographic realism, particularly in the eyes and skin texture, though it misses some specific hair details. Wan 2.7 Pro provides a more literal interpretation of the prompt, successfully incorporating the braided beads, elaborate armor engravings, and leather straps in a clear, well-composed medium-close shot.
Modern Clean Menu
Text-to-Image“Modern minimalist restaurant menu design, white background with colorful food photos in grid, sections for appetizers/pizza/mains, bold sans-serif fonts, vibrant accents, clean professional layout for casual dining.”
AI Judge Analysis
FLUX1.1 [pro]
- + Strong minimalist aesthetic with high-quality product photography
- + Elegant use of negative space and clean sans-serif typography on the main menu
- + Realistic lighting and shadows for the surrounding cutlery props
- − Text rendering is poor with many garbled letters and nonsensical names
- − The grid layout of images feels a bit cramped at the bottom compared to the top half
Wan 2.7 Pro
- + Excellent typography rendering with readable fonts and coherent menu item names
- + Highly organized grid layout that clearly follows the request for specific food sections
- + Professional UI/UX elements like a QR code and social media icons
- − The composition feels slightly more like a flyer or digital interface than a physical menu
- − A few minor spelling errors in small body text like 'Loided Jachos'
Verdict: Wan 2.7 Pro is the clear winner as it produces a highly functional and legible design with impressive text adherence, creating a realistic menu layout. While FLUX1.1 [pro] captures a more artistic minimalist mood, its text is largely illegible which makes it less useful for a design-related prompt.
Magic Burger Explosion: Fiery Photorealism Challenge
Text-to-Image“Ad for 'Magic Burger'. Dynamic, exploded burger with all components (bun, patty, cheese, lettuce, tomato, sauce) suspended in mid-air. Emphasize photorealistic detail and a sense of motion. Dark, fiery background with glowing embers. Integrate text: 'MAGIC BURGER' as a prominent title, 'LIMITED TIME ONLY' as a secondary message, and '€6.99' in a starburst, all rendered with a fiery, glowing effect.”
AI Judge Analysis
FLUX1.1 [pro]
- + Excellent photorealistic lighting and depth of field
- + Clean, professional typography with a modern neon style
- + Dynamic motion blur on background particles adds to the sense of action
- − Failed to 'explode' the burger; it remains a solid structured stack
- − Missing the starburst element for the price point
- − Price text is not rendered with the requested fiery, glowing effect
Wan 2.7 Pro
- + Perfectly followed the 'exploded burger' instruction with all components separated
- + Accurately included the starburst element and fiery text effects as requested
- + Visual composition is vibrant and matches a commercial ad layout very well
- − Texture of the cheese appears slightly flat or artificial
- − Some minor clipping on the fiery text at the top edge of the frame
Verdict: Wan 2.7 Pro followed the complex prompt instructions much more accurately, successfully delivering the exploded view, the starburst, and the fiery text effects. While FLUX1.1 [pro] produced a more photorealistic image with better lighting, it failed to separate the burger components or include the specific graphic design elements requested.
Chalkboard Menu
Text-to-Image“Handwritten-style chalkboard menu in a cozy café, all text rendered in the exact same realistic chalk handwriting style with natural variations in letter size, slight slant, and chalk texture — no printed or digital fonts anywhere on the board. Title at the top in elegant cursive chalk handwriting: ‘TODAY’S SPECIALS – APRIL 30, 2026’. Below it, three menu items also in the same handwritten chalk style: ‘Truffle Mushroom Risotto – $24’, ‘Grilled Octopus with Lemon & Herbs – $28’, ‘Brown Butter Chocolate Chip Cookies – $9’. At the very bottom, smaller text in the identical handwritten chalk style (slightly smaller but still clearly legible with the same handwriting characteristics): ‘All items made fresh daily • Ask about our gluten-free options’. Warm ambient café lighting, visible chalk dust and smudges, realistic handwriting imperfections, no clean printed text anywhere.”
AI Judge Analysis
FLUX1.1 [pro]
- + Excellent chalk-like texture on the lettering
- + Natural-looking handwriting style with believable variations
- − Failed to render the full names of the items correctly, repeating and hallucinating prices
- − The text layout is uneven and messy compared to the prompt requirements
Wan 2.7 Pro
- + Perfect adherence to the complex menu text and pricing
- + Beautiful composition with a very authentic chalk dust texture on the board surface
- + Consistently high quality across all letters and numbers
- − The handwriting style is slightly more uniform than requested, though still hand-drawn
- − Small spacing issues between some of the characters in the body text
Verdict: Wan 2.7 Pro followed the text instructions perfectly, including the specific prices and long menu item names, whereas FLUX1.1 [pro] struggled with the text content, repeating the octopus item and failing to complete the third item. Wan 2.7 Pro also provided a more cohesive and realistic chalkboard aesthetic.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
AI Judge Analysis
FLUX1.1 [pro]
- + Cinematic lighting and atmospheric effects enhance the requested surreal mood.
- + Excellent level of high-frequency detail in the space suit and horse's mane.
- − Failed the logical constraint of the prompt; the astronaut is riding the horse.
- − The horse's anatomy becomes messy near the rear and chest.
Wan 2.7 Pro
- + Crisp image quality with clean subject rendering.
- + Effective placement of celestial bodies in the background.
- − Completely ignored the specific negative constraint that the horse should be on top.
- − Composition is relatively generic for this common AI art trope.
Verdict: Both models failed the specific logical reversal requested in the prompt ('horse on top, not vice versa'), instead delivering the standard 'astronaut riding a horse' trope. FLUX1.1 [pro] is slightly preferred for its superior cinematic lighting and more detailed, surreal atmosphere compared to the flatter presentation of Wan 2.7 Pro.
The Capybara Taxi Driver
Text-to-Image“Photorealistic scene inside a yellow New York taxi at night. A capybara is driving, wearing a yellow taxi driver cap and a dark jacket. It has a calm, professional expression and both front paws on the steering wheel. In the back seat sits a human businesswoman in a coat, looking at her phone with a completely normal, bored expression (as if this is just another normal ride). Through the windows you can see the streets of Manhattan at night with blurred lights. Realistic taxi interior, photorealistic, detailed fur and fabric, 35mm lens, night lighting with reflections, shallow depth of field.”
AI Judge Analysis
FLUX1.1 [pro]
- + Excellent atmospheric lighting and bokeh effect on the background lights
- + The capybara's professional expression and clothing are well-rendered
- + Rich, cinematic color palette that fits a New York night scene
- − Failed the spatial layout by putting the passenger in the front seat next to the driver
- − The steering wheel is missing or obscured by the capybara's fur/pose
- − The capybara's paws are not visible on a steering wheel
Wan 2.7 Pro
- + Accurately followed the spatial layout with the passenger in the back and driver in the front
- + Good depiction of the capybara's paws on the steering wheel
- + Very realistic taxi exterior and Manhattan street environment
- − The capybara's paws look slightly more like primate hands with longer fingers
- − The passenger's face is somewhat blurry and less detailed than the driver
- − The composition is a bit tight on the left side
Verdict: Wan 2.7 Pro followed the complex spatial instructions much better by placing the woman in the back seat and showing the capybara's paws on the steering wheel. While FLUX1.1 [pro] has superior artistic lighting and textures, it failed the fundamental layout by placing both characters in the front seat.
The Halloween Invitation
Text-to-Image“Vintage gothic Halloween party invitation. Dark parchment poster, spooky border with webs and thorns, central glowing jack-o-lantern, bats, twisted trees, moody night sky. Add elegant gothic title text saying "Halloween Party Invitation", a small scroll banner saying "You are invited to a night of frights", and event details at the bottom: Date: 30.10.2026 Time: 7pm Location: The Arches, NYC Spooky but polished, cinematic lighting, square format.”
AI Judge Analysis
FLUX1.1 [pro]
- + Excellent cinematic lighting and moody atmospheric colors
- + High-quality central jack-o-lantern rendering
- + Follows the dark parchment and thorny border prompt well
- − Serious text rendering issues including typos and repetition of fields
- − The 'elegant gothic title' was split into two different lines/sections
- − The composition feels slightly bottom-heavy with blank space
Wan 2.7 Pro
- + Perfect text rendering for all requested details including the scroll banner
- + Rich, detailed composition with webs, thorns, and extra gothic elements
- + Excellent alignment with the 'vintage gothic' and 'polished' aesthetic
- − The overall image style leans more toward illustration than 'cinematic' photography
- − The sky colors are a bit more vibrant/warm than the 'moody night sky' requested
Verdict: Wan 2.7 Pro is the clear winner for this design task because it successfully rendered all requested text with 100% accuracy, whereas FLUX1.1 [pro] struggled with typos and repetitive lines. While FLUX1.1 [pro] offered more cinematic lighting, Wan 2.7 Pro provided a more complete and professional-looking invitation layout that met every requirement of the prompt.
Isometric Miniature Diorama Scenes
Text-to-Image“Create a clear, 45° top-down isometric miniature 3D cartoon scene of Japan's signature dish: sushi, with soft refined textures, realistic PBR materials, gentle lighting, on a small raised diorama base with minimal garnish and plate. Solid light blue background. At top-center: 'JAPAN' in large bold text, 'SUSHI' below it, small flag icon. Perfectly centered, ultra-clean, high-clarity, square format.”
AI Judge Analysis
FLUX1.1 [pro]
- + Excellent soft 3D cartoon aesthetic
- + Very clean and bold typography
- + Good variety of sushi types on the diorama
- − Failed to include the requested flag icon
- − Small garnishes like the tomatoes are not typical for a sushi scene
- − Lighting on 'SUSHI' text has low contrast against the background
Wan 2.7 Pro
- + Includes all text elements plus the requested flag icon
- + Excellent material rendering particularly on the salmon and roe
- + Sophisticated diorama base with gold trim
- − Text layout is slightly cluttered with extra unrequested words
- − Floating fragments in the top corners clutter the 'solid' background
- − Includes unrequested chopsticks and soy sauce dish outside the diorama
Verdict: Wan 2.7 Pro is the superior choice as it followed the complex prompt requirements more precisely, including the specific flag icon and more realistic PBR textures. While FLUX1.1 [pro] produced a cohesive 3D cartoon style, it missed key instructional details and included unusual garnishes like tomatoes.
Adorable Baby Animals in Sunny Meadow
Text-to-Image“Hyper-photorealistic scene of fluffy baby animals—a golden retriever puppy, tabby kitten, baby bunny, and red fox kit—with big expressive eyes and ultra-detailed soft fur, playfully chasing butterflies and tumbling together in a lush wildflower meadow, warm golden sunrise light with god rays and dew sparkles, joyful wholesome vibe, 8K masterpiece.”
AI Judge Analysis
FLUX1.1 [pro]
- + Excellent shallow depth of field and bokeh effect
- + Beautiful warm color palette and soft backlighting
- + The animal faces are incredibly expressive and cute
- − Failed to include the fox kit requested in the prompt
- − The butterflies are glowing blobs rather than detailed insects
- − Setting lacks the requested wildflower variety, appearing mostly as blurred yellow/white spots
Wan 2.7 Pro
- + Successfully included all four requested animals: golden retriever, tabby kitten, bunny, and fox kit
- + Extremely sharp details on fur texture and butterfly wings
- + Perfect adherence to 'god rays' and 'dew sparkles' atmospheric elements
- − The fox's front right leg is anatomically confusing/mangled where it meets the bunny
- − The scale of the butterflies is slightly large relative to the animals
- − The lighting on the animals is a bit more artificial than the background light source suggests
Verdict: Wan 2.7 Pro is the clear winner for prompt adherence, successfully including all four specific animals and intricate details like dew sparkles and god rays. While FLUX1.1 [pro] created a more aesthetically pleasing, soft-focus image, it failed to generate the fox kit and simplified the butterly details into generic light specks.
Vintage Cafe Logo
Text-to-Image“Vintage minimalist restaurant logo for "Caffè Florian", retro cloche dome with steam and "Est. 1720" banner, classic typography, warm brown and cream tones, subtle texture on light background, vector emblem style.”
AI Judge Analysis
FLUX1.1 [pro]
- + Excellent vector aesthetic that matches the logo prompt
- + Sophisticated use of warm brown and cream tones
- + High-quality linework and complex illustrative detail
- − Significant spelling error in the primary text ('FRANILIAN')
- − Interpreted the cloche dome as a decorative architectural dome or crown rather than food service hardware
Wan 2.7 Pro
- + Successfully rendered the specific 'cloche dome' requested
- + Accurate rendering of the date 'Est. 1720'
- + Clean, balanced circular composition
- − Misspelled the primary name as 'Florion' instead of 'Florian'
- − Includes stray decorative elements in the corners that break the minimalist logo feel
- − The steam effect is a bit wispy and less integrated into the icon style
Verdict: Wan 2.7 Pro followed the specific iconography prompt better by including an actual cloche dome, whereas FLUX1.1 [pro] generated a more abstract architectural shape. However, both models failed to spell the brand name correctly, with FLUX1.1 [pro] having a much more severe misspelling, making Wan 2.7 Pro the better choice despite its minor 'o' replacement.
Apollo 11: Journey to Tranquility
Text-to-Image“Create a clean, modern vector infographic poster about the Apollo 11 mission. NASA-inspired palette (navy, white, muted red, light gray). Flat-vector style, crisp lines, consistent iconography, subtle gradients only. Steps (stop at landing): 1. Launch (Saturn Vicon) 2. Earth Orbit (Earth + orbit ring icon) 3. Translunar (trajectory arc icon) 4. Lunar Orbit (Moon + orbit ring icon) 5. Descent (lunar module descending icon) 6. Landing (lunar module on the surface icon) Small supporting elements (minimal text): • Crew strip: three silhouette icons with only last names: Armstrong, Aldrin, Collins. • Landing site marker: Moon pin labeled "Tranquility" only. Layout constraints: generous margins, large readable labels, clean background with subtle stars. Vector-only, print-poster look, high resolution.”
AI Judge Analysis
FLUX1.1 [pro]
- + Clean vector illustration style
- + Adheres well to the requested color palette
- − Nonsensical text rendering
- − Steps are numbered incorrectly and layout is confusing
- − Icons do not match the specific mission phases requested
Wan 2.7 Pro
- + Excellent text legibility and historical accuracy
- + Perfect logical flow following all six requested steps
- + Professional, clean infographic layout with bonus relevant data
- − One minor spelling error in 'DESCRIPT' instead of Descent
- − Slightly less 'modern' illustrative style compared to Model A
Verdict: Wan 2.7 Pro is significantly better for this task as it successfully followed the complex instruction set for a sequential infographic, including legible and accurate text for all six steps. FLUX1.1 [pro] produced a visually striking image but failed completely on information hierarchy, text legibility, and logical sequencing of the mission phases.
Explore each model
Alibaba's Wan 2.7 Pro image generation and editing model with higher-quality outputs and support for 4K image generation