Recraft's latest text-to-image generation model with high-quality output, supporting various aspect ratios and custom color palettes
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
Recraft V4
#11 of 62 in Text-to-Image
Wan 2.7 Pro
#36 of 62 in Text-to-Image
Where the votes landed
Recraft V4
50.0%
win rate
Ties
0.0%
Wan 2.7 Pro
50.0%
win rate
Challenge by challenge
The strongest take from each model on every shared challenge, with the AI judge's read.
Geometric Composition
Text-to-Image“A glass cube on a wooden table. Inside the cube is a small blue sphere. On top of the cube sits a red book. A green plant is behind the cube, partially visible through the glass. Soft window light from the left.”
AI Judge Analysis
Recraft V4
- + Excellent photographic realism in the glass and wood textures.
- + Accurate reflection and refraction of the blue sphere within the glass base.
- + Very faithful interpretation of the soft window lighting.
- − The blue sphere appears to be floating mid-air inside the cube, which might be physically impossible if it is a hollow glass container.
- − The plant in the background is less distinct through the glass than in Model B.
Wan 2.7 Pro
- + Naturalistic placement of the sphere resting on the bottom of the cube.
- + Strong adherence to the 'partially visible through the glass' instruction for the plant.
- + Good perspective and composition of the wooden table.
- − The glass cube has some geometric inconsistencies, such as the bottom edge appearing like a mirror rather than clear glass.
- − The lighting is slightly flatter and less cinematic than in Model A.
Verdict: Both models followed the prompt instructions perfectly. Recraft V4 produced a more aesthetically pleasing, high-quality photograph with superior lighting and materials, while Wan 2.7 Pro handled the physical logic of the scene slightly better by placing the sphere on the floor of the cube. Recraft V4 is the winner due to its superior visual fidelity and realistic glass refractions.
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
Recraft V4
- + Excellent depiction of motion blur from passing cars
- + Strong adherence to 'imperfect framing' and 'shallow depth of field'
- + Realistic atmospheric rain and light reflection
- − The bicycle frame is anatomically incorrect with the wheel passing through a structural bar
Wan 2.7 Pro
- + Natural and detailed skin texture on the face
- + Clearer depiction of the 'repairing' action with hands on the handlebars
- + Good reflection on the wet pavement
- − Missed the 'motion blur' requirement; the car in the background is static
- − The bicycle has structural issues, including the kickstand merging into the chain ring
Verdict: Recraft V4 captures the 'vibe' of the prompt much better, successfully incorporating the requested motion blur and imperfect, candid framing that creates a sense of street photography. While Wan 2.7 Pro has better facial detail, it fails to deliver on the cinematic motion elements and feels more like a static portrait than a candid street scene.
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
Recraft V4
- + Excellent depiction of grit and dirt, fitting the 'battle-worn' description perfectly.
- + High-relief ornate engraving on the plate armor with convincing metal textures.
- + Strong prompt adherence regarding the beads in the braids and the intense eyes.
- − The sparks look a bit like static orange lines rather than blurry embers.
- − The armor design is a bit busy and physically improbable near the neck.
Wan 2.7 Pro
- + Superior photographic quality with more realistic bokeh sparks and lighting.
- + Extremely lifelike eyes and skin texture that looks like a real photograph.
- + Better leather strap details with realistic wear and buckle construction.
- − The character looks less 'battle-worn' and cleaner compared to Model A.
- − The scar on the forehead is a bit faint and simple.
Verdict: Recraft V4 captures the 'battle-worn' aesthetic significantly better, with heavy grime and intense character expression that fits a paladin in the heat of conflict. However, Wan 2.7 Pro produces a more photorealistic image with better depth of field and more natural light interactions, even if the character looks a bit too clean. Recraft V4 wins for superior prompt adherence regarding the specific gritty details requested.
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
Recraft V4
- + Excellent text legibility and correct spelling
- + Perfectly clean white background and minimalist grid
- + Consistent photography style and lighting across all food items
- − Composition feels slightly empty with large white spaces
- − Layout is more like a gallery than a functional one-page menu
Wan 2.7 Pro
- + Sophisticated graphic design elements including logos, icons, and a footer
- + Creative presentation as a flyer/menu on a wooden table with props
- + Better use of space and hierarchy for a casual dining context
- − Significant spelling errors throughout the text (e.g., 'Caesa Salad', 'Sparkiing')
- − Food photos are somewhat inconsistent in framing and quality
- − Text is too small and cluttered to be functional
Verdict: Recraft V4 produces a technically superior and highly legible design with perfect spelling and a clean minimalist aesthetic. While Wan 2.7 Pro offers a more comprehensive graphic design concept with branding elements, its severe spelling issues and cluttered layout make it less practical than the crisp, professional output of Recraft V4.
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
Recraft V4
- + Excellent photorealistic texture on the meat and bread
- + Realistic physics and sauce drips conveying a natural sense of motion
- + Crisp, integrated 'MAGIC BURGER' typography with high-quality textures
- − The 'LIMITED TIME ONLY' text is cut off at the bottom edge
- − The starburst for the price is a bit simple and lacks the 'fiery' rendering requested
Wan 2.7 Pro
- + Strong adherence to all text requirements including 'LIMITED TIME ONLY' positioning
- + Vibrant, symmetrical composition that feels like a finished marketing graphic
- + Powerful fiery glow effects on the text and throughout the background
- − The meat patty and cheese look slightly more artificial/digital than those in Model A
- − The inclusion of cucumbers/pickles and herbs was not requested in the prompt
Verdict: Wan 2.7 Pro is the clear winner for its superior layout and full adherence to the text prompts, delivering a polished ad with impressive glowing effects. While Recraft V4 features much more realistic food textures, it fails on the graphic design elements by cutting off the text and providing a very basic price burst.
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
Recraft V4
- + Excellent photographic composition with realistic café background and depth of field
- + Includes charming chalk illustrations that complement the menu items
- + High legibility and accurate text rendering
- − Text lacks the requested 'elegant cursive' for the title
- − The handwriting looks a bit too clean and consistent, bordering on a digital font appearance
Wan 2.7 Pro
- + Successfully captures the elegant cursive style for the title and menu items
- + Handwriting has a more authentic chalk texture with varying weights
- + Fills the frame well with large, easy-to-read text
- − The 'A' in 'April' is slightly malformed
- − Background is less detailed and lacks the cozy atmosphere of a full café scene
Verdict: Recraft V4 produces a superior overall image in terms of environment and composition, appearing more like a real photograph. However, Wan 2.7 Pro better followed the specific stylistic instructions for 'elegant cursive' handwriting and chalk texture, whereas the text in Recraft V4 felt more like a uniform digital font overlay.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
AI Judge Analysis
Recraft V4
- + Excellent cinematic lighting and atmosphere
- + High level of texture detail on the astronaut and horse
- + Dynamic composition with floating rocks that fits the 'cinematic' prompt
- − Failed the negative constraint: astronaut is riding the horse, not the horse riding the astronaut
Wan 2.7 Pro
- + Crips, high-resolution visual quality
- + Clean rendering of the astronaut suit and horse
- − Failed the negative constraint: astronaut is riding the horse, not the horse riding the astronaut
- − Composition feels flat and less 'surreal' or 'cinematic' than requested
Verdict: Both Recraft V4 and Wan 2.7 Pro completely ignored the specific spatial instruction 'horse on top, not vice versa', resulting in standard astronaut-on-horse images. Recraft V4 is the winner because it successfully captured the requested 'cinematic' and 'surreal' aesthetic with superior lighting and depth, whereas Wan 2.7 Pro felt like a more generic composite.
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
Recraft V4
- + Excellent photorealistic texture on the capybara's fur and clothing.
- + The composition perfectly captures the scale of a backseat passenger relative to the front seat.
- + The blurred Manhattan background feels authentic to a night-time professional photograph.
- − The passenger's phone is slightly warped and lacks detail.
- − The passenger is partially obscured by the car seat, making her expression less visible.
Wan 2.7 Pro
- + High clarity on the passenger's face and expression.
- + Strong lighting on the capybara and well-defined front paws on the steering wheel.
- − The steering wheel and passenger are positioned awkwardly, making the interior space look flat and unrealistic.
- − The capybara's hands/paws look slightly too primate-like rather than typical capybara morphology.
Verdict: Recraft V4 produces a much more convincing and cinematic image with realistic depth of field and correct spatial relationships between the driver and passenger. Wan 2.7 Pro has good detail but the composition feels claustrophobic and the perspective of the interior is warped.
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
Recraft V4
- + Excellent photographic realism in the center pumpkin and background
- + Modern cinematic lighting with a moody atmospheric effect
- + Accurate text rendering for all requested details
- − The 'scroll banner' is just a flat white rectangular box
- − The text overlay feels like a digital layer rather than an integrated part of a 'vintage parchment'
Wan 2.7 Pro
- + Stronger adherence to the 'vintage' and 'parchment' aesthetic
- + Proper execution of the scroll banner and ornate gothic border
- + Unified artistic style where text and illustration blend seamlessly
- − The style is more of a clean vector/illustration rather than 'cinematic' realism
- − Added extra text elements not requested in the prompt like 'Est. 1847'
Verdict: Recraft V4 produces a more realistic and eerie atmospheric image, but it fails to capture the 'vintage parchment' texture or the 'scroll banner' effectively. Wan 2.7 Pro excels in composition and layout, perfectly executing the scroll and vintage gothic invitation aesthetic, making it the better choice for a graphic design task.
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
Recraft V4
- + High realism in food textures and lighting.
- + Accurate text placement and minimal, clean typography.
- − Failed the '3D cartoon scene' requirement, opting for a realistic photo-style.
- − The diorama base looks like raw salt or crushed ice rather than a cohesive miniature base.
Wan 2.7 Pro
- + Perfectly captures the 'miniature 3D cartoon' and 'soft refined texture' aesthetic.
- + Excellent render quality with clear PBR materials and gentle lighting.
- + Clever interpretation of the diorama base that looks like a high-quality toy or model.
- − Included extra text elements and icons not requested in the prompt.
- − The flag icon is placed to the right instead of at the top-center above the text.
Verdict: Wan 2.7 Pro followed the stylistic instructions much more closely, producing a beautiful 3D cartoon render that matches the requested isometric miniature look. While Recraft V4 produced a high-quality image, it went for a realistic culinary photography style that ignored the 'cartoon' and 'soft refined texture' prompts.
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
Recraft V4
- + Excellent fur texture and detail on all four animals.
- + Rich, immersive environment with multiple layers of foliage and butterflies.
- + Beautiful lighting with visible god rays and convincing dew sparkles.
- − The bunny appears a bit small relative to the other animals' scale.
- − Composition is a bit crowded with many butterflies overlapping.
Wan 2.7 Pro
- + Natural interaction and 'tumbling' movement between the animals.
- + Strong adherence to all subject types requested.
- + Clean, bright sunrise lighting and clear focus.
- − The fox's front leg and the kitten's position have minor anatomical glitches where they overlap.
- − Fur texture on the cat and fox looks slightly more digitally smoothed compared to the pup.
- − Fewer butterflies and less 'magic' in the atmosphere compared to the other model.
Verdict: Both images followed the prompt exceptionally well, capturing all four specific baby animals in a beautiful meadow setting. Recraft V4 is the winner due to its superior texture rendering (especially the fur and dew) and more magical atmosphere, whereas Wan 2.7 Pro had some slight anatomical awkwardness where the cat and fox intersect.
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 unavailable for this challenge.
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
Recraft V4
- + Excellent text legibility and clean font choices.
- + Perfect adherence to the requested flat-vector style with crisp icon lines.
- + Intuitive layout for the creative 'Crew' section.
- − The layout is fragmented and lacks a clear 'flow' for a mission timeline.
- − Stylistically very sparse with significant empty white space.
- − The icon for the Saturn V is less detailed compared to Model B.
Wan 2.7 Pro
- + Superior infographic composition with a vertical timeline flow.
- + Includes more detailed mission metadata and accurate NASA-inspired iconography.
- + Better adherence to the requested color palette against a navy background.
- − Minor spelling errors such as 'DESCRIPT' instead of 'DESCENT' and 'Tranquilicy'.
- − The icons for descent and landing are identical, lacking the visual progression seen in model A.
Verdict: Wan 2.7 Pro is the clear winner for its superior composition, capturing the essence of a 'poster' with a logical vertical flow and a professional navy-centric NASA palette. While Recraft V4 has fewer spelling errors and cleaner individual icons, its layout feels like a collection of clipart rather than a cohesive infographic.
Explore each model
Alibaba's Wan 2.7 Pro image generation and editing model with higher-quality outputs and support for 4K image generation