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
#39 of 62 in Text-to-Image
Where the votes landed
Recraft V4
100.0%
win rate
Ties
0.0%
Wan 2.7
0.0%
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 photorealism with shallow depth of field.
- + Impressive glass refractions and reflections on the wood surface.
- + Correct lighting direction from the left.
- − The sphere is floating unnaturally in the center of the cube.
- − The perspective of the table feels slightly inconsistent with the glass cube's base.
Wan 2.7
- + The sphere sits realistically on the bottom surface of the cube.
- + Superior composition with a more natural three-quarter view.
- + Accurate adherence to all spatial elements in the prompt.
- − The mirror-like base of the cube creates a confusing double-reflection of the sphere.
- − The book's scale feels a bit large compared to the cube.
Verdict: Both models followed the prompt perfectly, but Wan 2.7 produced a more coherent scene where the sphere respects gravity. While Recraft V4 has higher-quality glass textures and a more professional photographic feel, the floating sphere makes the image feel less realistic than Wan 2.7.
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.
- + Beautiful cinematic lighting and high-contrast reflections on the pavement.
- + Captures a convincing 'candid' and 'imperfectly framed' street photography aesthetic.
- − Physical logic errors with the bicycle's fork and wheel assembly.
- − The man's hand-to-bike interaction is anatomically messy.
Wan 2.7
- + Stronger anatomical realism in the man's face and hands.
- + Highly realistic wet clothing textures and subtle rain effects.
- + Realistic street environment that looks distinctly Japanese.
- − Missed the 'motion blur from passing cars' instruction.
- − The lighting is a bit flat compared to the requested cinematic look.
Verdict: Recraft V4 captured the requested mood and cinematic elements like motion blur and bokeh more effectively, but suffered from significant structural errors in the bicycle and the man's hands. Wan 2.7 produced a much more grounded and physically accurate image with superior skin and clothing textures, though it failed to include the requested motion blur. Wan 2.7 is the preferred choice for its photographic realism and coherent details.
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 detail on the intricate, filigreed engraving of the armor
- + Very lifelike, intense expression and wet-looking eyes
- + Superb texture on the leather straps and weathered fabric beneath the plate
- − The hair braids are a bit messy and lack the distinct beadwork visible in Model B
- − The sparks in the air look like flat strokes rather than glowing bokeh
Wan 2.7
- + Perfect adherence to the 'hair braided with small beads' part of the prompt
- + Clean, cinematic bokeh effect for the sparks and background torches
- + Realistic scarring and skin texture that matches the 'battle-worn' description
- − The engraving on the armor is much simpler and less 'ornate' than Model A's version
- − The leather straps look a bit more synthetic compared to the material realism in Model A
Verdict: Both models followed the prompt closely, but Recraft V4 excels in the material textures and the complexity of the armor's engravings. However, Wan 2.7 produced a cleaner photographic composition with better execution of the braided beads and a more convincing shallow depth of field, making it the overall winner for visual balance.
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 across all items.
- + Clean, modern minimalist aesthetic that perfectly matches the 'white background' requirement.
- + Consistent, high-quality food photography with professional lighting.
- − The layout is a bit sparse with significant whitespace.
- − Descriptions are missing for about half of the menu items.
Wan 2.7
- + Complete, stylized menu design with a logo, footer, and contact information.
- + Good use of vibrant accents and defined sections.
- + Creative presentation with background props like herbs and a pen.
- − Significant spelling errors throughout the text (e.g., 'Bisge', 'Calanrfri', 'Mmargerita').
- − The text becomes illegible in the smaller description areas.
- − The white background requirement is secondary to the 'mockup' style presentation.
Verdict: Recraft V4 is the clear winner for a functional design task because it generates perfectly legible, correctly spelled text alongside professional food imagery. While Wan 2.7 provides a more comprehensive layout with a logo and footer, its pervasive spelling errors and illegible small text make it unusable for a real-world menu design.
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 patty and buns
- + Authentic lighting that makes the ingredients look appetizing
- + The text integration feels professional and balanced with the image composition
- − The '€6.99' starburst looks like a flat sticker rather than a glowing/fiery element
- − The 'exploded' effect is slightly messy with dripping sauce appearing in odd places
Wan 2.7
- + Perfect adherence to the 'fiery, glowing' text effect requirement
- + Very dynamic composition with splashing sauces and floating sesame seeds
- + All requested text is rendered perfectly and placed logically
- − The style leans more toward digital illustration/3D render than 'photorealistic'
- − The lighting on the cheese and patty looks a bit plastic and artificial
Verdict: Recraft V4 produces a much more realistic and appetizing food image that looks like a high-end photograph, whereas Wan 2.7 follows the specific stylistic instructions for glowing, fiery text and a starburst much better. Wan 2.7 is the winner for perfectly incorporating every complex text element and the 'magic' theme, even if the food looks slightly less realistic than Recraft V4.
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 unavailable for this challenge.
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 suit and horse's coat.
- + Strong sense of scale and depth within the asteroid field.
- − Failed the negative constraint; the astronaut is riding the horse instead of vice versa.
- − The horse's anatomy is slightly obscured by the composition.
Wan 2.7
- + Very clean and sharp rendering.
- + Good global composition with multiple celestial bodies.
- + Excellent detail on the astronaut's patches and gear.
- − Failed the negative constraint; it shows an astronaut riding a horse.
- − The lighting feels a bit flat compared to Model A.
Verdict: Both Recraft V4 and Wan 2.7 failed the specific logic puzzle in the prompt, which requested the horse to be on top of the astronaut. However, Recraft V4 is the superior image due to its much more sophisticated cinematic lighting, realistic textures, and dramatic atmosphere, whereas Wan 2.7 has a more generic, illustrative appearance.
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 photorealism with convincing textures on the capybara's fur and the leather steering wheel.
- + The woman is correctly positioned in the back seat as requested.
- + Captures a moody, cinematic atmosphere with realistic lighting and rain on the window.
- − The passenger's face is slightly soft/out of focus compared to the foreground.
- − The capybara's paws look more like human hands in gloves than actual capybara paws.
Wan 2.7
- + The capybara's face is very clear and high-resolution.
- + Includes accurate-looking capybara front feet on the steering wheel.
- − The woman is sitting in the front passenger seat instead of the back seat.
- − The transition between the capybara's head and the jacket looks like a mask or a costume rather than a seamless animal.
- − The rendering has a slightly 'too sharp' digital feel compared to photograph-like film grain.
Verdict: Recraft V4 followed the prompt instructions much better by placing the passenger in the back seat, creating a more realistic spatial composition. While Wan 2.7 had sharper details on the animal's face, it failed a key positioning instruction and resulted in a less cinematic, less realistic image overall. Recraft V4 also excelled in lighting and atmospheric consistency.
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 cinematic lighting with atmospheric rainy details
- + High-quality, realistic textures on the jack-o-lantern and trees
- + Clean and legible gothic typography for all text elements
- − The 'scroll banner' is just a plain white rectangle rather than a parchment scroll
- − The web border feels a bit repetitive and flat compared to the central art
Wan 2.7
- + Perfectly captures the 'vintage' and 'parchment' aesthetic requested
- + Highly detailed border containing webs, thorns, skulls, and foliage
- + Authentic-looking scroll banner and superior composition for a physical invitation
- − The overall style is more illustrative/cartoonish than 'cinematic'
- − Incorrectly added 'Est. 1847' which was not in the prompt
Verdict: Recraft V4 produces a much more atmospheric and realistic image with impressive lighting, but Wan 2.7 better understands the compositional layout of an invitation, specifically the parchment and scroll banner elements. Wan 2.7 is the stronger choice for an actual invitation design, while Recraft V4 excels in pure visual fidelity and mood.
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
- + Excellent typography with clean, professional spacing
- + High-clarity realistic textures for the salmon and tuna
- + Accurate 45 degree isometric perspective
- − The 'diorama base' looks like a slab of salt or ice, which may not have been the intended miniature aesthetic
- − The lighting creates a very harsh shadow compared to the 'gentle lighting' requested
Wan 2.7
- + Perfectly captures the 'miniature 3D cartoon scene' aesthetic with soft, clay-like textures
- + Excellent diorama base and composition incorporating multiple sushi types and chopsticks
- + Solid adherence to the 'gentle lighting' and PBR material request
- − The text 'SUSHI' has minor kerning/alignment issues within the blue background block
- − Slightly less 'realistic' in its food representation compared to Model A
Verdict: Wan 2.7 is the winner as it perfectly captures the requested '3D cartoon' and 'miniature' style with a cohesive diorama base. While Recraft V4 has superior text rendering and more realistic fish textures, it fails to deliver on the soft, gentle, cartoonish aesthetic specified in the prompt.
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 realistic anatomy for all animals.
- + Dynamic, energetic composition with a great sense of movement.
- + Beautiful integration of atmospheric lighting and 'god rays'.
- − The kitten is partially merged/obscured by the puppy and bunny.
- − The large butterfly in the foreground is slightly blurry.
Wan 2.7
- + Clear visibility and distinct placement for all four animals.
- + Vibrant color palette with sharp, well-defined wildflowers.
- + Strong adherence to the 'dew sparkles' requirement in the grass.
- − The fox kit has somewhat unnatural facial features and a thick neck.
- − The lighting feels a bit more artificial compared to the natural haze of Model A.
- − The kitten's pose and expression are slightly awkward.
Verdict: Recraft V4 produces a much more cinematic and 'hyper-photorealistic' result with superior fur rendering and natural lighting. While Wan 2.7 does a better job of spacing out the four animals so they are all clearly visible, the anatomical accuracy and overall artistic quality of Recraft V4 make it the more successful '8K masterpiece'.
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
Recraft V4
- + Excellent high-contrast minimalist vector style.
- + Accurate and aesthetically pleasing custom typography.
- + Very clean and professional logo composition.
- − Missed the request for a banner element.
- − Missing the secondary texture on the background requested in the prompt.
Wan 2.7
- + Successfully included all elements including the cloche, steam, and banner.
- + Matches the 'warm brown and cream' color palette and subtle texture perfectly.
- + Excellent adherence to the 'Est. 1720' text requirement.
- − Misspelled the name as 'Florion' instead of 'Florian'.
- − The composition is a bit crowded for a minimalist logo.
- − Design style leans more toward a badge than a modern minimalist vector.
Verdict: Recraft V4 produced a much more professional and stylish minimalist logo with perfect spelling, though it omitted the banner element. Wan 2.7 followed the prompt's structural instructions more closely but failed on the most critical text element 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.”
AI Judge Analysis
Recraft V4
- + Excellent text legibility and flawless spelling.
- + Very clean, professional vector iconography that looks like a real minimalist infographic.
- + Strong adherence to the requested color palette on a clean light background.
- − Non-linear layout makes the sequence of steps a bit confusing to follow.
- − The icons for descent and landing are identical in shape, lacking visual progression.
Wan 2.7
- + Strong vertical composition that clearly communicates a timeline or sequence.
- + High information density with creative supporting text elements.
- + Excellent use of the 'Tranquility' location pin to bridge the stages.
- − Typographical errors in several places, such as 'DESCRIPT' and 'Tranquiliry'.
- − The descent module icon is distorted and lacks the crispness of the other icons.
Verdict: Recraft V4 produces a much cleaner aesthetic with perfect spelling and high-quality vector icons, making it look like a finished professional asset. While Flux 1.1 [pro] (Wan 2.7) has a superior vertical layout for an infographic and includes more detailed supporting data, its significant spelling errors and slightly messy icon rendering make it the weaker choice for a graphics-focused task.
Explore each model
Alibaba's Wan 2.7 image generation and editing model for text-to-image, reference-guided generation, and instruction-based image edits