Black Forest Labs' precision image generation model with maximum control, reliable text rendering, and complete creative control supporting up to 4MP output
Settled by community votes across 19 shared challenges, with an AI judge weighing in on each.
FLUX.2 [flex]
#14 of 62 in Text-to-Image
Wan 2.7
#39 of 62 in Text-to-Image
Where the votes landed
FLUX.2 [flex]
0%
win rate
Ties
0%
Wan 2.7
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
FLUX.2 [flex]
- + Excellent adherence to lighting instructions with a clear soft light from the left.
- + Clean, minimalist composition with very sharp focus on the glass cube.
- + Modern and polished visual quality.
- − The sphere is quite large, pushing the interpretation of a 'small blue sphere' compared to the cube's volume.
- − The glass appears very thin, almost looking like a plastic frame in some areas.
Wan 2.7
- + Features a highly realistic, weathered wooden table texture.
- + The cube and sphere proportions feel more natural and accurate to the prompt.
- + Detailed glass reflections including the floor and surrounding objects.
- − The glass geometry is slightly confusing with an unexplained internal glass pane or vertical reflection.
- − The lighting is more diffuse and lacks the distinct 'from the left' directionality requested.
Verdict: FLUX.2 [flex] produced a very clean and aesthetically pleasing image that followed the lighting prompt perfectly, though the elements feel a bit more digital. Wan 2.7 created a more tactile, realistic scene with better scaling of the objects, but sufferedจาก minor geometric inconsistencies in the glass rendering. FLUX.2 is the winner for its superior clarity and exact adherence to the spatial and lighting details.
Man and Car in California
Editing“Make a photo of the man driving the car down the California coastline”
AI Judge Analysis
FLUX.2 [flex]
- + Excellent preservation of the man's facial features and distinctive hairstyle
- + Near-perfect replication of the car's model and design details
- + Realistic motion blur on the wheels and road
- − The man is placed in the passenger seat instead of the driver's side
Wan 2.7
- + Successfully places the man on the driver's side
- + Good environmental atmosphere and lighting
- − Completely fails to preserve the identity and appearance of the man from the source image
- − Distorted and unrecognizable facial features
- − Static wheels despite the car being in motion
Verdict: FLUX.2 [flex] successfully preserved the identity of both the man and the car with high fidelity, though it placed the man on the wrong side of the vehicle. Wan 2.7 followed the driving instruction better but failed the edit challenge by completely losing the subject's likeness and producing a distorted face.
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
FLUX.2 [flex]
- + Excellent shallow depth of field with beautiful bokeh.
- + Highly realistic skin textures and fine details on the man's hands.
- + Captures the cinematic lighting and wet pavement reflections perfectly.
- − The 'imperfect framing' is a bit forced, with the pole on the left occupying too much space.
- − Motion blur from passing cars is subtle compared to the static background.
Wan 2.7
- + Excellent wet pavement texture and realistic puddles.
- + Higher fidelity and more natural colors that feel less like a digital render.
- + Great portrayal of 'imperfect framing' that feels like a genuine candid snapshot.
- − Lacks the requested 'motion blur from passing cars'.
- − The bicycle geometry is slightly warped where it touches the ground.
Verdict: FLUX.2 [flex] excels in technical photographic qualities like shallow depth of field and skin textures, feeling very cinematic. However, Wan 2.7 captures a more authentic 'candid' atmosphere with superior environmental lighting and textures, avoiding the slightly artificial look found in FLUX.2 [flex]. Wan 2.7 is preferred for its more grounded, less stylized realism.
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
FLUX.2 [flex]
- + Excellent depiction of intricate engraved plate armor with high detail
- + Strong adherence to the 'beads in hair' and 'bokeh sparks' prompt elements
- + Warm, directional torchlight lighting captures a cinematic mood
- − The facial scars look somewhat superficial or painted on rather than deep-set
- − The face has a slightly smoothed, typical AI-generated aesthetic compared to the armor
Wan 2.7
- + The facial texture is more realistic and weathered, appearing more 'battle-worn'
- + High-quality rendering of various textures including leather, metal, and skin
- + Natural-looking hair braids and beads that integrate well with the portrait
- − The armor engraving is less ornate and intricate than requested
- − A small artifact where a braid appears to merge into the leather strap on the collar
Verdict: Both models followed the prompt very well, but FLUX.2 [flex] produced superior plate armor with much more intricate engravings and better-defined bokeh sparks. While Wan 2.7 had a more convincingly weathered face for a 'battle-worn' warrior, FLUX.2 [flex] overall delivered a more visually striking image with higher technical detail in the requested materials.
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
FLUX.2 [flex]
- + Excellent typography with clean, legible sans-serif fonts
- + The layout feels like a realistic professional graphic design template
- + Clean grid alignment between images and text blocks
- − Confusing categorization where the 'Pizza' section includes a chicken bowl
- − The large 'Appetizers' header is redundant with the smaller logo text
Wan 2.7
- + High-quality food photography with consistent lighting
- + Comprehensive layout including a footer with QR code and social handles
- + Excellent use of a colorful grid as requested in the prompt
- − Text is largely nonsensical 'Lorem Ipsum' style or mangled characters
- − The top navigation buttons overlap and feel cluttered
Verdict: FLUX.2 [flex] wins because the primary purpose of a menu is readability, and it provides perfectly legible, bold sans-serif text that looks like a real design. While Wan 2.7 has more vibrant food photography and helpful contextual elements like a footer, its text is unreadable, making it less useful as a design mockup.
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
FLUX.2 [flex]
- + Excellent photorealistic texture on the patty and bun
- + Highly integrated fiery text effects
- + Great use of dynamic particles and dripping sauce
- − The burger feels a bit vertically stacked rather than fully 'exploded'
Wan 2.7
- + Superb 'exploded' dynamic composition with wide separation
- + Accurate and clear text rendering for all requested elements
- + Creative use of flying ingredients like the pickle and sesame seeds
- − The textures look more like a digital illustration than a photorealistic image
- − The bun lacks realistic lighting compared to the fiery surroundings
Verdict: FLUX.2 [flex] produces a much more realistic and appetizing image with superior lighting and textures, though the 'exploded' effect is subtle. Wan 2.7 delivers a much better composition in terms of the layout and motion of the ingredients, perfectly matching the marketing 'deconstructed' look, but it looks more like a 3D render than a photo. FLUX.2 is the winner for its professional advertising aesthetic and believable textures.
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
FLUX.2 [flex]
- + Excellent chalk texture with realistic smudges and varying opacity.
- + Captures the handwritten aesthetic perfectly with natural variations and slants.
- + Perfect prompt adherence including the completion of the truncated text.
- − The alignment of the bottom lines is slightly irregular, though arguably realistic for chalk.
Wan 2.7
- + Perfectly legible and accurate text rendering of all requested items.
- + Bright lighting and clear, high-contrast composition.
- − The text appears more like a digital font than authentic chalk handwriting.
- − The 'handwriting' is too uniform and lacks the grain/texture of real chalk.
Verdict: FLUX.2 [flex] achieved a much more authentic result by successfully mimicking the specific texture and unevenness of real chalk handwriting on a board. While Wan 2.7 produced very clean and accurate text, it failed the specific instruction to avoid digital-looking fonts, making FLUX.2 [flex] the superior choice for this prompt.
Pose & Character Mashup
Editing“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.”
AI Judge Analysis
FLUX.2 [flex]
- + Excellent character preservation of the man from Image 2, including his clothes, scarf, and sunglasses.
- + Accurately places the character onto the red stool with the yellow background from Image 1.
- + High visual quality and clear details on the clothing and face.
- − Failed to replicate the exact pose from Image 1, opting for a squatting pose instead of the crossed-leg leaning pose.
- − The right hand contains an extra finger and a messy anatomical structure.
Wan 2.7
- + Perfectly preserves the composition, pose, and background of Image 1.
- − Completely failed the character replacement task, leaving Image 1 entirely unedited.
- − Zero adherence to the instruction to use Image 2 as a character reference.
Verdict: FLUX.2 [flex] successfully integrated the character's clothing and appearance from Image 2 into the environment of Image 1, though it struggled to duplicate the complex pose precisely. Wan 2.7 failed the task entirely, providing an identical copy of the pose reference (Image 1) without any edits. FLUX.2 [flex] is the winner for actually attempting and partially succeeding at the multi-image synthesis task.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
AI Judge Analysis
FLUX.2 [flex]
- + Excellent adherence to the 'horse on top' spatial instruction
- + Cinematic lighting and high level of detail in the astronaut suit and horse mane
- + Creative use of composition where the astronaut is physically holding the horse
- − The horse's front legs merge awkwardly with the astronaut's hands
- − The scale is slightly inconsistent between the horse's body and the astronaut
Wan 2.7
- + High visual clarity and clean rendering
- + Standard cinematic composition with well-defined background elements like Earth and galaxies
- − Completely failed the negative constraint to have the horse on top
- − Generic interpretation that ignores the specific surrealism requested in the prompt
Verdict: FLUX.2 [flex] is the clear winner as it followed the difficult instruction to place the horse on top of the astronaut, creating a truly surreal image. Wan 2.7 ignored the specific spatial instruction and produced a standard, cliché image of an astronaut riding a horse.
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
FLUX.2 [flex]
- + Excellent adherence to the 'back seat' positioning for the passenger
- + High-quality textures on the capybara's fur and the jacket
- + Superior cinematic lighting that captures the NY night atmosphere
- − The capybara's paws look slightly more like human hands than actual capybara feet
Wan 2.7
- + Realistic capybara paws on the steering wheel
- + Good clarity on the human passenger's bored expression
- − Failed to place the passenger in the back seat, placing her in the front passenger seat instead
- − The capybara's fur appears slightly detached or overlaid from the body
- − Lower contrast and less 'photorealistic' lighting compared to Model A
Verdict: FLUX.2 [flex] successfully followed the spatial instructions by placing the passenger in the back seat, creating a much more believable and humorous composition. Wan 2.7 failed the positioning instruction by placing the woman in the front seat and had less sophisticated lighting and textures.
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
FLUX.2 [flex]
- + Excellent typography with clean, consistent gothic font
- + Achieves a moody, cinematic lighting that feels professional
- + Perfectly centered and balanced composition
- − The 'parchment' effect is a bit simple with just a torn edge graphic
- − Less intricate detail in the border compared to its competitor
Wan 2.7
- + Highly detailed hand-drawn illustration style with many thematic elements
- + Intricate border with webs, thorns, and integrated skulls
- + Good use of color and layering within the central frame
- − The text has slight kerning issues and inconsistencies in font weight
- − The composition feels a bit cluttered with the addition of unrequested elements like the cauldron and books
Verdict: FLUX.2 [flex] produced a very polished, professional invitation that looks ready for print, with excellent text rendering and atmospheric lighting. Wan 2.7 created a more illustrative and complex piece with beautiful borders, but the text quality and overall clarity are slightly lower than FLUX.2. FLUX.2 followed the prompt's 'polished' and 'cinematic' requirements better than the comic-book style of Wan 2.7.
Bald man challenge
Image Editing“Give the person a full, thick head of natural hair with realistic texture, density, and a natural hairline. Preserve facial features and lighting.”
AI Judge Analysis
FLUX.2 [flex]
- + Excellent preservation of the background and clothing.
- + The hair texture matches the coarseness of the existing beard well.
- + Maintains the exact head shape and lighting of the source.
- − The hairline looks a bit repetitive and artificial at the forehead.
- − The 'full, thick head of hair' is interpreted as a very short buzz cut.
Wan 2.7
- + Provides a much fuller, more natural-looking hairstyle that better fits the 'thick head of hair' prompt.
- + Excellent blending of the new hair into the sideburns and temples.
- + Preserves facial features and environmental details perfectly.
- − The forehead is slightly shortened to accommodate the new hairline.
Verdict: Both models did an exceptional job of preserving the source image's identity, lighting, and detail. FLUX.2 [flex] provided a very short, coarse buzz cut which feels slightly more like a 'hairy scalp' than a full head of hair, whereas Wan 2.7 delivered a more aesthetically pleasing, natural-looking hairstyle that fits the description perfectly.
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
FLUX.2 [flex]
- + Excellent adherence to the 'icon below text' layout.
- + Clean, minimalist aesthetic with high fidelity.
- + Accurate text rendering and centered composition.
- − The sushi models are a bit thicker/chunkier than traditional sushi proportions.
- − Lighting is a bit flat across the text area.
Wan 2.7
- + High level of detail in the food textures, especially the shrimp and rice grains.
- + Dynamic composition with a wider variety of sushi types.
- + Nice use of color contrast between the base and the background.
- − Failed the text placement instructions, putting the flag to the side instead of below the text.
- − Chopsticks and napkins add clutter that deviates from the 'minimalist' request.
- − Text has some slight aliasing/jagged edges compared to Image A.
Verdict: FLUX.2 [flex] adhered much better to the specific layout instructions, placing the text and flag exactly where requested in a clean, professional manner. While Wan 2.7 has more impressive textures on the food itself, its failure to follow the typography placement and the addition of extra objects makes FLUX.2 [flex] the better overall response to the prompt.
Over-the-top cartoon caricature
Editing“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.”
AI Judge Analysis
FLUX.2 [flex]
- + Excellent integration of all prompt elements including dogs, professional news set, and hockey jerseys.
- + High-quality, clean vector-style caricature that retains the subjects likeness through exaggerated features.
- + Logical composition with the subject seated at a news desk and various dogs filling the scene.
- − Text on the news desk ('THEIANAES') is mangled and nonsensical.
Wan 2.7
- + Creative use of speech bubbles and a floating hockey puck to enhance the humorous caricature style.
- + Retains the wide-angle 'selfie' perspective from the original source image.
- + Displays a very high level of energy and exaggeration in the facial expression.
- − The text 'Dogs Rolee!' contains a spelling error.
- − The hockey elements, such as the tiny desk rink and floating puck, feel slightly cluttered and less cohesive than Model A.
Verdict: FLUX.2 [flex] produced a more professional and well-composed caricature that perfectly blends the TV anchor profession with the requested hobbies by dressing the dogs in hockey jerseys on a news set. While Wan 2.7 also captures all prompt requirements and maintains the 'selfie' framing of the original photo, its composition is more chaotic and the text rendering is less successful.
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
FLUX.2 [flex]
- + Excellent action posing with the animals mid-leap, creating a sense of movement.
- + Atmospheric lighting with clear god rays and a soft morning mist.
- + Stronger individual detail on the golden retriever and fox kit fur texture.
- − The kitten's anatomy looks slightly distorted with one very large eye.
- − The background tree feels a bit disconnected from the ground plane.
Wan 2.7
- + Beautiful color palette with vibrant blue and yellow butterflies.
- + Higher consistency in the facial features across all four animals.
- + Better integration of the subjects into the tall grass and wildflowers.
- − The fox's anatomy is a bit stiff and its paws are submerged awkwardly.
- − The lighting is a bit flat across the animals' bodies compared to the background brightness.
Verdict: Both models followed the complex prompt very well, including all four specific animals and environmental details. FLUX.2 [flex] excels at capturing the 'tumbling' motion requested in the prompt, while Wan 2.7 provides more consistent facial features and a more vibrant floral environment.
Studio Ghibli Anime Style
Editing“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”
AI Judge Analysis
FLUX.2 [flex]
- + Perfectly captures the Studio Ghibli art style with flat cel-shading and iconic facial features.
- + Includes Japanese signage in the background to enhance the thematic mood.
- + Excellent adherence to the 'soft pastel colors' and 'nostalgic mood' keywords.
- − Changes the facial expressions, making the girlfriend look happy instead of jealous.
- − The hand texture on the man's jeans is slightly messy.
Wan 2.7
- + Maintains the original facial expressions and emotional context of the source image perfectly.
- + Beautiful watercolor-inspired 'hand-painted' texture that feels very high quality.
- + Preserves the composition and details of the original clothing accurately.
- − Art style leans more toward generic watercolor illustration rather than specifically 'Studio Ghibli'.
- − Lighting is a bit less 'dreamy' compared to Model A.
Verdict: FLUX.2 [flex] successfully captures the specific Studio Ghibli aesthetic, particularly the eye and mouth styles, though it fails to preserve the original emotional tension by making the characters look too cheerful. Wan 2.7 preserves the source image's narrative and expressions much better while applying a beautiful painterly texture, even if it feels slightly less like a Ghibli film and more like a high-end watercolor sketch. Wan 2.7 is the winner for better source preservation and emotional accuracy.
Golden Hour Stroll
Image Editing“Add dynamic motion to this photo: make hair blow in the wind, add leaves flying, energetic and lively feel.”
AI Judge Analysis
FLUX.2 [flex]
- + Successfully added wind-blown hair effect
- + Added bright green leaves consistent with the park's summer appearance
- + Maintains strong continuity with the original subject's facial features
- − The wind direction appears inconsistent between the hair (blowing back and up) and the leaves (falling straight down)
- − The green leaves look slightly like stickers and lack natural shadows
Wan 2.7
- + Excellent integration of autumn leaves with motion blur and depth
- + The hair physics look more natural and integrated with the overall wind direction
- + High edit accuracy for 'energetic and lively' feel
- − Introduces a slight change to the woman's face and skin texture compared to the source
- − Leaves are brown while the background trees are vibrant green, creating a seasonal mismatch
Verdict: Both models followed the instructions well, but Wan 2.1 produced a much more realistic sense of motion with blurred leaves and better hair integration. FLUX.2 [flex] had better source preservation regarding the woman's face and background, but the added leaves felt flat and lacked the 'dynamic' quality requested.
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
FLUX.2 [flex]
- + Perfect text accuracy for both the brand name and established date.
- + Strong minimalist vector aesthetic with clean, balanced lines.
- + Follows the color palette and texture requests precisely.
- − The steam icons are a bit thin compared to the bold lines of the cloche.
Wan 2.7
- + Intricate vintage emblem design with high visual appeal.
- + Good use of shading on the cloche dome to give it dimension.
- + Excellent background texture and framing elements.
- − Typographical error in the main brand name, spelling it 'Florion' instead of 'Florian'.
- − Less minimalist than requested, leaning more into a maximalist crest style.
Verdict: FLUX.2 [flex] successfully delivered a minimalist and accurate logo that followed all prompt instructions, including correct spelling. Wan 2.7 created a more visually complex and attractive vintage emblem, but failed on the primary text accuracy and went beyond the 'minimalist' requirement.
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
FLUX.2 [flex]
- + Excellent typography and layout clarity
- + Accurate flat-vector style with professional, clean lines
- + High-quality icon graphics for the Earth and Moon
- − Failed to include the final 'Landing' step requested in the prompt
- − Icons become somewhat fragmented in the middle section
Wan 2.7
- + Successfully included all 6 steps including the Landing
- + Added relevant historical details like dates and crew names
- + Perfect adherence to the requested NASA-inspired color palette
- − Contains minor typos in technical text like 'Tranquiliry' and 'Descript'
- − Icons for the spacecraft are less detailed and slightly inconsistent in scale
Verdict: FLUX.2 [flex] produces a more aesthetically pleasing and professional-looking vector graphic with superior typography, but it fails to include all of the requested steps. Wan 2.7 follows the instructional sequence of the prompt more accurately and provides extra thematic details, despite having some spelling errors in the small text. Wan 2.7 is the preferred choice for a functional infographic that meets all prompt requirements.
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