Distilled version of Black Forest Labs' FLUX.2 [dev] outperforming it at a cheaper price. Developed by fal.ai.
Settled by community votes across 20 shared challenges, with an AI judge weighing in on each.
FLUX.2 [dev] Turbo
#4 of 62 in Text-to-Image
Wan 2.7
#39 of 62 in Text-to-Image
Where the votes landed
FLUX.2 [dev] Turbo
50.0%
win rate
Ties
0.0%
Wan 2.7
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
FLUX.2 [dev] Turbo
- + Excellent photorealistic texture on the wooden table and book cover.
- + Accurate physical rendering of the glass edges and reflections.
- + Strong adherence to the lighting prompt with convincing soft window light and shadows.
- − The plant is slightly less 'behind' the cube compared to Model B, though still visible through the glass.
Wan 2.7
- + Successfully includes all prompt elements including the red book and blue sphere.
- + The plant is very clearly positioned behind the glass cube.
- − The glass rendering is inconsistent, appearing more like mirrors or a solid block in several places.
- − The blue sphere has a strange reflection on the left that doesn't match the scene's geometry.
- − The book's texture looks somewhat AI-generated and less tactile than Model A.
Verdict: FLUX.2 [dev] Turbo produces a much more realistic and physically coherent image, particularly in how the glass cube interacts with light and its environment. Wan 2.7 follows the spatial instructions well but fails on the material properties of glass, making it look like a collection of mirrors rather than a transparent cube.
Man and Car in California
Editing“Make a photo of the man driving the car down the California coastline”
AI Judge Analysis
FLUX.2 [dev] Turbo
- + Excellent preservation of the subject's face, hair, and clothing.
- + Extremely accurate interior detail that matches the source convertible's upholstery color.
- + Dynamic composition with motion blur and a clear California coastline setting.
- − The car color appears slightly more silver/champagne than the vibrant white of the source.
Wan 2.7
- + Successfully placed the correct white car on a coastal road.
- + Good lighting and perspective for the environment.
- − Completely failed to preserve the man's appearance from the source image, resulting in a distorted figure.
- − The person in the car lacks any resemblance to the provided subject.
Verdict: FLUX.2 [dev] Turbo followed the edit instructions perfectly, successfully combining both source images by placing the specific man into the specific car while maintaining high fidelity for both. Wan 2.7 correctly identified the car and setting but failed significantly on the human subject, producing a distorted face that looks nothing like the source image. FLUX is the clear winner for its superior identity preservation and attention to detail.
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 [dev] Turbo
- + Excellent adherence to motion blur on passing cars.
- + Highly detailed and realistic mechanical components of the bicycle.
- + Superior skin texture and naturalistic lighting on the subject.
- − The bike's front wheel is clipping through the ground.
- − Physical interaction between hands and tools is slightly messy.
Wan 2.7
- + Strong composition with a believable street depth.
- + Effective wet pavement reflections and rain atmosphere.
- + Good posture for a candid street photography feel.
- − Failed to include motion blur on the passing cars.
- − The bicycle's structure is physically warped and inconsistent.
- − Overall image lacks the high-frequency detail seen in the competitor.
Verdict: FLUX.2 [dev] Turbo followed the prompt much more accurately, specifically regarding the motion blur of passing cars and the 50mm lens look. While it has a clipping error on the front tire, its overall detail and realism far exceed Wan 2.7, which produced a warped bicycle and missed key motion elements.
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 [dev] Turbo
- + Exceptional intricate engraving on the plate armor.
- + Superior texture on leather straps with weathered, realistic details.
- + Excellent balance of warm torchlight and cool ambient light.
- − Hair beads are slightly inconsistent and multicolored, which may feel a bit modern.
- − The background torch has a slightly artificial flame shape.
Wan 2.7
- + Naturalistic hair braiding and bead placement.
- + Very strong 'battle-worn' expression and facial construction.
- + Good use of bokeh sparks and warm lighting cast.
- − The armor engravings are noticeably less detailed and flatter than Image A.
- − The leather straps lack the worn tactile texture requested in the prompt.
- − Eye reflections are slightly less lifelike compared to Image A.
Verdict: FLUX.2 [dev] Turbo takes the lead in this comparison due to its incredible rendering of textures, particularly the ornate metalwork and weathered leather straps requested in the prompt. While Wan 2.7 produces a very convincing character portrait, it lacks the fine-grained surface detail and high-fidelity texture of the clothing and armor that the FLUX model provides.
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 [dev] Turbo
- + Excellent typography rendering with very readable main headers
- + Creative use of color blocking and modern grid layout
- + High-quality, appetizing food photography with consistent lighting
- − Nonsensical pricing for pizza ($160-$300)
- − Mains section is poorly organized with text and images overlapping strangely
Wan 2.7
- + Perfectly logically structured menu with realistic pricing and item descriptions
- + Includes professional brand elements like a logo, QR code, and social media icons
- + Very clean alignment of text elements and a cohesive color palette
- − Some smaller descriptive text is blurry or illegible
- − Stylized 'pill' buttons for categories are slightly less 'minimalist modern' than the grid in Image A
Verdict: While FLUX.2 [dev] Turbo produces much sharper main headings and more vibrant photography, Wan 2.7 creates a far superior functional design with realistic prices, logical menu categories, and professional details like a QR code. FLUX.2 fails on the logic of the menu (extreme prices, confusing layout for 'Mains'), whereas Wan 2.7 feels like a completed graphic design project.
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 [dev] Turbo
- + Excellent photorealistic texture on the meat and bun
- + Very effective fiery, glowing text treatment that looks organic to the scene
- + High-quality rendering of the 'starburst' element for the price
- − The 'exploded' effect is a bit tamer and more vertical compared to the dynamic energy requested
Wan 2.7
- + Strong sense of motion with sauce splashes and individual ingredients flying outward
- + Bold, clear typography that is very legible
- + Includes more variety in ingredients like pickles and individual seeds
- − The lighting on the burger components feels less realistic and more like a 3D digital illustration
- − The 'LIMITED TIME ONLY' text lacks the requested fiery, glowing effect
Verdict: FLUX.2 [dev] Turbo achieves a superior photorealistic look with lighting and textures that feel cohesive, especially in how the fiery glow interacts with the text. While Wan 2.7 has a more energetic 'exploded' composition, its rendering style is more illustrative and it fails to apply the fiery effect to all text elements as 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
FLUX.2 [dev] Turbo
- + Excellent chalk texture with natural-looking rub marks and graininess
- + Truly handwritten appearance with realistic variations in character slant and size
- + Perfectly followed the prompt's request for cursive style for the title
- − Layout is slightly cluttered with line breaks in the middle of items
- − Duplicated the price for the cookie item
Wan 2.7
- + Text is very legible and perfectly spelled including the full third item
- + Clean and centered composition with decorative underline flourishes
- + High contrast makes it easy to read
- − Text looks like a digital font rather than natural chalk handwriting
- − Failed to render the title in the requested elegant cursive style
- − Uniformity of the letters lacks the 'natural variations' requested in the prompt
Verdict: FLUX.2 [dev] Turbo followed the stylistic requirements of the prompt much more accurately, producing text that genuinely looks like it was written with chalk, including natural imperfections and the requested cursive title. While Wan 2.7 produced a cleaner layout with perfect spelling, the text has a distinct 'digital font' look that directly contradicts the prompt's instruction for no printed or digital fonts.
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 [dev] Turbo
- + Successfully integrated clothing, scarf, and sunglasses from Image 2
- + Attempts a dynamic pose on the red stool from Image 1
- + Matches the yellow background lighting and style moderately well
- − Extreme anatomical errors including a floating second head and severed limbs
- − Failed to replicate the specific pose from Image 1, resulting in a nonsensical composition
- − Hands and feet have significant artifacts and distort the character's physical integrity
Wan 2.7
- + Perfectly maintains the exact image quality and background of Image 1
- − Completely failed the edit instruction to change the character to the subject of Image 2
- − No changes were made to the face, clothing, or gender of the person in the reference pose
Verdict: This was a difficult task that both models struggled with. FLUX.2 [dev] Turbo followed the character instructions by including the man from Image 2 and his accessories, but the final image is a horrific anatomical mess with two heads and disjointed limbs. Wan 2.7 failed the assignment entirely, providing what appears to be a cropped version of Image 1 with zero edits applied. FLUX.2 [dev] Turbo is the technical winner only because it attempted to merge the subjects, despite the catastrophic failure in physical coherence.
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 [dev] Turbo
- + Excellent cinematic lighting and atmosphere
- + High level of detail in the horse's fur and the astronaut's suit texture
- + Dynamic composition with a sense of motion
- − Failed the specific spatial instruction for the horse to be on top of the astronaut
Wan 2.7
- + Clean, sharp image resolution
- + Good anatomical rendering of the horse
- + Well-defined background with spiral galaxies
- − Failed the specific spatial instruction for the horse to be on top of the astronaut
- − Appearance is somewhat generic and less 'surreal' than requested
Verdict: Both FLUX.2 [dev] Turbo and Wan 2.7 failed to follow the specific 'horse on top' instruction, which suggests a common difficulty with subverting the standard concept of a rider. FLUX.2 [dev] Turbo is the preferred choice as it better captures the 'cinematic' and 'surreal' stylistic cues from the prompt with superior lighting and atmospheric depth compared to the more clinical look of Wan 2.7.
Outfit Transfer Challenge
Editing“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.”
AI Judge Analysis
FLUX.2 [dev] Turbo
- + Successfully transferred the coat, scarf, and sunglasses from Image 2.
- + Maintained high resolution and textures of the clothing.
- − Failed to keep the person's face from Image 1, replacing them with the person from Image 2.
- − Added excessive, unrequested jewelry that was not in either source image.
- − Changed the person's skin condition entirely.
Wan 2.7
- + Perfectly preserved the specific person, face, and unique skin features from Image 1.
- + Accurately maintained the beach background and wooden structure.
- + Correctly applied clothing to the person's specific body pose.
- − Did not use the exact outfit from Image 2, instead generating a generic 'elaborate' black and gold coat.
- − Failed to include the scarf or specific sunglasses from Image 2.
Verdict: This is a case of conflicting failures: FLUX.2 [dev] Turbo succeeded at the clothing transfer but completely failed to preserve the base person, while Wan 2.7 perfectly preserved the person but failed to use the specific clothing requested. Wan 2.7 is the likely winner because the instruction explicitly required keeping the person's face and hair completely unchanged, which FLUX.2 [dev] Turbo ignored completely.
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 [dev] Turbo
- + Excellent photorealism with cinematic lighting and realistic textures.
- + Perfect adherence to the perspective of being inside the taxi.
- + Great character expressions, especially the bored businesswoman.
- − The capybara's hands look slightly more humanoid/monstrous than animal-like.
Wan 2.7
- + Natural composition and clear character placement.
- + Good rendering of the city lights and background bokeh.
- + The capybara's fur has high detail and definition.
- − The businesswoman is sitting in the passenger seat rather than the back seat.
- − The perspective feels more like it is looking into the taxi from a drone or a side window than being 'inside' the scene.
- − The capybara's head is angled somewhat unnaturally for a driver.
Verdict: FLUX.2 [dev] Turbo followed the prompt much more accurately by placing the woman in the back seat and capturing the bored 'everyday' atmosphere perfectly. Wan 2.7 failed the spatial requirement by putting the passenger in the front seat, although both models did a great job with the capybara's attire and the general NYC night vibe.
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 [dev] Turbo
- + Excellent typography style that matches the gothic theme perfectly.
- + Superb cinematic lighting with a moody, dark parchment feel.
- + Perfect adherence to all text requirements with high legibility.
- − Composition is a bit more centered and simple compared to the varied elements of the other model.
Wan 2.7
- + Highly detailed border with skulls, thorns, and hidden lanterns.
- + Creative use of a layered frame-within-a-frame composition.
- + Includes charming extra details like crows and a bubbling cauldron.
- − The parchment is too bright and clean, losing the 'dark parchment' and 'cinematic' mood requested.
- − Text rendering on the date and time line is slightly less polished than the first image.
Verdict: FLUX.2 [dev] Turbo captured the requested 'cinematic lighting' and 'dark parchment' aesthetic much more effectively, creating a cohesive and spooky invitation. While Wan 2.7 added more interesting decorative elements like skulls and birds, its overall look was too bright and illustrative, failing the specific atmospheric requirements of the prompt.
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 [dev] Turbo
- + Excellent preservation of the original facial features and expression
- + Highly realistic hair texture and individual strand rendering
- + Maintains the lighting and grain of the source image perfectly
- − The choice of an afro-texture style is a bold interpretation that might not be what every user expects for a 'natural head of hair' given the beard texture
Wan 2.7
- + Natural and plausible hair style that blends well with the existing beard
- + Good preservation of background and clothing
- + Realistic hairline placement
- − Noticeable AI artifacting on the left temple where the hair meets the forehead
- − Slight alteration of the shape of the nose compared to the original
Verdict: FLUX.2 [dev] Turbo provides a technically superior edit with exceptional texture and perfect preservation of the original's facial features, despite picking a more stylistically distinct haircut. Wan 2.7 also performs well but suffers from visible smudging/artifacts at the hairline on the left side and slight facial warping.
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 [dev] Turbo
- + Excellent photographic texture on the fish and rice grains.
- + Perfectly clean and well-balanced typography.
- + Realistic lighting and shadows consistent with the dioramas style.
- − The diorama base is a bit small, cutting into the plate's footprint.
Wan 2.7
- + Better variety of sushi pieces as requested in the 'sushi' theme.
- + Captures the 'cartoon' aesthetic mentioned in the prompt more effectively.
- + Spacious and clean diorama base layout.
- − The 'JAPAN' text is slightly clipped at the top edges.
- − Minor artifacts such as the floating soy sauce drop near the shrimp and inconsistent textures on the maki.
Verdict: FLUX.2 [dev] Turbo produces much higher quality textures and professional typography, though it leans more toward realism than 'cartoon'. Wan 2.7 provides a more creative arrangement and captures the 'cartoon' vibe better, but suffers from technical flaws like text clipping and small object artifacts. FLUX.2 is the winner due to its superior clarity and polished execution.
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 [dev] Turbo
- + Excellent caricature technique with a large head and small body while maintaining the subject's likeness.
- + Highly detailed and coherent integration of all theme elements: anchor desk, hockey rink setting, and numerous dogs.
- + Superior artistic rendering with professional-looking lighting and perspective.
- − The text on the anchor desk is gibberish.
- − The character lost the denim jacket from the source image, though the suit fits the 'anchor' persona better.
Wan 2.7
- + Incorporates fun elements like a dog in a hockey helmet and speech bubbles.
- + Maintains the selfie-style composition of the original photograph.
- + Readable text in some speech bubbles.
- − Lower quality illustration style with some messy line work and flat coloring.
- − The hockey rink is represented as a tiny, floating box which feels disconnected from the scene.
- − Anatomical issues with the dogs, such as the one in the bottom right.
Verdict: FLUX.2 [dev] Turbo provided a much more professional and creative caricature, successfully blending the TV anchor role with a hockey arena setting and multiple dogs. While Wan 2.7 followed the selfie composition of the source photo more closely, its execution of the hockey and dog elements felt cluttered and lower in visual quality compared to the polished 'sports-desk' concept of FLUX.2.
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 [dev] Turbo
- + Perfectly captures the 'tumbling together' action with dynamic posing.
- + Superior rendering of 'dew sparkles' and atmospheric god rays.
- + Excellent character interaction with cohesive fur-to-interaction lighting.
- − The fox's anatomy is slightly more puppy-like than distinctively vulpine.
Wan 2.7
- + Strong 'god rays' lighting effect from the top of the frame.
- + Clear inclusion of all four requested animals with distinct silhouettes.
- + Good usage of diverse wildflower colors.
- − The kitten has a distorted paw/extra limb resting on the bunny.
- − The animals appear to be floating or awkwardly superimposed rather than interacting on the ground.
- − The fox's face lacks the hyper-photorealistic detail found in the other animals.
Verdict: FLUX.2 [dev] Turbo significantly outperforms Wan 2.7 by creating a more believable and dynamic interaction between the animals, truly capturing the 'tumbling' aspect of the prompt. While Wan 2.7 has strong lighting, it suffers from anatomical errors in the kitten and a less integrated composition that feels like a collage.
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 [dev] Turbo
- + Excellent character translation into a Studio Ghibli art style with rounded features and distinct line work.
- + Atmospheric background enhancements including cherry blossoms and soft pastel lighting that match the prompt.
- + Perfect preservation of the original meme composition and character poses.
- − The facial expression of the man is slightly softened, losing a bit of the original 'pucker' intensity.
Wan 2.7
- + Successfully applies a watercolor texture and hand-painted aesthetic to the image.
- + Maintains the structural integrity and layout of the source photo very well.
- − The art style leans more toward generic Western watercolor illustration than the specific Studio Ghibli anime aesthetic.
- − The woman in the foreground's face looks slightly semi-realistic and doesn't blend as well with the painterly background.
Verdict: FLUX.2 [dev] Turbo is the clear winner as it successfully captured the specific 'Studio Ghibli' aesthetic requested, altering the character designs and adding dreamy environmental details like blossoms. Wan 2.7 provided a high-quality watercolor edit, but it failed to capture the iconic stylistic markers of the Ghibli brand as effectively as the other model.
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 [dev] Turbo
- + Excellent adherence to hair blowing instruction
- + Significant amount of motion-contributing elements
- + Preserves the original identity and background perfectly
- − Leaves sometimes appear to float on top of the character rather than around her
Wan 2.7
- + Natural integration of leaves with motion blur
- + Good preservation of original image details
- + Hair movement looks realistic
- − Hair motion is less 'dynamic' compared to Model A
- − Fewer leaves added compared to the requested lively feel
Verdict: FLUX.2 [dev] Turbo followed the prompt more aggressively, providing a very dynamic look with hair spreading out significantly. Wan 2.7 also performed well but was more conservative with the hair movement and leaf count, making FLUX.2 [dev] Turbo the more effective choice for this specific energetic request.
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 [dev] Turbo
- + Excellent typography including the grave accent on the letter 'è'
- + Perfectly captures the requested vintage grainy texture and minimalist emblem aesthetic
- + Clean and balanced layout with a professional vector feel
- − The steam trails are slightly high and sparse compared to the cloche
Wan 2.7
- + Clear and readable text
- + Nice use of color palette and star border elements
- − Misspelled the name as 'Florion' instead of 'Florian'
- − The cloche is missing its handle and the steam is floating disconnected from the object
- − The composition is a bit crowded with too many secondary icons
Verdict: FLUX.2 [dev] Turbo followed the prompt with much higher accuracy, correctly spelling 'Caffè Florian' and capturing the specific minimalist vintage texture requested. Wan 2.7 suffered from a spelling error and a less cohesive design that felt more like a modern badge than a classic restaurant emblem.
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 [dev] Turbo
- + Excellent text rendering and character names
- + Consistent high-detail vector illustrations
- + Included creative additions like the crew silhouettes
- − The layout is cluttered and lacks a clear logical flow through the steps
- − Unnecessary repetition of the Earth and Translunar icons
- − Literal interpretation of 'Saturn Vicon' as text instead of just an icon
Wan 2.7
- + Highly professional vertical infographic layout with a clear hierarchy
- + Matches the requested 'Flat-vector style' and 'NASA-inspired palette' perfectly
- + Included impressively accurate supporting technical data like mission dates and velocities
- − Minor spelling errors in secondary text (e.g., 'Tranquiliry', 'Descript')
- − Icons are less detailed than model A's illustrations
Verdict: Wan 2.7 produced a superior infographic that follows the requested structure flawlessly, featuring a professional vertical flow and consistent iconography. While FLUX.2 [dev] Turbo has better spelling and more detailed illustrations, its layout is chaotic and fails to effectively communicate the chronological steps of the mission.
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