Distilled version of Black Forest Labs' FLUX.2 [dev] outperforming it at a cheaper price. Developed by fal.ai.
Settled by community votes across 19 shared challenges, with an AI judge weighing in on each.
FLUX.2 [dev] Turbo
#3 of 62 in Text-to-Image
Wan 2.6
#26 of 62 in Text-to-Image
Where the votes landed
FLUX.2 [dev] Turbo
66.7%
win rate
Ties
0.0%
Wan 2.6
33.3%
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 depiction of physics and glass refraction
- + Highly realistic textures on the wooden table and red book cover
- + Very accurate lighting that creates a believable soft mood
- − The glass plant leaves behind the cube look slightly messy/distorted
Wan 2.6
- + Vibrant colors on the blue sphere
- + Strong adherence to the spatial positioning requested in the prompt
- + Good use of direct sunlight effects
- − The glass cube geometry is flawed, showing extra vertical panes inside the cube
- − The red book looks overly small compared to the cube and has inconsistent edge wear
Verdict: FLUX.2 [dev] Turbo produces a much more realistic and physically coherent image, specifically regarding the construction of the glass cube and the texture of the materials. While Wan 2.6 captures the colors well, it suffers from structural artifacts within the glass cube that break the illusion of reality.
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 character preservation maintaining the specific plaid pattern and hair style.
- + High attention to interior detail with clear dashboard instruments.
- + Natural composition with realistic motion blur on the road.
- − The car color appears slightly more silver/champagne than the brilliant white of the source.
Wan 2.6
- + Successfully captures the man's expression and facial features.
- + The background scenery is very vibrant and clearly evocative of the California coast.
- + Good preservation of the car's exterior design and white color.
- − The man is sitting too low in the seat, making the scale look incorrect.
- − There is a strange ghosting artifact near the palm tree in the upper left.
Verdict: Both models performed well on this complex multi-subject editing task. FLUX.2 [dev] Turbo is the winner because it maintained a much more realistic scale for the driver within the vehicle and preserved the clothing details more accurately. While Wan 2.6 created a beautiful landscape, the positioning of the man in the car feels disjointed compared to the high-quality integration in the FLUX.2 image.
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 the 'imperfect framing' prompt with a square, slightly unbalanced street photography feel.
- + High realism in the textures of the road, the bicycle, and the man's clothing.
- + Effective use of motion blur on the background cars to simulate a fast shutter speed in a busy environment.
- − The man appears to be floating or kneeling awkwardly, with his legs merging into the dark pavement.
- − The front wheel of the bicycle is clipped and lacks a clear connection to the ground.
Wan 2.6
- + Beautiful cinematic lighting with strong reflections on the wet pavement.
- + Naturalistic skin texture and convincing hands/anatomy during the repair task.
- + Superior depth of field and bokeh that creates a professional photographic look.
- − The raindrops on the man's jacket look more like static glass beads or physical artifacts than moving water.
- − The composition is a bit too 'perfectly' centered, leaning away from the requested 'imperfect framing'.
Verdict: FLUX.2 [dev] Turbo followed the specific stylistic cues like 'imperfect framing' and 'motion blur' much better, capturing the frantic energy of a street photo. However, Wan 2.6 produced a much more visually pleasing and anatomically correct image with superior lighting, even if it felt slightly more 'staged' than 'candid'.
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 sharpness and skin texture
- + Perfect realization of braided hair with small beads
- + Accurate rendering of leather straps and buckles
- − The torch in the background looks a bit like a flat graphic element
Wan 2.6
- + Strong atmospheric lighting and cinematic mood
- + Excellent tattered cloth details on the underlayer
- + Realistic representation of wet dirt/mud on the skin
- − The beads in the hair are fewer and less distinct than requested
- − Slightly softer facial details compared to Model A
Verdict: Both models followed the prompt exceptionally well, capturing the essence of a battle-worn paladin. FLUX.2 [dev] Turbo provides a clearer, more detailed look at the character's face and the specific intricate elements like the beads and leatherwork, whereas Wan 2.6 offers a superior cinematic atmosphere with grittier textures on the skin and cloth. FLUX.2 [dev] Turbo is the winner due to better hair detail and overall clarity.
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
- + Clean and authentic bold sans-serif typography for main headings.
- + Well-structured grid layout that separates images and text clearly.
- + Superior photographic quality and lighting in the food images.
- − Logical consistency issues with pricing (e.g., $260 for a pizza).
- − Contains gibberish text in the secondary headings and descriptions.
- − Section headers are messy, with a pizza appearing under the 'Mains' category.
Wan 2.6
- + Excellent colorful accents and geometric framing that feel modern.
- + More realistic casual dining price points (around $1.95 - $8.95).
- + Balanced use of negative space and grid alignment.
- − Severe spelling errors in headers (e.g., 'RESTAUR MENU', 'MAÏNS').
- − Lower clarity in the food photography compared to the other model.
- − Text layout is cluttered with strange symbols and distorted characters.
Verdict: FLUX.2 [dev] Turbo produces much higher quality food photography and cleaner main headers, but the pricing logic and categorization are poor. Wan 2.6 offers a better aesthetic interpretation of 'vibrant accents' and realistic pricing, but fails significantly on text rendering and image sharpness. FLUX.2 [dev] Turbo is the preferred choice for a professional design base due to its superior visual coherence.
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 typography with a consistent glowing flame effect.
- + Clean, photorealistic food photography with distinct layering of ingredients.
- + Precise execution of the requested starburst design for the price.
- − The 'sauce' looks a bit stagnant and plastic-like compared to the other textures.
- − The composition is a bit static for an 'exploded' view.
Wan 2.6
- + Dynamic composition with a strong sense of motion and energy.
- + Rich, atmospheric background with smoke and intense fire effects.
- + Appetizing food rendering, particularly the melted cheese and dripping sauce.
- − The price starburst looks like a flat clip-art element that clashes with the 3D scene.
- − The 'LIMITED TIME ONLY' text is slightly warped and less legible than Model A.
- − Missing the secondary bun piece at the bottom to complete the burger assembly.
Verdict: FLUX.2 [dev] Turbo produced a more balanced and professional-looking advertisement with superior text integration and adherence to the starburst request. While Wan 2.6 offered a more dynamic and exciting sense of motion, its final output was marred by inconsistent graphic elements that felt poorly integrated into the photorealistic scene.
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 realistic smudges and dust.
- + Flawless spelling and adherence to the specific date and menu items.
- + Highly consistent and realistic handwriting style across the entire board.
- − Slightly awkward line breaking on the first item with a floating dollar sign.
Wan 2.6
- + Great chalk dust accumulation at the bottom of the frame.
- + Strong handwriting aesthetic that feels very authentic to a cafe.
- + Correct spelling and adherence to the prompt's specific menu items.
- − Repeats the price '$24' unnecessarily on two lines for the first item.
- − Composition is slightly tilted and cropped more tightly than Model A.
Verdict: Both models performed exceptionally well on complex text rendering, but FLUX.2 [dev] Turbo is the winner due to a cleaner layout and superior text consistency. While Wan 2.6 has excellent environmental details like chalk dust, it had a minor logic error by repeating the price '$24' on two consecutive lines for the same dish.
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 anatomical realism for the horse
- + High-fidelity rendering of the spacesuit and textures
- + Sophisticated cinematic lighting and atmospheric dust
- − Failed the specific spatial instruction 'horse on top'
- − Less vibrant color palette compared to Model B
Wan 2.6
- + Vibrant and artistic background nebulae
- + Dynamic interaction with the light rays
- + Clean, high-quality rendering of the astronaut's visor reflections
- − Failed the specific spatial instruction 'horse on top'
- − Anatomical issues with the horse's left rear leg which appears mutated
- − Floating reins that lack physics coherence
Verdict: Both models failed the specific prompt constraint of putting the horse on top of the astronaut, instead defaulting to the standard interpretation of the phrase. FLUX.2 [dev] Turbo is the superior image due to its much better anatomical accuracy and more realistic cinematic integration, whereas Wan 2.6 has a noticeable structural error in the horse's hind leg.
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
- + Excellent transfer of the clothing items specified in Image 2, including the scarf pattern and jacket style.
- + Successfully captures the extra jewelry mentioned in the detailed instruction.
- − Completely failed the source preservation requirement by swapping the face and skin of Image 1 for the person in Image 2.
- − Replaced the base person entirely instead of editing them.
Wan 2.6
- + Perfectly preserved the base person from Image 1, including the unique skin patterns and facial features.
- + Accurately applied the clothing from Image 2 (peacoat, scarf, sunglasses) while adapting them to the subject's pose.
- − Missed the smaller jewelry accessories like the watch and rings present in the source image.
- − The sunglasses style is slightly different from the source image 2.
Verdict: FLUX.2 [dev] Turbo failed the core constraint of the challenge by replacing the subject's face and identity with the person from the clothing source image. Wan 2.6 followed the instructions perfectly, successfully dressing the base person from Image 1 in the outfit from Image 2 while maintaining his identity and the environment.
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 in fur texture and lighting
- + Captures the woman in the passenger seat with a very convincing bored expression
- + The taxi sign and interior details look high-quality
- − The woman is in the front passenger seat instead of the back seat as requested
- − The capybara's paws lack clear digits or anatomy
Wan 2.6
- + Follows the spatial instruction correctly by placing the woman in the back seat
- + Dynamic lighting with realistic rain effects on the windows
- + The capybara's pose with paws on the wheel is very natural
- − The woman's hand holding the phone is slightly distorted
- − The texture of the interior seat looks a bit worn or messy
Verdict: While FLUX.2 [dev] Turbo has slightly superior textures, it failed a key spatial requirement by placing the passenger in the front seat. Wan 2.6 correctly positioned the businesswoman in the back seat and captured the requested bored expression and professional capybara demeanor perfectly.
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 with perfect spelling and spacing.
- + Cohesive vintage aesthetic with a dark, moody color palette.
- + Clean and legible scroll banner integration.
- − The jack-o-lantern glowing effect is a bit flat compared to the lighting in Model B.
Wan 2.6
- + Superior cinematic lighting with a realistic glow and ground shadows.
- + Dynamic scroll banner shape that feels integrated into the scene.
- + Rich, vibrant colors in the night sky and pumpkin.
- − Minor spelling error in 'Invitation' (the 'n' at the end is malformed/missing).
- − The border is a bit cluttered with overlapping thorn and web assets.
Verdict: FLUX.2 [dev] Turbo produced a more professionally finished graphic with perfect text rendering and a very clean layout. While Wan 2.6 featured much better lighting effects and a more painterly atmosphere, it failed on the final letter of the main title, making FLUX.2 better for a functional invitation.
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 face, features, and lighting
- + Realistic hair texture and natural integration with the forehead
- + The background and clothing remain completely identical to the source
- − The hairstyle choice (afro) may not be the expected style for the subject
Wan 2.6
- + Natural-looking hairstyle that fits the character's aesthetic
- + Good hair texture and volume
- − Substantially altered the person's facial structure, especially around the eyes and cheekbones
- − The glasses frames were slightly changed in shape and color from the original
Verdict: FLUX.2 [dev] Turbo followed the editing instructions perfectly by adding hair while keeping all underlying features, clothing, and background details identical to the source. Wan 2.6 provided a more stylistically appropriate haircut but failed as an edit by regenerating the face, resulting in a different-looking person.
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 text rendering and typography layout
- + High-quality PBR textures on the salmon and rice
- + Clean, professional composition that looks like a stock icon
- − The salmon texture looks slightly more realistic than 'miniature 3D cartoon' style requested
Wan 2.6
- + Stronger adherence to the '3D cartoon' and 'isometric miniature' aesthetic
- + Good variety of sushi types (nigiri, shrimp)
- + Accurate layout of diorama base and text
- − Text layout is slightly crowded compared to Image A
- − The salmon texture is quite simplified and lacks the requested 'refined texture'
Verdict: FLUX.2 [dev] Turbo produced a very polished, professional graphic with superior text rendering and highly detailed materials. Wan 2.6 better captured the 'miniature/cartoon' style requested in the prompt, looking more like a 3D assets set, though its text styling was less refined. FLUX.2 [dev] Turbo is the overall winner for its exceptional clarity and high-end visual appeal.
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 preservation of the subject's facial features in a caricature style.
- + Cleverly integrates the news desk directly onto an ice rink.
- + Creative background details including dogs as hockey players on the screens.
- − The hands on the desk are slightly blurry and small compared to the head.
- − Text on the desk is garbled gibberish.
Wan 2.6
- + Good use of a fun, vibrant cartoon art style.
- + Includes specific hockey gear like the stick and puck prominently.
- + Clean, bold line work with high contrast.
- − The face is a generic cartoon character and loses the likeness of the source image.
- − The hockey stick is being held in a very awkward, non-functional way.
Verdict: FLUX.2 [dev] Turbo succeeded much better in the editing task by actually transforming the woman from the source image into a caricature while maintaining her specific facial identity. Wan 2.6 created a high-quality illustration, but the character no longer resembles the original person, and its integration of the elements feels more like a collection of clip-art versus the cohesive scene in FLUX.2 [dev] Turbo.
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
- + Excellent fur texture with high resolution and clarity
- + Beautifully rendered dew sparkles and bokeh in the foreground
- + Dynamic, joyful interactions between all four specified animals
- − The fox kit has eyes that look slightly more like a domestic dog than a wild fox
- − Butterflies are static and floating in a repetitive manner
Wan 2.6
- + Strong implementation of god rays and warm sunrise lighting
- + Very expressive facial features on the kitten and fox
- + Effective bokeh and depth of field creating a cinematic look
- − The kitten has five legs, with one appearing to sprout from its chest
- − The bunny is significantly less detailed and lacks the 'fluffy' texture of the other animals
- − The 'dew drops' in the foreground look like large floating glass orbs rather than water
Verdict: FLUX.2 [dev] Turbo provides a much more anatomically correct and consistent image, whereas Wan 2.6 suffers from a significant structural error where the kitten has an extra limb. While Wan 2.6 captures the 'god rays' lighting more dramatically, FLUX.2 [dev] Turbo excels in the 'ultra-detailed soft fur' requirement and overall image coherence.
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 adherence to the 'dreamy background' request with cherry blossoms and lush greenery
- + Preserves the characters' poses and facial expressions with high fidelity
- + Perfectly captures the hand-painted texture through soft pencil-like outlines and watercolor washes
- − The woman in the red dress has a slightly sharper gaze compared to the soft-focus source
Wan 2.6
- + Effective watercolor texture and pastel color palette
- + Good preservation of the original image's composition and character positions
- + Strong lighting control that adds to the 'warm, nostalgic' mood
- − Background is noticeably less detailed and 'Ghibli-esque' compared to Model A
- − White specks/artifacts on the red dress are a bit distracting
Verdict: Both models successfully transformed the 'Distracted Boyfriend' meme into a Studio Ghibli illustration style while maintaining the source's composition. FLUX.2 [dev] Turbo is the winner because it went further in transforming the environment, replacing a generic city street with a beautiful Ghibli-inspired landscape filled with flowers and trees, whereas Wan 2.6 kept the background relatively plain.
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 the 'flying leaves' request with numerous particles
- + Striking hair motion that feels very dynamic
- + High source preservation regarding the character and background
- − Hair looks slightly unnatural/symmetrical in its flow
- − The sheer volume of leaves creates a somewhat cluttered composition
Wan 2.6
- + Natural and realistic hair movement
- + Subtle and tasteful inclusion of leaves
- + Excellent source preservation including lighting and facial features
- − Fewer leaves make the 'energetic and lively' instruction feel less fulfilled compared to the other model
Verdict: Both models handled the image editing task exceptionally well, maintaining the character's identity and background perfectly. FLUX.2 [dev] Turbo provided a more literal and dramatic interpretation of the 'dynamic motion' request with a large swarm of leaves and highly splayed hair, while Wan 2.6 opted for a more realistic, subtle breeze that looks more like a professional photograph but feels less 'energetic'.
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
- + Perfect adherence to text, including the 'Est. 1720' text within a banner.
- + Excellent composition with a balanced emblem style that feels like a professional logo.
- + Consistent and beautiful vintage texture across both the paper and the vector art.
- − None identified.
Wan 2.6
- + Clean vector style with good contrast between light and dark brown tones.
- + Accurate spelling of the restaurant name.
- − The 'Est. 1720' banner is awkwardly placed and lacks the classic design requested.
- − The typography is a bit generic compared to the first model.
- − The background texture is concentrated only on the edges, making it look less integrated.
Verdict: FLUX.2 [dev] Turbo provided a superior result that perfectly captured the 'Est. 1720 banner' requirement with a cohesive, professional emblem design. Wan 2.6 struggled with the placement and style of the banner and offered a more basic interpretation of the typography and texture.
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 prompt adherence, including all requested stages of the mission.
- + High-quality text rendering for labels and headings.
- + Detailed and consistent vector-style illustrations and icons.
- − Redundant elements, such as multiple 'Translunar' and 'Landing' icons that clutter the flow.
- − The Saturn V rocket illustration includes strap-on boosters which were not part of the actual Apollo 11 vehicle.
Wan 2.6
- + Clean, minimalist aesthetic that follows the requested color palette.
- + Crisp text rendering for the title and names.
- − Fails completely on infographic content, missing all 6 requested steps and icons.
- − Large empty space in the center makes the composition feel unfinished.
Verdict: FLUX.2 [dev] Turbo significantly outperformed Wan 2.6 by actually following the complex prompt instructions. While FLUX.2 suffered from some layout redundancy and minor historical inaccuracy in the rocket design, it successfully created a full infographic with readable text and relevant icons, whereas Wan 2.6 failed to include any of the requested mission stages.
Explore each model
Alibaba's multimodal generation model from the Wan AI suite, supporting text-to-video, image-to-video, reference-to-video with audio, and text-to-image, in both Chinese and English