Black Forest Labs' compact, open-source image generation model with sub-second inference, optimized for production and near real-time applications with multi-reference support
Settled by community votes across 20 shared challenges, with an AI judge weighing in on each.
FLUX.2 [klein] 4B
#32 of 62 in Text-to-Image
FLUX.2 [klein] 9B
#13 of 32 in Image Editing
Where the votes landed
FLUX.2 [klein] 4B
0%
win rate
Ties
0%
FLUX.2 [klein] 9B
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 [klein] 4B
- + Excellent photographic realism in the texture of the red book cover.
- + Clean, sharp geometry for the glass cube with realistic internal reflections.
- + Lighting accurately follows the window source from the left.
- − The plant is very blurred in the background, making it less distinct through the glass.
FLUX.2 [klein] 9B
- + Successfully shows the green plant more clearly through the glass walls of the cube.
- + High level of detail in the wooden table grain.
- + Good use of caustics where the blue sphere projects light onto the table through the glass.
- − The sphere appears to be floating mid-air rather than resting at the bottom of the cube.
- − The geometry of the glass cube is slightly rounded and warped compared to a true cube.
- − The book is slightly too large for the cube, creating a less balanced composition.
Verdict: Both models followed the complex spatial instructions perfectly. FLUX.2 [klein] 4B produced a more physically grounded image with the sphere resting on the base and a perfect cube shape, whereas FLUX.2 [klein] 9B captured the 'visible through the glass' aspect of the plant more effectively but suffered from a floating sphere and slightly warped geometry.
Man and Car in California
Editing“Make a photo of the man driving the car down the California coastline”
AI Judge Analysis
FLUX.2 [klein] 4B
- + Excellent preservation of the man's identity and facial features
- + Successfully combines both source images into a single coherent scene
- + Maintains the pattern and style of the man's plaid coat from the source image
- − The driver appears slightly too large relative to the car interior
FLUX.2 [klein] 9B
- + Successfully places the car on a coastal road
- + Good motion blur on the wheels and road surface
- − The man is barely visible, with only the top of his hair showing behind the headrest
- − Fails to significantly incorporate the subject's face/identity from the second source image
Verdict: FLUX.2 [klein] 4B is the clear winner as it successfully integrated the man from the second source image into the driver's seat of the car, maintaining his likeness and clothing accurately. In contrast, FLUX.2 [klein] 9B essentially obscured the subject, showing only a small portion of his hair and failing the prompt's instruction to show the man driving.
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 [klein] 4B
- + Excellent depiction of rain on pavement and wet textures.
- + Good inclusion of bokeh from background traffic.
- + Effective shallow depth of field.
- − Anatomical and physical errors where the man appears to be merging with the bike seat/frame.
- − Mechanical nonsense in the bicycle drivetrain and rear wheel attachment.
- − The man's right hand position is awkward and lacks clear intent.
FLUX.2 [klein] 9B
- + Highly realistic skin texture and facial details.
- + Better logic in the physical interaction between the man and the bicycle.
- + Includes details like a toolbox which adds to the storytelling of 'repairing'.
- − Lacks the requested motion blur on the passing cars.
- − Background cars feel static compared to the prompt's motion blur requirement.
Verdict: While FLUX.2 [klein] 4B followed the 'motion blur' instruction better, it suffered from significant structural failures where the man and the bicycle merged into an impossible shape. FLUX.2 [klein] 9B provided much higher anatomical realism, better skin textures, and a more coherent scene, making it the superior image despite the cars being mostly stationary.
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 [klein] 4B
- + Excellent metallic texture and engraving detail on the pauldrons
- + Very clean face with lifelike skin texture
- + Strong adherence to the 'beads in hair' prompt
- − The character looks slightly too clean and 'young' for the 'battle-worn' description
- − Background bokeh is a bit generic
FLUX.2 [klein] 9B
- + Superb interpretation of 'battle-worn' with grit, deeper scars, and a rugged expression
- + Incredible texture on the weathered leather straps and chainmail
- + More convincing lighting integration with the torches and sparks
- − Hair braids look slightly more like cornrows than standard braids with beads
- − The background torches are somewhat symmetrically placed
Verdict: Both models performed exceptionally well on the prompt, but FLUX.2 [klein] 9B captures the 'battle-worn' essence much better through more detailed skin weathering and complex leather textures. While FLUX.2 [klein] 4B is very polished and highlights the armor engravings beautifully, it feels a bit too clean compared to the ruggedness suggested by the prompt.
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 [klein] 4B
- + Stronger grid-based layout for photography as requested.
- + Better text placement that mimics a realistic menu flow.
- + Higher diversity in the food types depicted in the images.
- − Nonsensical section headers like 'FRAZZA' and 'MDAINS'.
- − Some food images are slightly muddy in detail compared to B.
- − Lack of currency symbols makes pricing less clear.
FLUX.2 [klein] 9B
- + Better typography rendering with fewer gibberish characters in headers.
- + Clean, modern minimalist presentation with good use of white space.
- + Accurately includes dollar signs for pricing.
- − Repetitive food imagery, with almost every section showing a pizza regardless of the header.
- − Redundant section headers (Appetizers appears twice side-by-side).
- − The grid layout for photos is less complex than Model A's.
Verdict: While both models struggle with English text, Model B provides a cleaner minimalist aesthetic and much more readable typography. However, Model A followed the prompt's request for a variety of food types (appetizers, mains, pizza) much better, whereas Model B simply used pizza images for almost every category including mains and appetizers.
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 [klein] 4B
- + Successfully included all required text elements.
- + Good photorealistic texture on the burger bun and patties.
- + Effectively uses glowing embers to create a sense of motion.
- − Significant text rendering errors for the main title ('MAAC AGID BUIRCGER').
- − The burger is mostly intact rather than 'exploded' with suspended components as requested.
FLUX.2 [klein] 9B
- + Perfect text rendering for all titles and labels.
- + Better adherence to the 'exploded' request with sauce and components separated.
- + Superior fiery effects and glowing starburst design.
- − The burger components could be even further separated to maximize the 'mid-air' suspension effect.
Verdict: FLUX.2 [klein] 9B is the clear winner as it accurately rendered all requested text, whereas FLUX.2 [klein] 4B failed significantly on the main title. Additionally, FLUX.2 [klein] 9B better interpreted the 'exploded' aspect of the prompt by showing sauce droplets and separating the layers more dynamically.
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 [klein] 4B
- + Excellent chalk texture and smudge marks for a realistic board feel.
- + Captures the natural variation in letter size and slant consistently.
- + High contrast and legible layout.
- − Numerous spelling errors including 'Truffel', 'Musheram', 'Ootrpous', and 'Brawn Buter'.
- − Extra spaces and characters in the title such as 'TODAY'S S TPECIALS'.
FLUX.2 [klein] 9B
- + Near-perfect spelling of complex menu items like 'Truffle Mushroom Risotto'.
- + Superior elegant cursive handwriting in the title.
- + Balanced composition with professional-looking line breaks.
- − One minor typo in the footer text ('fress' instead of 'fresh').
- − The chalk smudge texture is a bit heavy, though stylistically acceptable.
Verdict: FLUX.2 [klein] 9B is the clear winner due to its significantly better text rendering and spelling accuracy, correctly identifying all requested menu items. While FLUX.2 [klein] 4B has great chalk textures, it fails almost every word in the body text with phonetic misspellings.
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 [klein] 4B
- + Successfully replicates the complex cross-legged pose on the ottoman.
- + Accurately applies the character's scarf and black clothing style.
- − Retains the long, flowing hair from the source female model instead of the character's short hair.
- − Skin tone is significantly lighter than the character reference.
FLUX.2 [klein] 9B
- + Perfectly replicates the character's short hairstyle and facial features.
- + Accurately represents the character's skin tone and integrates the scarf and sunglasses well.
- + Maintains the difficult body position while adapting it to the specific character.
- − One hand is clenched in a fist, deviating slightly from the delicate finger position in Image 1.
Verdict: FLUX.2 [klein] 9B is the clear winner as it successfully transferred both the pose from Image 1 and the character identity (hair, skin tone, face) from Image 2. FLUX.2 [klein] 4B failed to swap the hair, resulting in a hybrid character that looks more like the person in the pose reference wearing the character's clothes.
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 [klein] 4B
- + Excellent anatomical rendering of the horse's legs and hooves
- + Clever grounding of the scene using the atmospheric haze of Earth's horizon
- + Strong lighting consistency between the astronaut and the environment
- − The astronaut's face appears somewhat distorted and uncanny
FLUX.2 [klein] 9B
- + Enhanced surrealism with multiple planets and celestial bodies filling the frame
- + Better facial rendering for the astronaut within the helmet
- + Dynamic galloping pose that conveys a sense of motion in space
- − Contains nonsensical gibberish text at the bottom of the image
- − The horse's front left leg has a slight anatomical clipping issue at the chest
Verdict: Both models failed the specific instruction for the horse to be 'on top' (implying a horse riding a human), instead providing the standard astronaut-on-horse interpretation. FLUX.2 [klein] 4B (Model A) is the winner because it provides a cleaner, more cinematic composition without the garbled, distracting text generated by FLUX.2 [klein] 9B (Model B).
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 [klein] 4B
- + Excellent preservation of the original person's face, hair, and unique skin patterns.
- + Accurately recreates the scarf pattern and coat style from the reference image.
- + Maintains the exact beach lighting and background details.
- − The coat is missing the internal shirt, leaving the chest exposed which was not in the reference.
- − The hand in the pocket has some minor anatomical blurring/artifacting.
FLUX.2 [klein] 9B
- + Perfectly captures all layers including the black shirt under the coat and scarf.
- + Correctly incorporates the gold jewelry and accessories seen in the reference image.
- + Maintains high fidelity to the original person's facial features and background.
- − The gold necklaces are slightly more numerous/elaborate than in the source image.
- − Very subtle change to the lighting on the face compared to the original image.
Verdict: Both models performed exceptionally well at preserving the identity and background of the original image while transposing the new outfit. FLUX.2 [klein] 9B is the winner because it adhered more strictly to the 'all layers' instruction by including the black shirt, whereas FLUX.2 [klein] 4B left the person's chest bare, failing to fully replicate the outfit's structure.
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 [klein] 4B
- + Excellent photorealism with shallow depth of field on the background
- + Captures the bored expression of the passenger perfectly
- + The capybara's paws on the wheel look relatively natural and proportional
- − The car interior feels more like a small vintage vehicle than a standard NYC taxi
FLUX.2 [klein] 9B
- + More accurate New York City taxi atmosphere with external yellow cabs visible
- + Great attention to detail with the light from the phone illuminating the passenger's face
- + Creative cap design that attempts to include text
- − The passenger appears to be in the front passenger seat rather than the back seat
- − The capybara's hands/paws look slightly like human gloves rather than animal paws
Verdict: FLUX.2 [klein] 4B (Model A) followed the spatial instructions more accurately, placing the passenger in the back seat as requested and capturing the 'bored' expression better. FLUX.2 [klein] 9B (Model B) had better lighting effects and background environmental storytelling with the other taxis, but it failed the seating arrangement prompt by placing the passenger in the front seat.
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 [klein] 4B
- + Strong cinematic lighting on the jack-o-lantern
- + Atmospheric background with subtle architectural silhouettes
- − Major spelling errors in the main title
- − Several spelling errors in the date and location text
- − Missing the 'Time' line entirely
FLUX.2 [klein] 9B
- + Perfect text rendering for all requested fields including the title and scroll
- + Excellent adherence to all prompt details including the date, time, and specific location
- + Dynamic composition with a visible moon and balanced thorny border
- − Slightly less 'gritty' parchment texture compared to model A
Verdict: FLUX.2 [klein] 9B is the clear winner as it successfully rendered all the requested text with zero spelling errors, whereas FLUX.2 [klein] 4B failed significantly on the typography. Both models followed the stylistic instructions well, but the 9B model provided a much more functional invitation by including the full date and time correctly.
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 [klein] 4B
- + Excellent preservation of the original facial features and expression
- + Hair texture looks natural and matches the style of the facial hair
- + Perfect source preservation with no changes to the background or clothing
- − The hairline on the forehead is slightly less integrated than model b
FLUX.2 [klein] 9B
- + Highly realistic hair texture with curly details
- + Strong integration of the hairline with realistic flyaway hairs
- + Perfectly preserves lighting and facial structure
- − None notable
Verdict: Both models handled the editing task exceptionally well, preserving the original person and environment perfectly while adding the requested hair. FLUX.2 [klein] 9B is the winner due to more complex hair texture and a slightly more natural-looking hairline integration across the forehead.
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 [klein] 4B
- + Excellent high-clarity 3D rendering of the sushi textures
- + Strict adherence to the 45-degree isometric perspective
- + Clean layout with high visual appeal
- − Text is missing the letter 'I' in 'SUSHI'
- − Failed to include a square diorama base/block
- − Flag icon is a generic red and white stripe, not a specific flag
FLUX.2 [klein] 9B
- + Perfect text rendering for both 'JAPAN' and 'SUSHI'
- + Followed the instruction for a small raised diorama base
- + Excellent 3D cartoon style with nice PBR-like soft surfaces
- − Flag icon is incorrect (appears more like the flag of Yemen)
- − The lighting is slightly flatter compared to Model A
Verdict: While FLUX.2 [klein] 4B has slightly more realistic textures on the fish, it failed to render the text correctly and missed the diorama base requirement. FLUX.2 [klein] 9B followed all structural prompts, including the diorama base and perfect text rendering, making it the more accurate image overall despite the incorrect flag icon.
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 [klein] 4B
- + Successfully captures the TV anchor profession with a news desk and studio monitors.
- + Maintains recognizable facial features from the source image in a caricature style.
- + Includes two well-drawn dogs that fit the art style.
- − Completely misses the 'hockey' requirement.
- − Hands appear slightly mangled with an incorrect number of fingers.
FLUX.2 [klein] 9B
- + Includes all three requested elements: TV anchor, dogs, and a hockey arena/crowd setting.
- + Creative integration of the hockey theme by placing the news desk inside an arena.
- + Good preservation of the subject's likeness while applying a classic caricature distortion.
- − The hands are poorly rendered, with a very strange thumb/finger configuration on the right hand.
- − Some minor artifacts in the crowd and text details.
Verdict: Model B is the clear winner because it followed the entire prompt, whereas Model A failed to include the hockey element. Model B creatively combined the three themes by placing a TV news anchor desk in the middle of a hockey arena filled with dogs. While both models struggled with drawing hands, Model B's adherence to all requested themes makes it superior.
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 [klein] 4B
- + Natural lighting and atmospheric god rays
- + Extremely soft and detailed fur texture
- + Includes more animals as requested by the prompt
- − Missed the baby bunny explicitly requested in the prompt
- − Unnecessary inclusion of two kittens instead of varying the animal types
FLUX.2 [klein] 9B
- + High energy and dynamic poses suited to the word 'tumbling'
- + Vibrant colors and sharp details on the butterflies
- + Excellent facial expressions that feel joyful
- − Completely missed the baby bunny requested
- − Anatomically awkward paw placement on the kitten
- − The fox's eyes appear slightly asymmetrical
Verdict: Both models failed to include the baby bunny, a key element of the prompt. FLUX.2 [klein] 4B followed the instruction for multiple kittens but missed the diverse variety requested, while FLUX.2 [klein] 9B captured a more energetic and playful 'tumbling' motion that fits the spirit of the prompt better, despite fewer animals.
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 [klein] 4B
- + Excellent preservation of the original pose and character expressions.
- + High-quality watercolor texture that very closely mimics hand-painted Ghibli backgrounds.
- + Maintains the urban setting from the original image while softening it with the requested style.
- − The color palette is a bit washed out compared to the vibrant Ghibli style.
FLUX.2 [klein] 9B
- + Beautifully rendered hand-painted aesthetic with warm lighting.
- + Colors are balanced and visually appealing.
- + Successfully transforms the urban environment into a dreamy, rural Ghibli-esque landscape.
- − Fails to preserve the core 'distracted boyfriend' meme context by changing the jealous girlfriend's expression to a peaceful smile.
- − Character anatomy in the background is slightly less integrated.
Verdict: Each model successfully captures the Ghibli aesthetic with soft lines and watercolor textures. However, FLUX.2 [klein] 4B is the clear winner for an image editing task as it preserves the essential narrative of the original image—specifically the distinct facial expressions that define the meme—whereas FLUX.2 [klein] 9B changes the mood of the characters, making them look happy and losing the source context.
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 [klein] 4B
- + Excellent preservation of the woman's face and original features.
- + Highly realistic hair physics that look naturally wind-swept.
- + The leaves integrated realistically into the scene with subtle focus depth.
- − The leash handle has been slightly simplified compared to the source.
FLUX.2 [klein] 9B
- + Successfully added significant motion to the hair.
- + Abundant leaves create a high sense of energy.
- − The woman's facial features were altered significantly from the source image.
- − The hair strands look somewhat artificial and overly symmetrical.
- − A leaf is awkwardly overlapping the dog's mouth/tongue area.
Verdict: FLUX.2 [klein] 4B is the clear winner as it successfully applied the dynamic edits while perfectly preserving the identity of the subject from the source image. FLUX.2 [klein] 9B, while energetic, failed a key requirement of image editing by noticeably changing the woman's face and adding strands of hair that look less natural than its counterpart.
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 [klein] 4B
- + Excellent texture on the light background
- + Balanced and symmetric vector emblem style
- − Spelling error in the main name ('FLAXTION' instead of 'Florian')
- − Redundant 'Est. 1720' text appearing twice
FLUX.2 [klein] 9B
- + Perfect text rendering for both the name and establishment date
- + Strong composition with a cohesive circular frame
- + Effective use of warm brown and cream tones
- − Steam detail is a bit thick compared to a minimalist style
Verdict: While both models correctly identified all visual elements of the prompt, FLUX.2 [klein] 9B is the winner due to its accurate text rendering. FLUX.2 [klein] 4B failed to spell the name correctly and included redundant text, whereas the 9B model delivered a professional, functional logo design.
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 [klein] 4B
- + Successfully captures a flat, clean vector aesthetic
- + Includes relevant silhouettes of the three astronauts as supporting detail
- + Follows the NASA-inspired color palette effectively
- − Text rendering is very poor and mostly nonsensical
- − Layout is disorganized with icons floating without a clear flow
- − Incorrect iconography for several steps, such as duplicating Earth and using a generic rocket shape
FLUX.2 [klein] 9B
- + Clearer infographic structure with arrows indicating a sequence of events
- + Much stronger text rendering, correctly identifying 'Apollo 11' and several mission phases
- + Distinct and recognizable icons for Earth, Moon, and the Lunar Module
- − Layout is a bit crowded and visually noisy for a 'clean' request
- − Slight spelling errors in labels such as 'AOILLO' and 'LANDINING'
- − The rocket design is more a generic cartoon style than a Saturn V
Verdict: FLUX.2 [klein] 9B is the superior choice because it understands the structure of an infographic, using directional arrows and logical flow to explain the mission steps. While FLUX.2 [klein] 4B has a slightly cleaner artistic style, its complete failure to produce legible text and its confusing layout make it unsuccessful as a source of information.
Explore each model
Black Forest Labs' distilled 9 billion parameter image generation model with sub-second inference and multi-reference support