Head to head
Esc

Models · slot A

to navigate to pick

FLUX.2 [dev] Black Forest Labs FLUX.2 [pro] Black Forest Labs

Settled by community votes across 19 shared challenges, with an AI judge weighing in on each.

FLUX.2 [dev]

24.3 arena score

#19 of 62 in Text-to-Image

Skill signature · Text-to-Image

FLUX.2 [pro]

26.3 arena score

#8 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.2 [dev]

42.9%

win rate

Ties

0.0%

FLUX.2 [pro]

57.1%

win rate

42.9% 0.0% ties 57.1%
Shared challenges 19

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.”

FLUX.2 [dev]
FLUX.2 [pro]
100% wins 0% ties 0% wins

AI Judge Analysis

FLUX.2 [dev]

  • + Perfect adherence to all spatial instructions.
  • + Excellent rendering of glass texture and refractive light.
  • + Accurate interpretation of 'soft window light' affecting the scene.

FLUX.2 [pro]

  • + Sophisticated composition and photographic depth of field.
  • + Very realistic material rendering for the book and wooden table.
  • + Sharp, clean glass edges.
  • The green plant is not visible through the glass as requested, only around it.
  • The blue sphere is partially fused with the bottom of the glass cube.

Verdict: FLUX.2 [dev] followed the complexity of the prompt more accurately, specifically ensuring the plant was visible through the glass cube and positioning all elements correctly. FLUX.2 [pro] produced a more aesthetically polished and realistic image, but failed to show the plant through the glass and had a minor clipping error where the sphere meets the cube's base.

Man and Car in California

Editing
Edit instruction

“Make a photo of the man driving the car down the California coastline”

Source
FLUX.2 [dev]
FLUX.2 [pro]

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent preservation of the man's specific clothing including the pattern, scarf, and hairstyle.
  • + Realistic interior car detail that matches the luxury aesthetic of the source car.
  • + Dramatically captures the 'drive' with high-quality background motion blur.
  • The man's facial features changed significantly compared to the source image.
  • The car's exterior frame is partially cut off due to the close-up angle.

FLUX.2 [pro]

  • + Successfully keeps the entire car and the man in the frame while showing the coastline.
  • + Preserves the man's smile and identifiable facial features much better than the other model.
  • + Accurately places the car specifically on a coastal highway with motion on the wheels.
  • The man's clothing took a significant loss in detail, losing the specific plaid pattern and heavy scarf from the source.
  • Slightly less 'cinematic' lighting compared to Model A.

Verdict: FLUX.2 [dev] excels at preserving the details of the subjects' clothing and the car's interior, but it loses the man's likeness. FLUX.2 [pro] does a better job of showing the full scene and preserving the man's actual face and expression, even though it simplifies his outfit. FLUX.2 [pro] is the likely winner for better capturing the specific 'driving' action and the identity of the person while maintaining the overall car model.

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.”

FLUX.2 [dev]
FLUX.2 [pro]
33% wins 0% ties 67% wins

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent representation of motion blur from passing cars as requested.
  • + Captures the feeling of 'light rain' through visible droplets and atmospheric haze.
  • + The framing feels appropriately 'imperfect' and candid for a street photo.
  • Significant anatomical and mechanical errors where the man's legs and the bicycle frame merge in a confusing way.
  • The bicycle's structure is nonsensical in the center area.

FLUX.2 [pro]

  • + Extremely high detail in skin texture and clothing materials.
  • + Clear, logical bicycle mechanics and a realistic squatting pose for the subject.
  • + Beautifully rendered reflections and wet pavement textures.
  • Failed to include the requested 'motion blur from passing cars'.
  • The background car is static and doesn't convey the busy street energy requested.

Verdict: FLUX.2 [dev] followed the complex motion blur and framing instructions much better, creating a more atmospheric and dynamic scene, though it suffered from major physical clipping issues between the man and the bike. FLUX.2 [pro] produced a much cleaner, more realistic image with superior textures and logical anatomy, but it missed the specific prompt requirement for motion blur, resulting in a more static composition.

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.”

FLUX.2 [dev]
FLUX.2 [pro]
0% wins 0% ties 100% wins

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent rendering of the ornate engraved armor texture.
  • + Very realistic leather straps with visible wear and accurate buckle placement.
  • + Good adherence to the 'beads' prompt with natural-looking wooden beads.
  • The lighting on the face feels a bit flat compared to the dramatic background.
  • The scarring is a bit simplistic in texture.

FLUX.2 [pro]

  • + Superior skin texture with grit, dirt, and more realistic, deep scarring.
  • + Dynamic lighting with very strong warm reflections off the armor's surface.
  • + Better sense of depth and atmospheric bokeh sparks.
  • The beads in the hair look slightly more like modern plastic or colorful jewelry than weathered paladin beads.
  • The metal engraving is slightly less crisp than in Model A.

Verdict: Both models followed the prompt exceptionally well, but FLUX.2 [pro] wins out due to its superior skin texture and more dramatic use of torchlight, which creates a more lifelike and cinematic feel. FLUX.2 [dev] produced excellent armor and leather details, but the character's face felt slightly more 'cleanly' rendered despite the requested dirt and scars.

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.”

FLUX.2 [dev]
FLUX.2 [pro]

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent photographic quality and realistic food rendering.
  • + Consistent use of bold, vibrant accent colors across different sections.
  • + Good spacing and visual balance for a two-page spread layout.
  • Text is largely gibberish strings of characters.
  • Includes a typo in a header (PIZZAU) and redundant labeling.

FLUX.2 [pro]

  • + Text is much more legible and includes recognizable menu items.
  • + Features a clean, centered layout with consistent iconography.
  • + Strict adherence to the requested grid-based food photo section.
  • The 'Mains' category is misspelled as 'MINS'.
  • Prices are awkwardly formatted with strange comma placement (e.g., $,30).

Verdict: Both models followed the prompt well, but FLUX.2 [pro] is the superior choice because it produced readable text for the menu items, whereas FLUX.2 [dev] generated mostly illegible nonsense characters. While FLUX.2 [dev] had slightly more appetizing food photography, the professional utility of FLUX.2 [pro]'s clear typography and centered design makes it much more effective 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.”

FLUX.2 [dev]
FLUX.2 [pro]

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent typography with a vibrant, fiery glow effect on all text elements.
  • + High-quality, distinct rendering of the burger toppings with great color saturation.
  • + The starburst design perfectly captures the 'fiery' prompt requirement.
  • The meat patty looks slightly dry compared to a typical food advertisement.
  • The composition is quite vertical and standard.

FLUX.2 [pro]

  • + Highly dynamic composition with motion trails and swirling grease/sauce particles.
  • + The texture of the meat and melted cheese is extremely realistic and appetizing.
  • + Excellent use of lighting to create depth and volume within the burger stack.
  • The text 'MAGIC BURGER' is slightly less legible than in the other version.
  • The starburst element looks a bit more like a vector graphic compared to the photorealistic burger.

Verdict: FLUX.2 [dev] excels in typography and graphic design, delivering the clearest text and the best 'fiery' starburst. However, FLUX.2 [pro] produces a more appetizing burger and a much stronger sense of motion and 'magic' through its dynamic composition and superior food textures. FLUX.2 [pro] is the likely winner for its professional food photography quality and adherence to the 'motion' aspect of the prompt.

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.”

FLUX.2 [dev]
FLUX.2 [pro]

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent chalk texture with hyper-realistic smudging and dust remnants
  • + Precise text rendering with zero spelling errors
  • + Strong framing that fills the board effectively
  • The handwriting style is a bit inconsistent across different lines
  • The 'with lemon' and '$28' spacing is slightly awkward

FLUX.2 [pro]

  • + Beautiful, consistent cursive handwriting that feels very authentic to a café aesthetic
  • + Better composition relative to the surrounding wall and background bokeh
  • + Perfectly followed the instruction for elegant cursive title
  • The 'S' in 'Specials' is slightly malformed
  • Minor spacing issues on the 'Brown Butter' line

Verdict: Both models performed exceptionally well on complex text rendering, but FLUX.2 [pro] is the winner for its more cohesive and aesthetically pleasing cursive handwriting style. While FLUX.2 [dev] had more realistic chalk texture and smudges, FLUX.2 [pro] better captured the 'elegant cursive' requirement and felt more like a professional café menu board.

Pose & Character Mashup

Editing
Edit instruction

“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.”

Source
FLUX.2 [dev]
FLUX.2 [pro]

AI Judge Analysis

FLUX.2 [dev]

  • + Successfully carries over the head and accessories from the character reference image.
  • Severely fails anatomically, leaving the original female head floating near the shoulder.
  • The body position is distorted and does not resemble a human form.

FLUX.2 [pro]

  • + Successfully recreates the character's clothing, face, and accessories in a high-quality render.
  • + Produces a coherent human anatomy that attempts to follow the spirit of the dynamic pose.
  • Fails to match the exact leg and torso position of Image 1, opting for a squat instead of the standing/leaning cross-legged pose.
  • The character is now wearing shoes/socks or has strangely textured feet compared to the barefoot reference.

Verdict: FLUX.2 [dev] suffered a catastrophic failure in anatomy, merging the two characters into one multi-headed entity. FLUX.2 [pro] successfully translated the character and clothing into the new environment with high visual fidelity, and although it modified the leg position from the source pose, it is vastly superior to the distorted output of the dev model.

The Reversed Rodeo

Text-to-Image

“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”

FLUX.2 [dev]
FLUX.2 [pro]

AI Judge Analysis

FLUX.2 [dev]

  • + High resolution and realistic textures on the spacesuit and horse fur.
  • + Cinematic lighting with a strong sense of scale over the planet.
  • Completely failed the negative constraint/spatial instruction of 'horse on top'.
  • Shows a generic astronaut riding a horse which is a very common AI trope.

FLUX.2 [pro]

  • + Followed the difficult spatial prompt of placing the 'horse on top' of the astronaut.
  • + Excellent surreal composition with beautiful nebula effects.
  • + High level of detail on the astronaut's life support systems.
  • Anatomical issues where the horse's legs merge oddly with the astronaut's body.
  • The 'horse on top' is actually a horse standing on another horse-like structure emerging from the astronaut.

Verdict: FLUX.2 [dev] ignored the specific instruction to have the horse on top, providing a standard 'astronaut riding horse' image. FLUX.2 [pro] followed the surreal spatial requirement much more effectively, creating a unique and visually striking composition that adhered to the prompt's logical twist.

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.”

FLUX.2 [dev]
FLUX.2 [pro]

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent front-on perspective emphasizing the capybara's expression.
  • + The businesswoman's 'bored' expression is perfectly captured and positioned clearly.
  • + Strong color contrast and high-resolution texture on the fur.
  • The paws look a bit human-like and awkward on the steering wheel.
  • The exterior environment through the windows is less detailed than in its counterpart.

FLUX.2 [pro]

  • + Superior interior detail, including the dashboard, meter, and gear shift.
  • + Cinematic lighting and realistic rain/bokeh effects on the windshield.
  • + The capybara's anatomy and paws on the wheel look very natural in the profil view.
  • The businesswoman looks somewhat distant and less integrated into the 'taxi ride' narrative than in model A.

Verdict: Both models followed the prompt exceptionally well, but FLUX.2 [pro] (Image B) is the winner due to its superior environmental storytelling and richer interior details. While FLUX.2 [dev] (Image A) hit the character expressions perfectly, Image B felt more like a complete, high-quality film still with more realistic lighting and complex 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.”

FLUX.2 [dev]
FLUX.2 [pro]

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent typography with a cohesive gothic font choice
  • + Very clean and intentional border design using thorns and webs
  • + Balanced layout with clear hierarchy of information
  • The dark jack-o-lantern blends slightly too much into the background
  • The scroll banner looks slightly flat compared to the rest of the image

FLUX.2 [pro]

  • + Dynamic cinematic lighting with a glowing pumpkin and moon
  • + Greater depth of field with misty ground and atmospheric background
  • + Higher level of texture on the parchment and scroll banner
  • Layout is slightly more cluttered with elements overlapping
  • The border is thinner and less defined than requested

Verdict: Both models followed the complex text and layout instructions perfectly. FLUX.2 [dev] produced a more balanced and graphic invitation with superior font consistency, while FLUX.2 [pro] offered more photographic depth and atmospheric lighting. FLUX.2 [dev] is slightly preferred for this specific task because the layout feels more like a finished, professional invitation.

Bald man challenge

Image Editing
Edit instruction

“Give the person a full, thick head of natural hair with realistic texture, density, and a natural hairline. Preserve facial features and lighting.”

Before After
FLUX.2 [dev]
Before After
FLUX.2 [pro]

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent preservation of the original face, beard, and eyewear
  • + Extremely convincing blend between the new hair and the existing beard texture
  • + High degree of realism in individual hair strands and volume
  • The choice of an afro-style texture may be seen as a specific interpretation rather than a generic head of hair
  • The hairline is slightly obscured by the volume

FLUX.2 [pro]

  • + Good preservation of the background and clothing
  • + The hair style feels like a natural extension of the person's likely younger appearance
  • Slightly alters the facial structure, making the man look slightly younger/different
  • Noticeable artifacts where the hair meets the forehead, appearing less integrated than Model A
  • The beard texture was slightly smoothed compared to the original

Verdict: FLUX.2 [dev] performed a superior edit by perfectly preserving the original facial features while seamlessly integrating a high-density hair texture that matches the beard perfectly. FLUX.2 [pro] also succeeded in the task but slightly altered the man's face and had a less realistic transition at the hairline.

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.”

FLUX.2 [dev]
FLUX.2 [pro]

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent PBR textures showing realistic translucency in the fish
  • + Accurate rendering of rice grains
  • + Perfectly followed text layout with large 'JAPAN' and smaller 'SUSHI'
  • Lighting is a bit soft, causing the white text to blend slightly into the background

FLUX.2 [pro]

  • + Strong 'cartoon' aesthetic with bold, stylized geometry
  • + Large, highly legible white text
  • + Clean isometric representation of the diorama base
  • Sushi rice appears more like a bumpy pattern than individual grains
  • The 'JAPAN' and 'SUSHI' text are nearly the same size, ignoring the hierarchy requested

Verdict: FLUX.2 [dev] follows the prompt instructions more closely, particularly in the text hierarchy and the 'realistic PBR' quality of the textures. While FLUX.2 [pro] captures the cartoon aesthetic well, its rice texture is less convincing and it missed the specific font scaling requested.

Over-the-top cartoon caricature

Editing
Edit instruction

“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.”

Source
FLUX.2 [dev]
FLUX.2 [pro]

AI Judge Analysis

FLUX.2 [dev]

  • + Successfully maintains a high level of facial resemblance to the source image within the caricature style.
  • + Includes clever details like dogs wearing hockey jerseys and a camera crew.
  • + Creative integration of a hockey rink as the studio background.
  • The text on the anchor desk is garbled and nonsensical.
  • The additional human character in the background is not explicitly requested and looks a bit cluttered.

FLUX.2 [pro]

  • + Clean and vibrant illustration style that feels professional.
  • + Very symmetrical and balanced composition.
  • + Includes fun details like dogs sitting in office chairs and holding hockey sticks.
  • Loses significant facial resemblance to the source image, looking more like a generic cartoon character.
  • The hands are slightly distorted with inconsistent finger counts.

Verdict: FLUX.2 [dev] is the clear winner for this editing task because it successfully translates the specific facial features of the source image into a caricature, whereas FLUX.2 [pro] generates a generic character that looks nothing like the user. FLUX.2 [dev] also does a better job of blending all three requested elements—TV anchor, dogs, and hockey—into a single, cohesive scene that feels more personalized.

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.”

FLUX.2 [dev]
FLUX.2 [pro]

AI Judge Analysis

FLUX.2 [dev]

  • + Includes all four requested animals (dog, cat, fox, and two bunnies).
  • + Excellent use of backlight and 'god rays' through the fur.
  • + Very high level of realism in the fur texture and meadow details.
  • The animals are mostly sitting still rather than 'playfully chasing' and 'tumbling' as requested.
  • The bunny looks a bit static and duplicated in the foreground.

FLUX.2 [pro]

  • + Captures the 'playfully chasing' and 'tumbling' action much more dynamically.
  • + Superior composition with more expressive, 'big' eyes as requested.
  • + The lighting and dew sparkles are beautifully rendered.
  • Failed to include the baby bunny requested in the prompt.
  • The anatomy of the puppy's raised paw is slightly distorted.

Verdict: FLUX.2 [dev] followed the technical requirements of the prompt better by including all four animal types, whereas FLUX.2 [pro] missed the bunny entirely. However, FLUX.2 [pro] much more effectively captured the 'playful' and 'tumbling' energy of the scene, resulting in a more charming and expressive image despite the missing subject.

Studio Ghibli Anime Style

Editing
Edit instruction

“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”

Source
FLUX.2 [dev]
FLUX.2 [pro]

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent soft lighting and pastel color palette.
  • + Beautiful dreamy floral background effectively adds to the theme.
  • + Great preservation of the characters' expressions and poses.
  • The background departs significantly from the original street scene.
  • The character design leans slightly more towards modern anime than classic Ghibli.

FLUX.2 [pro]

  • + Superb preservation of the original street composition and background elements.
  • + Authentic Studio Ghibli art style with watercolor-like textures and character line work.
  • + Stronger adherence to the 'hand-painted' texture request.
  • The man's expression is slightly more neutral/curious than the 'checking out' expression in the original.

Verdict: Both models performed exceptionally well in translating the famous meme into an illustration. FLUX.2 [dev] created a more visually poetic and 'dreamy' image by replacing the city with flowers, but FLUX.2 [pro] is the superior edit as it successfully transformed the entire scene while preserving the setting, including the background bus and street architecture, in a style that perfectly mimics a Ghibli background painting.

Golden Hour Stroll

Image Editing
Edit instruction

“Add dynamic motion to this photo: make hair blow in the wind, add leaves flying, energetic and lively feel.”

Before After
FLUX.2 [dev]
Before After
FLUX.2 [pro]

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent hair motion that blends naturally with the original portrait.
  • + Subtle and realistic addition of flying leaves that fit the background scale.
  • + Maintains perfect structural integrity of the woman and the dog.
  • The 'lively and energetic' feel is a bit more restrained compared to Model B.

FLUX.2 [pro]

  • + Successfully adds motion to more elements, including the denim jacket flaring out.
  • + Dynamic leaf placement with depth of field, creating a strong sense of wind.
  • + Maintains high fidelity to the original subject's face and the dog.
  • Some foreground leaves are slightly distracting and can obscure the composition.
  • A few leaves have minor artifacts or look pasted on compared to the background elements.

Verdict: Both models did an exceptional job at preserving the source image while adding the requested motion. FLUX.2 [dev] provides a more subtle and grounded edit, whereas FLUX.2 [pro] captures a much more 'energetic' feel by adding movement to the clothing as well as the hair and using larger, more dynamic leaves.

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.”

FLUX.2 [dev]
FLUX.2 [pro]

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent typography integrated into a classic banner
  • + Strong vector emblem aesthetic with high contrast
  • + Perfect adherence to the requested color tones and textures
  • The cloche steam is a bit small and simplistic

FLUX.2 [pro]

  • + Elegant circular composition that feels more like a complete brand mark
  • + Superior rendering of the steam and shading on the cloche
  • + Very clean, professional typography with classical serif styling
  • The 'Est. 1720' text is slightly less prominent than the banner style in Model A

Verdict: Both models performed exceptionally well, capturing the vintage aesthetic and correctly rendering the specific text. FLUX.2 [dev] provides a punchier, more traditional banner-style emblem, while FLUX.2 [pro] offers a more sophisticated, balanced circular logo that feels like a premium restaurant brand.

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.”

FLUX.2 [dev]
FLUX.2 [pro]

AI Judge Analysis

FLUX.2 [dev]

  • + Includes all six individual stages as distinct icons.
  • + Cleverly includes the names of the Apollo 11 crew correctly.
  • + Matches the requested navy, white, and red color palette perfectly.
  • The layout is cluttered and non-linear, making the mission steps hard to follow.
  • Several text labels are garbled or contain typos (e.g., 'Trarquility', 'UALSIST ORDIT').
  • Included redundant launch icons that break the requested numbered step sequence.

FLUX.2 [pro]

  • + Higher quality text rendering for the main headers and location pin.
  • + Better infographic flow with connected path lines between steps.
  • + More consistent vector style that feels like a professional poster.
  • Combines descent and landing into a vertical flow, missing the explicit 'Landing' text for the final step.
  • The 'Earth Orbit' and 'Translunar' icons are visually similar and slightly repetitive.
  • The placeholder body text under headers is gibberish.

Verdict: FLUX.2 [pro] is the superior model here because it correctly interprets the layout of an 'infographic poster' with a logical flow, whereas FLUX.2 [dev] produces a disorganized grid of icons with several illiterate text errors. FLUX.2 [pro] also maintains a more consistent flat-vector aesthetic that adheres better to the modern professional design style requested.

Next steps

Explore each model