Head to head
Esc

Models · slot A

to navigate to pick

FLUX.2 [dev] Turbo fal 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] Turbo

27.9 arena score

#3 of 62 in Text-to-Image

Top 3 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] Turbo

42.9%

win rate

Ties

14.3%

FLUX.2 [pro]

42.9%

win rate

42.9% 14.3% ties 42.9%
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] Turbo
FLUX.2 [pro]

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent glass physics, featuring realistic dust/scratches and light refraction.
  • + The plant is clearly visible through the glass as requested, interacting logically with the refractive edges.
  • + Very high level of photorealism in the wood grain and book texture.
  • The sphere has a slight blue reflection on the floor of the cube that is a bit intense.
  • The composition feels slightly crowded compared to the cleaner look of the other image.

FLUX.2 [pro]

  • + Clean, minimalist aesthetic with very sharp edges on the glass cube.
  • + Excellent lighting that feels soft and diffuse, consistent with window light.
  • + Perfectly centered sphere and well-balanced composition.
  • The plant is heavily blurred and almost disappears behind the cube, failing the 'partially visible through glass' prompt detail compared to Model A.
  • The glass lacks the subtle imperfections that make Model A look like a real photograph.

Verdict: Both models followed the complex spatial instructions perfectly. FLUX.2 [dev] Turbo created a more convincing, lived-in photograph with realistic glass refractions and a better rendering of the plant through the glass, whereas FLUX.2 [pro] produced a cleaner, more commercial-style render but sacrificed the visibility of the plant through the glass.

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] Turbo
FLUX.2 [pro]

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent preservation of the man's identity, including his hairstyle, plaid coat, and scarf.
  • + High-quality rendering of the car's interior details and woodwork.
  • + Dynamic composition with a great sense of motion and scenic California background.
  • The car color appears slightly more beige/silver than the original white.
  • The driver is positioned on the wrong side of the car for a standard US-market vehicle (right-hand drive).

FLUX.2 [pro]

  • + Perfectly maintains the exterior color and design of the original Rolls Royce.
  • + Successfully places the car and driver in the requested coastal environment with motion blur.
  • + Correctly places the driver on the left side of the vehicle.
  • Significant loss of detail on the man's face and clothing due to scale and distance.
  • The man's hair appears slightly simplified compared to the source image.

Verdict: Both models performed remarkably well at this complex multi-image editing task. FLUX.2 [dev] Turbo excels at preserving the fine details of the man's clothing and likeness, creating a more intimate and high-quality portrait, though it defaults to a right-hand drive configuration. FLUX.2 [pro] is better at maintaining the car's exact exterior appearance and correct driving position, but loses the character detail provided in the source image due to the wide shot.

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

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent depiction of motion blur from passing cars
  • + Strong adherence to the 'imperfect framing' prompt with a centered, slightly cluttered composition
  • + Authentic rain textures including visible drops and wet asphalt reflections
  • The rear tire of the bicycle is clipping through the ground in the reflection area
  • The bicycle geometry is slightly warped near the handlebars

FLUX.2 [pro]

  • + Incredible skin texture and facial detail for the subject
  • + Very realistic bicycle mechanics and physical interaction with the wheel
  • + Masterful use of shallow depth of field and bokeh in the background
  • Lacks the requested 'motion blur from passing cars'
  • The framing feels a bit too 'perfectly' staged despite the request for imperfect framing

Verdict: Both models followed the prompt well, but FLUX.2 [dev] Turbo captured the specific 'candid' atmosphere and 'motion blur' requested more effectively. However, FLUX.2 [pro] produced a much higher quality image in terms of human anatomy, skin texture, and realistic bicycle mechanics, making it the more visually impressive result despite missing the motion blur detail.

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

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Sharp focus and excellent resolution on facial features and armor textures.
  • + Highly detailed engraving on the plate armor with a more realistic metallic sheen.
  • + Accurate interpretation of leather straps and buckles with visible stitching and textures.
  • The beads in the hair look slightly more like plastic modern crafts compared to the overall gritty aesthetic.

FLUX.2 [pro]

  • + Strong atmospheric lighting with warm torchlight highlights on the character's face.
  • + Dynamic composition with a slightly angled perspective that adds to the battle-worn feel.
  • + Good integration of scars and dirt, looking naturally seated on the skin.
  • The textures on the armor and leather straps are softer and less detailed than Image A.
  • The bokeh sparks are somewhat smeary and less defined.

Verdict: While both models perform exceptionally well, FLUX.2 [dev] Turbo produces a superior level of technical detail, particularly in the intricate engravings of the armor and the texture of the leather. FLUX.2 [pro] has slightly better atmospheric lighting, but loses out on the sharpness and tactile realism requested in the prompt for the leather and metal surfaces.

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

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent adherence to the grid layout with clean, professional alignment.
  • + Very high-quality food photography that fits a modern culinary aesthetic.
  • + Superior rendering of legible text for item names and pricing.
  • Logical inconsistency in pricing (e.g., $260 for a pizza).
  • Food photos under 'Appetizers' primarily show pizzas.

FLUX.2 [pro]

  • + Features more logical pricing for a casual dining establishment.
  • + Includes helpful icons alongside section headers.
  • + Good use of vibrant color accents to differentiate sections.
  • Text rendering is messy with typos like 'MINS' instead of 'Mains'.
  • Repeats the same menu items (Margherita Pizza) multiple times in several sections.
  • The layout feels slightly more cramped and less professional than the competitor.

Verdict: FLUX.2 [dev] Turbo produced a much more professional and visually appealing layout that looks like a real minimalist menu, despite some nonsensical high prices. FLUX.2 [pro] struggled with text accuracy, repeating the same dishes across every category and misspelling the section headers.

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] Turbo
FLUX.2 [pro]

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent text integration with a consistent fiery texture across all three elements.
  • + The burger components are beautifully separated, and the sauce droplets add a great sense of motion.
  • + Photorealistic textures on the beef patty and lettuce are highly detailed.
  • The starburst shape is slightly irregular compared to a standard graphic icon.

FLUX.2 [pro]

  • + Dynamic composition with swirling particles and steam around the burger.
  • + Clean, professional starburst graphic for the price tag.
  • + The lighting on the cheese and buns is very appetizing and soft.
  • The price text is missing the requested fiery/glowing effect, appearing as flat yellow text.
  • The secondary text 'LIMITED TIME ONLY' lacks the fire effect seen in the primary title.

Verdict: Both models followed the prompt well, but FLUX.2 [dev] Turbo provided more consistent adherence to the text styling requirements by applying the fiery glow to all requested text elements. FLUX.2 [pro] has a slightly more polished graphic design for the starburst but failed to apply the fire effect to the pricing and secondary message.

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] Turbo
FLUX.2 [pro]

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent chalk texture with realistic smudges and dust on the board.
  • + Strong adherence to the requested text and pricing.
  • + Very natural variation in letter sizes and line spacing.
  • The layout for the octopus item is a bit messy with the trailing dash.
  • Includes a redundant '- 9' in the cookie item.

FLUX.2 [pro]

  • + Clean, elegant cursive handwriting as requested in the prompt.
  • + Better composition with centered text on a distinct slate-style board.
  • + More accurate completion of the truncated 'Brown But...' prompt instruction.
  • Slightly less 'chalky' texture compared to Model A, appearing more like a chalk marker.
  • Minor spacing issues between some letters.

Verdict: FLUX.2 [dev] Turbo captures the messy, authentic texture of a real chalkboard with impressive realism, while FLUX.2 [pro] delivers a more polished, aesthetically pleasing layout with superior cursive legibility. FLUX.2 [pro] is the winner for its better composition and for more logically finishing the truncated prompt item with correct pricing and formatting.

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] Turbo
FLUX.2 [pro]

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Successfully captures the clothing details from Image 2 including the patterned scarf.
  • Has terrifying logical failures, depicting two heads (one from each image) in a surreal manner.
  • Completely fails the pose instruction, creating a nonsensical floating body and mangled limbs.

FLUX.2 [pro]

  • + Successfully recreates the character's facial features, sunglasses, and clothing details from Image 2.
  • + Matches the environment and lighting of Image 1 perfectly.
  • + Anatomy is coherent and follows the basic crouched/dynamic intention of the pose.
  • Does not perfectly replicate the exact leg crossing pose from Image 1, though it is much closer than the competitor.

Verdict: FLUX.2 [pro] followed the instructions effectively, creating a realistic recreation of the man from Image 2 in the environment of Image 1 with coherent anatomy. FLUX.2 [dev] Turbo failed significantly by generating a surreal image with two different heads and disjointed limbs, completely ignoring the 'recreate the character' and 'perfect anatomy' instructions.

The Reversed Rodeo

Text-to-Image

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

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

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent cinematic lighting and texture on the spacesuit
  • + Clear and detailed depiction of Earth and distant celestial bodies
  • + Great anatomical rendering of the horse's fur and motion
  • Completely failed the negative constraint of having the horse on top
  • Depicts a standard 'astronaut riding horse' scene which is a common AI trope

FLUX.2 [pro]

  • + Successfully interpreted the surreal prompt requirement of the horse being on top
  • + Vibrant and interesting background with multiple spiral galaxies
  • + High level of detail in the astronaut's visor reflections
  • The transition between the horse and the astronaut's back is physically nonsensical even for surrealism
  • The second horse torso appearing behind the astronaut is confusing and creates a cluttered mid-ground

Verdict: FLUX.2 [dev] Turbo produced a higher quality image in terms of realism and cinematic composition, but it failed the primary conceptual challenge of the prompt. FLUX.2 [pro] followed the specific instruction to place the horse on top of the astronaut, making it the winner for prompt adherence despite some anatomical clipping issues.

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] Turbo
FLUX.2 [pro]

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent front-facing composition that clearly shows the capybara's expression and paws on the wheel.
  • + Very high levels of detail on the capybara's fur and the businesswoman's face.
  • + Accurate text rendering on the taxi roof light.
  • The businesswoman is sitting in the front passenger seat instead of the requested back seat.
  • The paws have a slightly unnatural, almost human-like finger structure.

FLUX.2 [pro]

  • + Perfectly adheres to the spatial prompt by placing the businesswoman in the back seat.
  • + Realistic leather jacket texture and side-profile lighting.
  • + Captures the 'bored' expression of the passenger very effectively within the background blur.
  • The side view makes it harder to see the capybara's expression compared to the other model.
  • The lighting on the capybara's face is a bit flat.

Verdict: FLUX.2 [dev] Turbo produces a more striking image with better facial details and textures, but it fails the spatial requirement of placing the passenger in the back seat. FLUX.2 [pro] followed the prompt instructions more accurately regarding the seating arrangement, making the scene feel more like a genuine taxi ride. FLUX.2 [pro] is the winner for its superior prompt adherence despite the slightly less detailed fur texture.

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] Turbo
FLUX.2 [pro]

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent typography style that fits the gothic theme perfectly.
  • + The thorn and web border is more intricate and visually impactful.
  • + Consistent illustrative style across all elements including the background trees.
  • The parchment texture is slightly less realistic compared to Model B.
  • The lighting on the pumpkin is a bit flat.

FLUX.2 [pro]

  • + Highly realistic lighting and atmospheric effects with fog and moonlight.
  • + The central jack-o-lantern has more depth and a realistic glow.
  • + Text is sharp and very easy to read against the dark background.
  • The 'scroll' banner looks a bit like a modern digital asset pasted on.
  • The border thorns are thinner and less 'vintage' in feel than requested.

Verdict: FLUX.2 [dev] Turbo produced a more cohesive vintage illustration that feels like a physical poster, especially with its heavy thorn border and stylized typography. However, FLUX.2 [pro] wins on technical visual quality, offering cinematic lighting, realistic textures, and a more frighteningly illuminated jack-o-lantern that creates a superior spooky atmosphere.

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] Turbo
Before After
FLUX.2 [pro]

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent preservation of original identity and facial features
  • + Perfectly maintains original lighting and skin texture
  • + Seamless transition between the new hair and existing sideburns/beard
  • The 'afro' style chosen might not be what every user considers 'natural' hair for this specific character's phenotype

FLUX.2 [pro]

  • + Natural, realistic hair texture and messy wind-blown styling
  • + Follows the instruction for a full, thick head of hair with a varied hairline
  • Alters the facial features, making the eyes smaller and changing the bone structure
  • Noticeable color shift in the beard compared to the source image
  • Distorts the frames of the glasses significantly

Verdict: FLUX.2 [dev] Turbo succeeded much better as an editing model by perfectly preserving the man's identity, glasses, and the underlying image while adding a voluminous hairstyle. FLUX.2 [pro] produced a realistic hair texture but failed the edit by altering the man's face and distorting his glasses, making it look like a new generation rather than an edit.

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] Turbo
FLUX.2 [pro]

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent PBR material rendering with realistic rice and fish textures
  • + Clean and readable typography with correct flag placement
  • + Perfect balance of realistic details within a miniature aesthetic
  • The sushi looks a bit more realistic than the 'cartoon' style requested

FLUX.2 [pro]

  • + Stronger adherence to the '3D cartoon' style with simplified shapes
  • + Clean, bold white typography that pops against the background
  • + Good variety of sushi types presented on the plate
  • The rice texture is slightly repetitive and less realistic than the other model
  • The diorama base is very plain compared to the wood grain in model A

Verdict: Both models followed the prompt exceptionally well, including the specific text and flag requirements. FLUX.2 [dev] Turbo is preferred for its superior material quality and realistic textures that make the miniature feel more premium, whereas FLUX.2 [pro] captures the '3D cartoon' aesthetic slightly better but lacks the same level of tactile detail.

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] Turbo
FLUX.2 [pro]

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent preservation of the subject's facial features and likeness within the caricature style.
  • + Perfectly integrates all requested themes including the hockey arena background and numerous dogs.
  • + Dynamic composition with a complex, detailed background that feels like a professional illustration.
  • The text on the anchor desk is gibberish.
  • The hands are slightly disproportionate, although somewhat expected in the caricature style.

FLUX.2 [pro]

  • + Clean, vibrant vector-like illustration style with high visual clarity.
  • + Creative use of dogs as co-anchors sitting in chairs.
  • Loses the specific facial likeness of the source image, looking more like a generic avatar.
  • The background is less immersive compared to the full arena scene in the other model.

Verdict: FLUX.2 [dev] Turbo is the clear winner because it successfully maintained the subject's specific facial features and likeness while translating them into a caricature. While FLUX.2 [pro] produced a clean illustration, it failed to capture the 'me' part of the prompt, resulting in a generic character that does not resemble the source image.

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] Turbo
FLUX.2 [pro]

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Includes all four requested animals: golden retriever, tabby kitten, bunny, and fox kit.
  • + Excellent composition with animals interacting in a cohesive group.
  • + Captures the 'dew sparkles' very well with floating droplets throughout the scene.
  • The kitten's facial expression is slightly unsettling and less realistic than the others.
  • The lighting, while warm, lacks the distinct 'god rays' requested in the prompt.

FLUX.2 [pro]

  • + Beautiful golden lighting with clear god rays filtering through the background tree.
  • + Highly expressive and anatomically charming faces on the puppy and fox.
  • + Excellent fur texture and sharp detail on the animals' features.
  • Failed to include the requested baby bunny animal.
  • The puppy's raised paw has an unusual number of pads/toes.

Verdict: FLUX.2 [dev] Turbo followed the prompt more accurately by including all four animals, whereas FLUX.2 [pro] missed the baby bunny. However, FLUX.2 [pro] produced a much more atmospheric image with superior lighting and 'god rays' that better captured the requested aesthetic. FLUX.2 [dev] Turbo is the winner for prompt adherence, while FLUX.2 [pro] is more visually stunning 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] Turbo
FLUX.2 [pro]

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent hand-painted texture with visible line-art and watercolor bleeding.
  • + Captures the dreamy aesthetic with soft cherry blossoms and floral accents.
  • + Preserves the characters' expressions and the specific plaid pattern of the shirt very well.
  • The background is heavily altered from an urban street to a nature-filled path.

FLUX.2 [pro]

  • + Better preservation of the original urban background architecture while applying the style.
  • + Cleaner character line art that closely mimics modern digital Ghibli works.
  • + Maintains the warm, nostalgic color palette effectively.
  • The character in the plaid shirt has a more generic face that loses the likeness of the original man.
  • The red dress lacks the textured shading seen in Model A.

Verdict: Both models do an exceptional job of translating the 'Distracted Boyfriend' meme into the Studio Ghibli style. FLUX.2 [dev] Turbo provides a more traditional, hand-painted watercolor look with beautiful floral details, whereas FLUX.2 [pro] maintains the architectural integrity of the original urban setting with a cleaner, more modern animation style. FLUX.2 [dev] Turbo is the likely winner for better capturing the 'hand-painted textures' and character nuances requested in the prompt.

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] Turbo
Before After
FLUX.2 [pro]

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent preservation of the original image's composition and subjects
  • + Adds a significant amount of leaves to create a dense motion effect
  • The hair edit looks a bit stiff and symmetrical
  • Several small leaves appear as artifacts directly on the woman's face and clothes

FLUX.2 [pro]

  • + Natural-looking hair motion that follows a clear direction
  • + Added wind effect to the denim jacket, enhancing the sense of movement
  • + Leaves have better depth with varied sizes and foreground blurring
  • Fewer leaves across the entire scene compared to the other model

Verdict: Both models did an excellent job of preserving the source image while adding the requested elements. FLUX.2 [pro] is the winner because it went the extra mile by adding movement to the woman's jacket as well as her hair, and the leaves are rendered with a more professional sense of depth and motion blur. FLUX.2 [dev] Turbo added more leaves but suffered from small artifacts on the subject's skin.

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] Turbo
FLUX.2 [pro]
50% wins 0% ties 50% wins

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Perfect adherence to typography including the grave accent on 'Caffè'.
  • + Excellent vintage texture and banner design.
  • + Strong vector emblem composition with balanced hierarchy.
  • The steam lines are a bit thin compared to the bold weight of the logo.

FLUX.2 [pro]

  • + Clean, modern-meets-vintage vector aesthetic.
  • + Effective use of shading and negative space on the cloche.
  • The 'Est. 1720' banner is very small and lacks visual impact.
  • The overall composition feels a bit fragmented with the split circle.

Verdict: Both models followed the prompt instructions accurately, but FLUX.2 [dev] Turbo produced a more cohesive and professional-looking logo. FLUX.2 [dev] Turbo's use of a large, detailed banner for the date and the bold, correctly accented typography makes it look like a finished brand identity, whereas FLUX.2 [pro] has some scale issues with its banner and text placement.

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] Turbo
FLUX.2 [pro]
50% wins 50% ties 0% wins

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent typography and accurate, legible text for the mission steps.
  • + High-detail illustrations of the Saturn V and Lunar Module.
  • + Includes accurate names and silhouettes for the three astronauts.
  • The layout is a bit cluttered and redundant, repeating the Earth icon and Translunar label.
  • Icons for the Earth and Moon are more detailed/realistic than 'flat vector style' requested.

FLUX.2 [pro]

  • + Superior infographic structure with clear, linear steps and horizontal dividers.
  • + Perfectly adheres to the requested 'flat-vector style' with crisp lines and consistent iconography.
  • + Excellent use of the specified NASA-inspired color palette.
  • The placeholder body text under the headings is gibberish.
  • Missed the final 'Landing' step label, though the imagery is present.

Verdict: FLUX.2 [pro] followed the stylistic instructions much better, producing a clean, modern vector aesthetic with a logical linear flow suitable for an infographic. While FLUX.2 [dev] Turbo had better text accuracy and more detailed icons, its layout was messy and it failed the 'flat-vector' style requirement compared to the professional design produced by the pro model.

Next steps

Explore each model