Head to head
Esc

Models · slot A

to navigate to pick

FLUX.2 [dev] Black Forest Labs FLUX.2 [dev] Turbo fal

Settled by community votes across 20 shared challenges, with an AI judge weighing in on each.

FLUX.2 [dev]

24.5 arena score

#18 of 62 in Text-to-Image

Skill signature · Text-to-Image

FLUX.2 [dev] Turbo

27.8 arena score

#4 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.2 [dev]

50.0%

win rate

Ties

0.0%

FLUX.2 [dev] Turbo

50.0%

win rate

50.0% 0.0% ties 50.0%
Shared challenges 20

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 [dev] Turbo

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent soft lighting consistent with the prompt
  • + Clean, minimalist aesthetic
  • + Correct placement of all objects
  • The sphere appears to be levitating inside the cube rather than resting on the bottom
  • Glass cube has slightly rounded edges that look more like a container than a geometric cube

FLUX.2 [dev] Turbo

  • + Highly realistic textures on the book and wooden table
  • + Accurate glass refraction and dust details on the cube surface
  • + Natural shadow and grounding for the blue sphere
  • The blue sphere looks slightly more like a marble than a simple sphere
  • The plant is slightly more obscured compared to Model A

Verdict: Both models followed the complex spatial prompt perfectly. FLUX.2 [dev] Turbo is the winner because of its superior texture work and realistic physics; specifically, the sphere sits naturally on the surface, whereas in FLUX.2 [dev] it appears to float. FLUX.2 [dev] Turbo also captured finer details like the wood grain and the embossed text on the book spine.

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 [dev] Turbo

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent preservation of the man's hair, scarf, and plaid coat pattern.
  • + Successfully merges the specific car's interior with a high-quality California coastline background.
  • + Realistic motion blur on the road that adds to the sense of driving.
  • The man's facial features are slightly altered to look more generic compared to the source image.
  • The dashboard layout is somewhat cluttered with redundant circular gauges.

FLUX.2 [dev] Turbo

  • + Perfectly captures the likeness and smile of the man from the source image.
  • + Great composition that shows both the driver, the car's luxury interior, and the coastal highway clearly.
  • + Accurately recreates the car's specific wood-grain dashboard and steering wheel logo.
  • The man's right hand position on the steering wheel looks slightly cramped.
  • The hair bun is a bit more vertically stretched than the source image.

Verdict: Both models performed exceptionally well, successfully placing the specific man and car from the source images into the requested scene. FLUX.2 [dev] Turbo (Model B) is the winner because it better preserved the man's facial identity and joyful expression, whereas FLUX.2 [dev] (Model A) made him look more stoic and slightly altered his features.

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 [dev] Turbo
100% wins 0% ties 0% wins

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent motion blur on the passing cars communicating speed.
  • + Highly realistic skin texture and facial lighting.
  • + Natural, high-quality depth of field rendering.
  • The anatomy of the man's lower body and how he is interacting with the bike is physically confused.
  • The bicycle frame geometry is somewhat abstract and nonsensical in the center.

FLUX.2 [dev] Turbo

  • + More coherent interaction between the man and the bicycle.
  • + Great attention to detail with the tools and reflections on the pavement.
  • + Captures the 'imperfect framing' request effectively by placing the subject slightly off-center.
  • The motion blur on the cars is much less pronounced, feeling more like a fast shutter speed than a 50mm candid.
  • The front wheel of the bicycle is clipping through the ground/pavement.

Verdict: Both models followed the prompt exceptionally well, capturing the atmosphere of a rainy Japanese street. FLUX.2 [dev] produced a more cinematically beautiful image with superior skin rendering and motion blur, but it failed on the structural logic of the bicycle. FLUX.2 [dev] Turbo provided a more grounded composition with better object logic, though it suffered from a clipping artifact where the front tire meets the road.

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 [dev] Turbo
0% wins 0% ties 100% wins

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent warm lighting that authentically reflects off the plate armor.
  • + Complex hair braiding with highly detailed bead work.
  • + High contrast and rich textures on the leather and metal.
  • The scars look slightly painted on rather than recessed into the skin.
  • The bokeh sparks are a bit large and distracting compared to the subject.

FLUX.2 [dev] Turbo

  • + Incredible skin texture and realistic depth to facial scars.
  • + Highly detailed cloth and chainmail underlayers.
  • + The colorful beads add a nice touch of personality to the character design.
  • The lighting is a bit cooler and flatter than Model A despite the torch presence.
  • Symmetry of the armor engraving feels slightly less organic.

Verdict: Both models captured the prompt with high accuracy, but FLUX.2 [dev] Turbo produced a more lifelike facial texture and better integration of scars into the skin. While FLUX.2 [dev] had superior warm lighting and reflections, the overall detail in the underlayers and the character realism of the Turbo model make it the stronger portrait.

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 [dev] Turbo

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent photographic quality in the food grid
  • + Very clean professional layout reminiscent of a high-end menu
  • + Good adherence to the 'vibrant accents' request with color bars
  • Text rendering is largely gibberish/non-English characters
  • Repeated photos (multiple pizzas) under non-pizza sections

FLUX.2 [dev] Turbo

  • + Legible English text for section headers and menu items
  • + Clean, balanced grid layout that feels modern
  • + Accurate use of color blocking at the bottom
  • Lower resolution and clarity in the food images compared to the other model
  • The 'Mains' photo is still just a pizza, lacking variety

Verdict: FLUX.2 [dev] produces much higher quality food photography, but fails significantly on text legibility. FLUX.2 [dev] Turbo provides a more functional menu design with legible text and a cohesive layout, even though the image assets are slightly less sharp. FLUX.2 [dev] Turbo is the winner for better overall utility in a design-focused prompt where readable text is crucial.

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 [dev] Turbo

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent typography with a clean, professional neon glow effect.
  • + Very high-quality texture on the burger patty and lettuce.
  • + Strong composition with well-defined layers and droplets of sauce.
  • The bun is a bit plain without sesame seeds.
  • The starburst shape is slightly irregular and jagged.

FLUX.2 [dev] Turbo

  • + Dynamic 'deconstructed' feel with swirling sauce trails for motion.
  • + Excellent inclusion of sesame seeds on the bun for added realism.
  • + Text integrated well with the fiery atmosphere of the background.
  • The cheese layers appear somewhat repetitive or thin.
  • The starburst outline is a bit thin and less impactful than the other graphic elements.

Verdict: Both models performed exceptionally well, following every instruction in the prompt including the complex text rendering and starburst. FLUX.2 [dev] is preferred for its cleaner typography and more appetizing ingredient textures, although FLUX.2 [dev] Turbo captured the 'sense of motion' slightly better with the swirling sauce.

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 [dev] Turbo

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent chalk texture throughout the board
  • + Superior handwriting clarity and legibility despite natural variations
  • + Perfectly followed the cut-off prompt to imagine the full 'Brown Butter' item
  • Has a slight visual glitch/smudge next to the word 'with' on the second item

FLUX.2 [dev] Turbo

  • + Successfully captured the requested handwritten style and blackboard texture
  • + Good environmental context including the café background
  • Repeated the price as just a '9' then '$9' for the third item
  • The '& Herbs' line is slightly cramped compared to the rest of the board

Verdict: Both models handled the complex text and texture requirements of the prompt very well. FLUX.2 [dev] is the winner because it maintained better layout consistency and avoided the repetitive text error found in FLUX.2 [dev] Turbo's third menu item description.

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 [dev] Turbo

AI Judge Analysis

FLUX.2 [dev]

  • + Accurately identifies and transfers the face, sunglasses, and scarf from Image 2.
  • + Captures the environment color and the red box accurately.
  • Horrific anatomical failure where the woman's head from Image 1 is still attached to the torso along with the new man's head.
  • The body position is completely distorted and floaty with no clear leg structure.
  • The left hand is severely malformed.

FLUX.2 [dev] Turbo

  • + Successfully replicates the clothing and facial features of the man in Image 2.
  • + Better attempt at dynamic movement and foot placement compared to Model A.
  • Extreme anatomical error with two heads clearly visible and overlapping.
  • The pose does not match the 'exact pose' of Image 1, instead opting for a generic jump.
  • The integration of the scarf and torso is messy and incoherent.

Verdict: Both models failed significantly on the primary instruction of recreating the pose by leaving the original woman's head visible behind the new character's torso, resulting in a 'two-headed' monster effect. FLUX.2 [dev] Turbo (Model B) is marginally better as it attempts a coherent jump and maintains more natural human proportions, whereas FLUX.2 [dev] (Model A) produces a nonsensical, floating mass of limbs.

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 [dev] Turbo

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent high-contrast colors in the nebula background.
  • + Smooth and clean rendering of the space suit.
  • + Dynamic sense of motion with the horse's flowing tail and mane.
  • Failed the specific spatial instruction for the horse to be 'on top' of the astronaut.
  • Minor artifacting around the horse's hooves over the clouds.

FLUX.2 [dev] Turbo

  • + Highly detailed textures on the space suit and equipment.
  • + Complex background with multiple planets and celestial bodies.
  • + Sharp focus and cinematic lighting.
  • Failed the specific spatial instruction for the horse to be 'on top' of the astronaut.
  • Anatomical weirdness where the horse's back leg appears to be missing or merged into the cloud effects.

Verdict: Both FLUX.2 [dev] and FLUX.2 [dev] Turbo completely failed the negative/inverse logic of the prompt, which specifically requested the horse to be 'on top' of the astronaut. Instead, both models produced a standard astronaut riding a horse. FLUX.2 [dev] is slightly preferred for its more coherent composition and cleaner horse anatomy compared to the Turbo version.

Outfit Transfer Challenge

Editing
Edit instruction

“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.”

Source
FLUX.2 [dev]
FLUX.2 [dev] Turbo

AI Judge Analysis

FLUX.2 [dev]

  • + Attempts to preserve the unique vitigilo pattern and hair color from Image 1.
  • + Correctly interprets the plaid scarf and navy peacoat from Image 2.
  • + Maintains the facial structure of the person in Image 1 better than the competitor.
  • Fails to keep the face 'completely unchanged' by blending it with the man from Image 2.
  • Includes extra gold necklaces not present in either source image.

FLUX.2 [dev] Turbo

  • + Accurately replicates the elaborate jewelry and accessories requested.
  • + Excellent fabric rendering and lighting integration on the peacoat.
  • + Keeps the background largely consistent with the source.
  • Completely fails to preserve the identity of the person from Image 1, replacing them with the man from Image 2.
  • Disregards the instruction to keep the person's face and hair unchanged.
  • Loss of the skin details (vitiligo) that defined the base subject.

Verdict: Both models failed the most difficult part of the prompt: keeping the base person's face 'completely unchanged.' However, FLUX.2 [dev] is the clear relative winner as it attempted to merge the person's features and hair color, whereas FLUX.2 [dev] Turbo simply pasted the man from Image 2 into the scene, ignoring the identity of the base subject entirely.

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 [dev] Turbo

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent adherence to the capybara's expression and posture with paws on the wheel.
  • + Superior bokeh and night-time lighting effects in the background.
  • + Very realistic textures on the capybara's fur and the jacket fabric.
  • The businesswoman in the back appears slightly more blurry than necessary compared to the foreground.
  • The cap on the capybara has a slightly less defined logo compared to the other model.

FLUX.2 [dev] Turbo

  • + Includes a clear 'TAX' sign on the roof which adds to the New York taxi aesthetic.
  • + The human passenger's expression and detail are very sharp.
  • + Strong color and lighting contrast across the scene.
  • The capybara's paws look slightly less natural on the steering wheel than in the other image.
  • The text on the roof sign is slightly distorted ('TAX' instead of 'TAXI').

Verdict: Both models perform exceptionally well, following the complex prompt with high fidelity. FLUX.2 [dev] is slightly preferred for its more cohesive lighting and more natural-looking interaction between the capybara's paws and the steering wheel, whereas FLUX.2 [dev] Turbo has a slightly clearer passenger but produces a distorted 'TAX' sign on the roof.

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 [dev] Turbo

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent text rendering with no spelling errors
  • + Stronger contrast and cinematic lighting
  • + Intricate thorny border with clean spiderweb details
  • The jack-o-lantern is black, which feels slightly less 'vintage' than traditional orange
  • The background trees are somewhat less detailed than the other model

FLUX.2 [dev] Turbo

  • + Classic orange pumpkin fits the vintage theme well
  • + Highly detailed twisted trees in the background
  • + Perfect text adherence for all requested phrases
  • The thorny border is slightly messier and overlaps the parchment edges inconsistently
  • Lighting is a bit flatter across the central area compared to model A

Verdict: Both models performed exceptionally well on complex text rendering and prompt adherence. FLUX.2 [dev] produced a more polished, high-contrast look with a cleaner border, while FLUX.2 [dev] Turbo provided a more traditional color palette for the pumpkin and more atmospheric background scenery.

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 [dev] Turbo

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent preservation of the source image's facial features and clothing
  • + Realistic hair texture and complex frizzy details
  • + Accurate lighting that matches the environmental scene
  • Hairline integration at the forehead looks slightly abrupt

FLUX.2 [dev] Turbo

  • + Natural integration of the hairline into the facial skin
  • + High preservation of the source image backgrounds and lighting
  • + Creative interpretation of 'thick' hair as a voluminous style
  • Subtle loss of detail in the jacket texture compared to the source
  • The hair volume is slightly disproportionate to the head size

Verdict: Both models perform exceptionally well at this task, maintaining almost all original pixel data for the face, body, and background. FLUX.2 [dev] Turbo is slightly better at blending the new hair into the forehead skin, while FLUX.2 [dev] maintains a slightly higher fidelity on the existing beard and clothing textures.

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 [dev] Turbo

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent typography layout with perfectly centered text and icon.
  • + Sophisticated soft-plastic 3D claymation aesthetic.
  • + Very clean isometric perspective and shadow rendering.
  • The sushi roll details are slightly less crisp than the second image.

FLUX.2 [dev] Turbo

  • + Highly realistic PBR textures on the fish and wood grain base.
  • + Superior detail in individual rice grains and garnish.
  • + Very high clarity and sharp focus.
  • The text layout is slightly off-center compared to the other model.
  • The flag icon is placed to the side rather than centered beneath the text.

Verdict: Both models followed the prompt exceptionally well, producing clean isometric dioramas. FLUX.2 [dev] produced a more balanced and graphic-design-oriented composition with perfect text centering, while FLUX.2 [dev] Turbo excelled in realistic material rendering, particularly with the textures of the fish and wooden base. FLUX.2 [dev] is slightly preferred for its superior adherence to the 'cartoon scene' and layout instructions.

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 [dev] Turbo

AI Judge Analysis

FLUX.2 [dev]

  • + Successfully incorporates all elements: tv anchor desk, dogs, and hockey rink background.
  • + Maintains a stylistically consistent caricature aesthetic with exaggerated proportions.
  • + Good use of the source image for the facial features while adapting it to the cartoon art style.
  • Text on the desk is nonsensical gibberish.
  • The inclusion of an extra human character in the top left is unnecessary and distracting.

FLUX.2 [dev] Turbo

  • + Excellent facial caricature that captures the expression and likeness of the source image very well.
  • + Clever integration of dogs both in the foreground and on the studio monitors in the background.
  • + Dynamic composition that makes the 'anchor' role very clear with the desk and lighting.
  • Text on the desk is nearly legible but ultimately garbled.
  • The hands are a bit stiff in their open-air pose compared to the rest of the illustration.

Verdict: Both models performed exceptionally well on this task, successfully merging three distinct themes (news anchor, dogs, and hockey) into a cohesive caricature. FLUX.2 [dev] Turbo takes the lead because the central caricature has a much stronger likeness to the original woman in the source image, and the overall composition feels more like a professional sports broadcast set.

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 [dev] Turbo

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent fur detail and texture lighting.
  • + Successfully included all four requested animal types.
  • + Beautiful, clean composition with soft backlighting.
  • The animals are mostly sitting still rather than 'playfully chasing' and 'tumbling'.
  • Included a second redundant bunny instead of active movement.

FLUX.2 [dev] Turbo

  • + Captures the 'playfully chasing' and 'tumbling' aspect of the prompt much better.
  • + Dynamic poses and expressions convey a more joyful vibe.
  • + Excellent rendering of dew sparkles and golden hour light.
  • The kitten's front paw is slightly distorted/blurry.
  • Slightly less 'hyper-realistic' in the fur textures compared to Model A.

Verdict: Both models followed the prompt well, but FLUX.2 [dev] Turbo better captured the requested action of the animals tumbling and chasing. While FLUX.2 [dev] produced a cleaner, more static portrait, FLUX.2 [dev] Turbo's dynamic composition feels more aligned with the 'sparkles' and 'joyful' tone requested.

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 [dev] Turbo

AI Judge Analysis

FLUX.2 [dev]

  • + Successfully captures the requested soft pastel color palette and hand-painted texture.
  • + Maintains the clear emotional expressions and iconic poses from the source image.
  • + The background transition into a flowery meadow fits the Ghibli aesthetic well.
  • The woman in the foreground has a face that looks slightly flatter than the other characters.
  • Lost the urban context of the original photo entirely by replacing it with a field of flowers.

FLUX.2 [dev] Turbo

  • + Excellent preservation of the original composition, including the background bus and city environment transformed into Ghibli style.
  • + Highly accurate facial expressions that perfectly match the 'distracted boyfriend' meme energy.
  • + Superior hand-painted texture quality and lighting that feels more distinctly like a film cel.
  • The character on the far left (added in) has a slightly different art style than the main trio.

Verdict: While both models successfully translated the image into a Ghibli-inspired art style, FLUX.2 [dev] Turbo is the clear winner for its superior preservation of the source image's layout and context. It managed to keep the urban elements like the bus and buildings while stylizing them, whereas FLUX.2 [dev] replaced the environment with generic flowers.

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 [dev] Turbo

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent hair motion that looks natural and windswept.
  • + Added leaves are detailed and integrated well with realistic motion blur.
  • + Maintains high color and lighting consistency with the original image.
  • The leash handle has slightly fused with the woman's hand compared to the original.

FLUX.2 [dev] Turbo

  • + Successfully adds both wind-blown hair and floating leaves as requested.
  • + Preserves the identity of the person and the dog accurately.
  • + Leaves are distributed throughout the scene, creating a sense of depth.
  • The hair motion looks slightly more stiff and symmetrical compared to Model A.
  • A stray leaf artifact appears directly over the woman's collarbone/neck area.

Verdict: Both models followed the instructions very well, effectively adding motion through hair and leaves while preserving the core elements of the source image. FLUX.2 [dev] is the winner because the hair physics look much more organic and the integration of leaves feels more natural than the slightly more chaotic and artifact-prone placement in FLUX.2 [dev] Turbo.

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 [dev] Turbo

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent vector logo clarity with clean lines.
  • + Includes all requested text elements accurately.
  • + Perfectly centered and balanced composition.
  • The 'Est. 1720' text is slightly small within the banner.
  • The texture on the background is very subtle, almost unnoticeable.

FLUX.2 [dev] Turbo

  • + Beautiful use of texture and distressed effects for a vintage feel.
  • + Sophisticated typography with subtle shadow details.
  • + More dynamic steam and banner design.
  • The extra decorative flourish at the bottom is slightly off-center.
  • The banner edges are a bit more complex, moving slightly away from 'minimalist'.

Verdict: Both models followed the prompt exceptionally well, producing high-quality professional logos. FLUX.2 [dev] is preferred for a cleaner, modern vector look, while FLUX.2 [dev] Turbo captured the 'vintage' and 'subtle texture' requirements more effectively, resulting in a more atmospheric and aesthetically pleasing 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.”

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

AI judge analysis unavailable for this challenge.

Next steps

Explore each model