Head to head
Esc

Models · slot A

to navigate to pick

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

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

FLUX.2 [dev]

24.3 arena score

#20 of 62 in Text-to-Image

Skill signature · Text-to-Image

FLUX.2 [dev] Flash

27.0 arena score

#7 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.2 [dev]

25.0%

win rate

Ties

25.0%

FLUX.2 [dev] Flash

50.0%

win rate

25.0% 25.0% 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] Flash
0% wins 100% ties 0% wins

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent rendering of the blue sphere with realistic internal light refraction.
  • + Soft, warm lighting that convincingly emanates from the left window.
  • + Smooth glass texture with realistic rounded edges.
  • The plant in the background is very blurry and lacks definition.
  • The blue sphere appears to be magically floating rather than resting on the bottom of the cube.

FLUX.2 [dev] Flash

  • + Superior sharpness and detail in the plant leaves and the book's spine text.
  • + The glass cube features realistic dust particles and reflections that ground it in the environment.
  • + Perfect adherence to the spatial arrangement, with the sphere correctly resting on the glass floor.
  • The lighting is slightly more clinical and less 'soft' than requested compared to Model A.

Verdict: Both models followed the complex prompt perfectly, including the specific spatial relationships of all four objects. FLUX.2 [dev] Flash is the winner because it provides much higher detail in the secondary elements like the plant and book spine, and realistically places the sphere on the floor of the cube, whereas FLUX.2 [dev] shows the sphere floating.

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] Flash

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent preservation of the subject's specific plaid coat, scarf, and hairstyle.
  • + Faithful recreation of the car's interior details, including the white leather seats and dashboard style.
  • + Realistic lighting and motion blur on the background coastline.
  • The man is facing away from the center of the car in a slightly awkward driving posture.
  • The steering wheel appears small and sits very close to the dashboard.

FLUX.2 [dev] Flash

  • + Strong composition that better highlights the scenery and the car's aesthetic.
  • + Higher detail in the facial rendering and hair texture.
  • + Captures the 'California coastline' vibe with clear, vibrant lighting.
  • The man's hand on the steering wheel has anatomical issues (clumsy grip and thumb placement).
  • Mirror placement on the windshield is slightly nonsensical and creates a distracting visual overlap.

Verdict: Both models do an impressive job of merging the two source images, maintaining the specific fashion of the man and the interior of the Rolls-Royce. FLUX.2 [dev] offers better consistency with the source man's profile and clothing patterns, while FLUX.2 [dev] Flash provides a more engaging cinematic composition and clearer background elements despite some anatomical flaws in the hand.

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] Flash

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent motion blur on passing vehicles
  • + Authentic 'imperfect framing' with a candid street photography feel
  • + Subtle, realistic rain effects
  • The structural integrity of the bicycle's handlebars and frame is messy
  • Skin texture is slightly smoothed compared to the prompt's request

FLUX.2 [dev] Flash

  • + Very high detail in skin texture and facial features
  • + Better bicycle coherence with a clear frame and basket
  • + Stronger puddles and rain splashes on the ground
  • Motion blur on cars is less convincing than Model A
  • The composition feels slightly more staged than Model A

Verdict: Both models followed the prompt well, but Model A (FLUX.2 [dev]) captures the 'candid' and 'motion blur' requirements more effectively, creating a more cinematic atmosphere. However, Model B (FLUX.2 [dev] Flash) provides much better anatomical and mechanical detail, with superior skin textures and a more realistically constructed bicycle.

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] Flash
0% wins 0% ties 100% wins

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent warm lighting with strong rim light on the character
  • + Highly realistic leather texture and metallic reflections
  • + More organic and believable integration of braids and beads
  • The scar on the forehead looks slightly like a surface-level sticker compared to the skin texture

FLUX.2 [dev] Flash

  • + Very intricate engraving details on the plate armor
  • + Symmetrical composition with balanced torchlight
  • + Better representation of realistic skin trauma and dirt
  • Slightly flatter lighting compared to the dynamic depth of the other model
  • Metal textures look a bit cleaner/newer despite the battle-worn prompt

Verdict: Both models followed the prompt exceptionally well, capturing the braided hair, ornate armor, and lighting. FLUX.2 [dev] produces a more cinematic shot with superior lighting and depth, whereas FLUX.2 [dev] Flash provides more intricate fine-line engravings on the armor and a more symmetrical composition.

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] Flash

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent typography layout and spacing
  • + Followed the specific header request including Appetizers, Pizza, and Mains
  • + Logical pricing alignment
  • Text is largely gibberish strings
  • Vibrant accents are a bit repetitive in color

FLUX.2 [dev] Flash

  • + Strong 'vibrant' color accents with colored photo borders
  • + Realistic food photography thumbnails
  • + Clean, central grid layout
  • Text rendering is messy with characters overlapping and inconsistent sizes
  • Section headers are less distinct than the other model
  • Pricing formatting contains some illogical decimals like $8,10

Verdict: Both models followed the prompt well, but FLUX.2 [dev] produced a much more realistic typographic layout that mimics a professional menu, whereas FLUX.2 [dev] Flash struggled with font consistency and text clarity. FLUX.2 [dev] also correctly included all three requested categories (Appetizers, Pizza, Mains) with distinct hierarchy.

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] Flash

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent text clarity and typography
  • + Perfectly rendered starburst shape
  • + Vibrant and high-contrast color palette
  • The burger ingredients are stacked very conventionally, losing some of the 'exploded' dynamic feel
  • Bottom bun looks slightly flat and less photorealistic compared to the top

FLUX.2 [dev] Flash

  • + Superior 'exploded' composition with a more dynamic, tilted angle
  • + Higher level of photorealistic detail in the ingredients like the sesame seed bun and patty
  • + Better integration of dripping sauce for a sense of motion
  • The main 'MAGIC BURGER' text is slightly less crisp than Model A
  • The starburst shape is a bit more irregular

Verdict: Both models followed the prompt exceptionally well, but FLUX.2 [dev] Flash produces a more professional and dynamic shot by tilting the burger and adding intricate details like sesame seeds and textures. While FLUX.2 [dev] has slightly cleaner text rendering, FLUX.2 [dev] Flash captures the 'exploded' and 'photorealistic' requirements with greater artistry.

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] Flash

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent chalk texture throughout the board
  • + Highly realistic smudging and chalk dust effects
  • + Successfully completed the description for 'Brown Butter Chocolate Chip Cookies'.
  • The 'Grilled Octopus' line has messy overlapping text and a misplaced hyphen.
  • The handwriting style is slightly inconsistent between the headers and the bottom text.

FLUX.2 [dev] Flash

  • + Layout is very clean and readable.
  • + Consistent handwriting style across all menu items.
  • + Good visual balance of the café background.
  • Repeated the price '$9' on two separate lines for the cookies.
  • The handwriting looks a bit more like a digital font compared to the realistic texture in Model A.

Verdict: Both models handled the text-heavy prompt impressively. FLUX.2 [dev] provides a more authentic chalkboard feel with superior chalk texture and dust, though it struggled with the layout of the middle item. FLUX.2 [dev] Flash produced a cleaner layout but suffered from a logical error by repeating the price on two lines and had a slightly more 'perfect' digital handwriting look.

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] Flash

AI Judge Analysis

FLUX.2 [dev]

  • + Successfully incorporates the character's clothing and accessories from Image 2.
  • + Captures the facial likeness and sunglasses of the man in Image 2.
  • Catastrophic failure in anatomy, showing a second distorted face growing out of the character's torso.
  • Fails to replicate the specific leg position of the pose from Image 1.

FLUX.2 [dev] Flash

  • + Accurately replicates the face and accessories of the character in Image 2.
  • + Maintains a cleaner background and more consistent lighting.
  • Significant anatomical error with a third leg and disembodied hair appearing behind the main character.
  • Does not replicate the dynamic body angle or leg crossing from Image 1, making it look like he is just standing on the box.

Verdict: Both models failed significantly on the task of mapping a new character onto a complex pose, resulting in severe anatomical glitches like extra limbs and faces. FLUX.2 [dev] Flash is slightly better only because its anatomical errors are less jarring than the distorted face growing out of the torso in FLUX.2 [dev], though both failed to accurately recreate the 'exact pose' from Image 1.

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] Flash

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent anatomical rendering of the horse and astronaut suit.
  • + High-quality cinematic lighting with realistic reflections on the visor.
  • + Clean composition with a beautiful contrast between the horse and the cosmic background.
  • Failed to follow the specific surreal instruction for the horse to be on top of the astronaut.

FLUX.2 [dev] Flash

  • + Strong visual details on the astronaut's face through the visor.
  • + Dynamic composition with added elements like floating rocks and multiple moons.
  • Serious anatomical glitch with a second horse's rear end appearing behind the main horse.
  • Failed to follow the specific surreal instruction for the horse to be on top of the astronaut.

Verdict: Both FLUX.2 [dev] and FLUX.2 [dev] Flash failed the negative constraint to have the horse on top of the astronaut, both opting for the traditional 'astronaut riding horse' trope. FLUX.2 [dev] is preferred as it is a much cleaner image, whereas FLUX.2 [dev] Flash contains a significant hallucination of a second horse tail and hindquarters merging into the main subject.

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] Flash

AI Judge Analysis

FLUX.2 [dev]

  • + Successfully transferred the coat, scarf, glasses, and jeans from Image 2.
  • + Maintained high image clarity and consistent lighting.
  • + Correctly applied the vitiligo pattern to the new hairstyle.
  • Failed to preserve the face of the person in Image 1, merging it with the person in Image 2.
  • Changed the person's hair and facial hair style significantly.
  • Added excessive gold jewelry that was not present in Image 2.

FLUX.2 [dev] Flash

  • + Attempted to keep the face of the person from Image 1.
  • + Included elaborate jewelry and accessories fitting the 'elaborate' description.
  • + Matched the scarf and coat textures well.
  • Extreme facial distortion and artifacts (multiple sets of eyes and nose).
  • Poorly blended composition with a floating head behind the main subject.
  • Did not maintain the 'exact' outfit from Image 2, adding much more ornate silver jewelry.

Verdict: Both models failed significantly on source preservation and accurate instruction following. FLUX.2 [dev] produced a clean, aesthetically pleasing image but completely ignored the instruction to keep the person's face from Image 1 unchanged, essentially creating a hybrid of the two people. FLUX.2 [dev] Flash attempted to keep the face and the 'elaborate' nature of the clothing but resulted in a nightmarish, distorted image with severe anatomical errors and artifacts. FLUX.2 [dev] is the winner simply for being a coherent image, despite the failure to preserve the identity.

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] Flash

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent character placement and framing from outside the windshield.
  • + The capybara's expression is very professional and matches the prompt perfectly.
  • + Superior lighting effects on the capybara's fur and the passenger's face.
  • The capybara's 'paws' look a bit too human-like and uncanny.
  • Small artifacting on the passenger's phone screen.

FLUX.2 [dev] Flash

  • + Successfully includes the taxi 'roof sign' which adds to the New York context.
  • + Good texture on the capybara's fur and the jacket material.
  • + Accurate bored/normal expression on the businesswoman.
  • The capybara's face shape is slightly distorted/elongated compared to a real capybara.
  • The cap is floating unnaturally above the head.
  • The steering wheel grip looks less natural and more like hooked claws.

Verdict: Both models followed the prompt exceptionally well, capturing the surreal humor of a capybara taxi driver. FLUX.2 [dev] edges ahead with better composition and a more convincing 'professional' expression for the capybara, whereas FLUX.2 [dev] Flash has some minor issues with the anatomy of the capybara's face and the placement of the hat.

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] Flash

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent text legibility and accuracy
  • + Strong, cohesive border design with clean thorns and webs
  • + Better central framing of the jack-o-lantern
  • The parchment texture is limited to the very edges
  • Slightly less 'vintage' feel in the background lighting

FLUX.2 [dev] Flash

  • + Atmospheric lighting with more visible environmental detail
  • + Good use of the scroll banner for the secondary text
  • + More complex background texture
  • Includes hallucinated nonsensical text ('Huck: 0s69') in the details
  • The border feels a bit more cluttered and less structured than Image A
  • The orange pumpkin body lacks the dark gothic contrast seen in Image A

Verdict: Both models followed the prompt very well, but FLUX.2 [dev] is the winner due to its flawless text execution and cleaner composition. FLUX.2 [dev] Flash delivers a more atmospheric background, but it introduced hallucinated characters in the event details section, making it less practical for an actual 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 [dev] Flash

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent preservation of the original face, lighting, and background.
  • + Realistic hair texture and complex silhouette.
  • + Natural integration with the existing facial hair.
  • The choice of a large afro-style haircut may be seen as a specific stylistic leap rather than a generic 'full head of hair'.

FLUX.2 [dev] Flash

  • + Successfully adds a full head of hair while preserving the identity of the person.
  • + Maintains the original environment and lighting perfectly.
  • The hairline is slightly less realistic than in model A, appearing a bit straighter/man-made.
  • The hair texture is slightly softer and has less fine detail than Model A.

Verdict: Both models performed remarkably well, maintaining the original person's features, clothing, and background with near-perfect fidelity. FLUX.2 [dev] (Model A) is the winner by a small margin due to the superior realism in the hair's fine texture and the more natural-looking 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 [dev] Flash

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent layout with the text and flag perfectly centered and stacked as requested.
  • + Realistic materials and soft lighting that match the miniature 3D cartoon style perfectly.
  • + High level of detail in the rice grains and fish textures.
  • The diorama base is a bit plain compared to the wood texture in the alternative.

FLUX.2 [dev] Flash

  • + Beautiful wood grain texture on the raised diorama base.
  • + Clean, vibrant colors and soft clay-like modeling for the food elements.
  • + Good adherence to the isometric perspective.
  • The flag icon is placed next to the word 'SUSHI' rather than being a separate element below as implies by the stacking logic.
  • The sushi roll in the front has slightly inconsistent cross-section patterns.

Verdict: Both models followed the prompt exceptionally well, capturing the 3D isometric cartoon aesthetic. FLUX.2 [dev] is the winner because it adhered more strictly to the requested text layout (stacking 'JAPAN', 'SUSHI', and the flag icon vertically) and provided a slightly more diverse and realistic platter of sushi.

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] Flash
100% wins 0% ties 0% wins

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent caricature style with classic 'big head' exaggeration.
  • + Cleverly combines the hockey and TV anchor themes by placing the desk on ice.
  • + Preserves the subject's facial features accurately in the illustrated style.
  • The text on the desk is garbled and unreadable.
  • Includes a random secondary human figure that wasn't requested.

FLUX.2 [dev] Flash

  • + Very clean and vibrant illustration style with great lighting.
  • + Excellent text rendering of 'TV SHOW' on the desk.
  • + Features a high variety of dogs in the requested hockey gear.
  • The hands of the central character are slightly odd/small in proportion to the body.
  • Subject's face feels slightly more generic than Model A's version.

Verdict: Both models followed the complex instructions excellently, creating a coherent scene that blends a news desk with a hockey rink and dogs. FLUX.2 [dev] (Model A) feels more like a traditional caricature but suffers from poor text rendering, whereas FLUX.2 [dev] Flash (Model B) delivers a more polished, professional-looking illustration with perfectly legible text.

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] Flash
0% wins 0% ties 100% wins

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent photorealistic lighting with realistic god rays and backlighting on the fur.
  • + Very high-quality textures on the animals, particularly the fox and golden retriever.
  • + The animals' eye expressions are sharp and soulful.
  • Includes an extra baby bunny not explicitly requested (two instead of one).
  • The kitten appears somewhat static and less 'playful' compared to the others.

FLUX.2 [dev] Flash

  • + Better captures the 'playfully chasing' and 'tumbling' aspect of the prompt with dynamic poses.
  • + Accurately includes more butterflies scattered throughout the scene.
  • + Bright, vibrant colors that enhance the wholesome vibe.
  • Anatomy errors: the kitten has an extra leg/paw under its chest, and the brown bunny has facial features that look like a cat/bunny hybrid.
  • The lighting feels slightly more filtered/digital and less naturally photorealistic than Model A.

Verdict: FLUX.2 [dev] produces a much more polished and photorealistic image with superior fur textures and realistic lighting, though it added an extra rabbit. FLUX.2 [dev] Flash better captured the playful movement requested in the prompt, but it suffered from notable anatomical glitches and a more artificial aesthetic. FLUX.2 [dev] is the winner for its overall technical quality and believable rendering.

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] Flash

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent preservation of the source image compositions and character poses.
  • + Effective use of the requested soft pastel color palette.
  • + Captures the Ghibli aesthetic through clean line work and watercolor-like textures.
  • The facial expression of the woman in the red dress is slightly more generic than the source.

FLUX.2 [dev] Flash

  • + Successfully replicates the Ghibli style with soft, hand-painted textures.
  • + Preserves the iconic meme composition and character relationships perfectly.
  • + Adds a charming 'dreamy' background with a setting sun and flower field.
  • The hand-holding between the man and the woman in blue is slightly less defined than in model A.

Verdict: Both FLUX.2 [dev] and FLUX.2 [dev] Flash did an exceptional job at transforming the 'distracted boyfriend' meme into a Studio Ghibli illustration. They both maintained the exact poses and character placement while applying a soft, painted aesthetic. FLUX.2 [dev] Flash is the slight winner for its more vibrant 'dreamy' lighting and the addition of a small whimsical creature in the background, which aligns perfectly with the Ghibli theme.

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] Flash

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent preservation of the source image's facial features and clothing.
  • + The hair motion feels natural and flows well with the character's movement.
  • + Leaves are integrated realistically with varying levels of focus.
  • The leaf count is slightly more sparse than Model B.

FLUX.2 [dev] Flash

  • + Strong dynamic feel with a high frequency of leaves.
  • + Excellent source preservation including the dog and background environment.
  • + Hair movement is dramatic and visually appealing.
  • Some leaves appear a bit repetitive or flat in lighting compared to the source.

Verdict: Both FLUX.2 [dev] and FLUX.2 [dev] Flash performed exceptionally well, perfectly preserving the source identity, background, and animal while accurately adding the requested motion effects. Model A is slightly preferred for its more natural hair integration and realistic depth-of-field on the flying leaves, whereas Model B provides a slightly busier, 'windier' appearance.

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] Flash

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent typography execution with clear, bold letters and proper accent usage.
  • + Very clean emblem layout that feels balanced and minimalist.
  • + Accurate adherence to the color palette and textures requested.
  • The banner structure is slightly disjointed where the top and bottom sections meet.

FLUX.2 [dev] Flash

  • + Beautiful steam effect that looks more organic and flowing.
  • + Sophisticated shading on the cloche dome adds depth and a premium feel.
  • + More cohesive banner design with better scrollwork on the ends.
  • The 'EST.' text is lowercase ('Est.') rather than the capitalization typically seen in classic logos.
  • Typography for 'FLORIAN' has slightly inconsistent kerning compared to Model A.

Verdict: Both models followed the prompt exceptionally well, producing high-quality vintage logos with perfect spelling. FLUX.2 [dev] is preferred for its cleaner vector-style lines and more professional typography, whereas FLUX.2 [dev] Flash offers a more artistic, shaded look that feels slightly more illustrative.

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] Flash

AI Judge Analysis

FLUX.2 [dev]

  • + Extremely clean vector aesthetic and consistent icon design.
  • + Adheres closely to the specified NASA-inspired color palette.
  • + Includes creative extra details like the astronaut names and 'Tranquility' marker.
  • Several labels are severely garbled or misspelled ('Tranquility', 'Ualsist Ordit').
  • The logical flow of the steps is disorganized across the grid.

FLUX.2 [dev] Flash

  • + Better logical flow with arrows indicating a sequential mission path.
  • + Text rendering for labels like 'Earth Orbit' and 'Landing' is highly accurate.
  • + Includes relevant character icons for the astronauts.
  • Redundant labels and graphics (e.g., 'Lunar Orbit' appears twice).
  • The 'Earth' icon is incorrectly used for the 'Lunar Orbit' step.
  • Visual layout feels more cluttered and less like a professional 'clean' infographic.

Verdict: FLUX.2 [dev] produces a much more polished and aesthetically pleasing vector style that perfectly matches the requested 'clean' look, though its spatial logic and text spelling are poor. FLUX.2 [dev] Flash follows the mission sequence more intuitively with its layout and has better text accuracy, but it suffers from repetitive elements and incorrect iconography for the lunar stages. FLUX.2 [dev] is the preferred choice for its superior visual quality and adherence to the art style prompt.

Next steps

Explore each model