Head to head
Esc

Models · slot A

to navigate to pick

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

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 [max]

25.9 arena score

#10 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.2 [dev]

66.7%

win rate

Ties

0.0%

FLUX.2 [max]

33.3%

win rate

66.7% 0.0% ties 33.3%
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 [max]
100% wins 0% ties 0% wins

AI Judge Analysis

FLUX.2 [dev]

  • + Perfect adherence to the prompt's spatial instructions.
  • + Excellent glass refraction and lighting consistency.
  • + Warm, natural photographic aesthetic.
  • The blue sphere appears slightly levitating rather than resting on the bottom.

FLUX.2 [max]

  • + High-fidelity textures, specifically on the book cover and wooden table.
  • + Sharp, clean geometry for the glass cube.
  • + Realistic light streaks on the table surface.
  • The sphere is not truly 'inside' the cube, appearing to float through or in front of the glass pane.
  • The glass cube lacks a bottom, making its structure physically confusing.

Verdict: FLUX.2 [dev] followed the spatial instructions perfectly, accurately placing the plant behind the glass and the sphere inside it. While FLUX.2 [max] has slightly more crisp textures, it failed the core logic of the prompt by rendering the blue sphere as if it were passing through the front glass panel and omitting the bottom of the cube.

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 [max]

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent character consistency, accurately preserving the man's hair, scarf, and coat pattern.
  • + High-quality interior detail of the car showing realistic dash and seats.
  • + Good sense of motion and perspective from within the vehicle.
  • The driver side is on the right, which is incorrect for a car driving in California.
  • The car's exterior frame is partially cut off due to the close framing.

FLUX.2 [max]

  • + Successfully places the original car and man into the full environment.
  • + Preserves the car's exterior design and the man's key features very well.
  • + Correctly places the driver on the left side for a US-based road.
  • The scale of the man relative to the car seems slightly off, making him look a bit small.
  • Minor artifacts in the background coastline texture.

Verdict: Both models perform exceptionally well at preserving both the subject and the vehicle from the source images. FLUX.2 [dev] provides a more intimate, cinematic interior shot with better character lighting but fails by placing the steering wheel on the right side for a California setting, while FLUX.2 [max] captures the full scene more logically with correct road placement and better preservation of the car's exterior.

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 [max]
0% wins 0% ties 100% wins

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent representation of motion blur from passing cars.
  • + Highly realistic skin texture and facial details.
  • + Stronger 'candid' feel with messy foreground elements and imperfect framing.
  • The structural integrity of the bike is poor, with mismatched parts and confusing geometry.
  • The man's hands melt into the bike's handlebars and wires.

FLUX.2 [max]

  • + The bicycle is significantly more coherent and realistic in its construction.
  • + The composition is clean and clearly depicts the act of 'repairing' with tools on the ground.
  • + Good use of wet pavement reflections and shallow depth of field.
  • Missed the 'motion blur from passing cars' instruction; the background car is sharp.
  • The framing feels a bit too staged and centered compared to the 'imperfect' request.

Verdict: FLUX.2 [dev] followed the technical prompt instructions better, specifically the inclusion of motion blur and the 'imperfect framing' of a candid street shot, though it struggled with the logical anatomy of the bicycle. FLUX.2 [max] produced a much more structurally sound bicycle and a very high-quality subject, but it ignored the motion blur requirement and felt more like a posed portrait than a candid street photo. FLUX.2 [dev] is preferred for closer adherence to the specific atmospheric and cinematic requests.

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 [max]

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent adherence to the 'beads in hair' prompt element
  • + Clear and visible torch source providing realistic lighting
  • + Very intricate engraving details on the chest plate
  • The leather straps look slightly flat in texture compared to the armor
  • Scars look a bit like face paint rather than physical indentations

FLUX.2 [max]

  • + Superior 'battle-worn' texture with realistic grime and weathered metal
  • + High-quality skin texture and more intense, lifelike eyes
  • + Exceptional detail on the frayed cloth underlayer
  • The torch is out of focus and less impactful for the 'warm torchlight' requirement
  • Hair beads are less colorful and distinct than Model A

Verdict: Both models followed the prompt exceptionally well, but FLUX.2 [max] produced a more convincing 'battle-worn' appearance with grittier textures and more realistic skin rendering. FLUX.2 [dev] captured the specific detail of the beads in the hair more effectively, but its overall lighting and scarring felt slightly more artificial.

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 [max]

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent photographic quality and lighting for food items.
  • + Strong adherence to the multi-column sections requested.
  • + Modern and high-end aesthetic with vibrant color gradients.
  • Text is largely gibberish or contains significant character glitches.
  • The grid layout is slightly uneven in the right column.

FLUX.2 [max]

  • + Highly legible and clean typography for a menu.
  • + Perfect grid alignment for the food photos.
  • + Professional iconography and social media footer added.
  • The food photography has a slightly flatter, more generic stock-photo look.
  • The image content doesn't always match the section titles (e.g. burgers and wraps under 'Appetizers').

Verdict: While FLUX.2 [dev] produces much more appetizing food photography, FLUX.2 [max] is the superior choice for a design task. FLUX.2 [max] delivers a perfectly organized grid, legible prices and headings, and a layout that actually functions like a professional graphic design piece. FLUX.2 [dev] suffers from garbled text that detracts from the professional menu feel.

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 [max]

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent typography with a cohesive neon fiery glow effect.
  • + Better composition where each individual ingredient is clearly separated.
  • + Stronger sense of motion with the dynamic splashing sauce droplets.
  • The meat patty texture is slightly less detailed than in the competitor's image.

FLUX.2 [max]

  • + Highly realistic food textures, especially the sesame seeds and the sear on the patty.
  • + Complex layering of ingredients with high sharpness.
  • The 'exploded' effect is less clear because several ingredients are still touching each other.
  • The starburst element looks like a flat graphic compared to the more integrated fiery version in Model A.
  • The 'LIMITED TIME ONLY' text lacks the requested fiery glow.

Verdict: FLUX.2 [dev] followed the prompt more accurately by ensuring all text elements had the requested fiery glow and the burger was fully 'exploded' with clear separation. While FLUX.2 [max] produced slightly more detailed food textures, it failed to apply the glowing effect to the secondary text and the starburst looked out of place.

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 [max]

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent chalk texture throughout the board
  • + Highly authentic 'handwritten' aesthetic with varied letter sizes
  • + Includes the complete requested text perfectly
  • The layout is a bit cluttered with the text overlapping some chalk smudges

FLUX.2 [max]

  • + Perfect alignment and spacing of the menu items
  • + Consistent and elegant cursive handwriting style
  • + Excellent lighting and warm café atmosphere
  • The handwriting looks slightly too uniform, almost like a digital chalk font
  • Missing the hyphen in the date requested in the prompt

Verdict: Both models handled the complex text rendering exceptionally well. FLUX.2 [dev] produced a more authentic 'messy' chalk look that feels manually written, while FLUX.2 [max] created a cleaner, more aesthetically pleasing composition that resembles professional calligraphy. FLUX.2 [dev] is slightly preferred for strictly following the prompt's request for 'natural variations' and specific punctuation.

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 [max]

AI Judge Analysis

FLUX.2 [dev]

  • + Successfully captures the facial features and accessories from the character reference.
  • Extreme anatomical errors including a severed head remaining on the left side of the torso.
  • Fails to match the pose, showing a floating figure rather than the specific stance on the box.
  • Low visual quality with blurry blending where the original person's head was.

FLUX.2 [max]

  • + Excellent adherence to the complex pose and body position from Image 1.
  • + Accurately replicates the clothing, scarf, and sunglasses from Image 2.
  • + High visual quality with natural lighting and consistent anatomy.
  • Perspective on the feet standing on the ottoman is slightly flat compared to the reference.

Verdict: FLUX.2 [dev] fails the task significantly by leaving the original person's head in the image and creating a nonsensical floating body. In contrast, FLUX.2 [max] perfectly executes the instruction, placing the correct character in the exact dynamic pose from Image 1 with high fidelity and realistic integration.

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 [max]

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent sense of motion and dynamic composition.
  • + Highly detailed spacesuit and horse anatomy.
  • + Beautiful lighting reflecting off the Earth's atmosphere.
  • Failed the negative constraint; the astronaut is riding the horse, not vice versa.
  • The horse's back hooves are blurred into the Earth's clouds.

FLUX.2 [max]

  • + Stellar background with a very cinematic galaxy formation.
  • + Interesting use of an asteroid as a platform for the horse.
  • + Crisp details on the horse's coat and equipment.
  • Failed the negative constraint; the astronaut is riding the horse.
  • The astronaut's left leg seems slightly malformed where it meets the saddle.

Verdict: Both FLUX.2 [dev] and FLUX.2 [max] failed the tricky negative constraint to have the 'horse on top' (meaning the horse riding the astronaut). Despite this, FLUX.2 [dev] produced a much more dynamic and visually compelling image with better lighting and a sense of movement compared to the more static composition of FLUX.2 [max].

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 [max]

AI Judge Analysis

FLUX.2 [dev]

  • + Successfully replicates the scarf pattern and coat style
  • + High visual quality and lighting integration
  • Failed to preserve the source person's face and identity, merging features with the person in Image 2
  • Inaccurately added gold chains not present in either source image
  • Altered the person's hair and skin patterns

FLUX.2 [max]

  • + Perfectly preserves the source person's face, skin patterns, and hair
  • + Accurately replicates the outfit including the scarf, coat, and jeans
  • + Excellent integration of clothing onto the subject's pose and body
  • Minor omission of the sunglasses from Image 2

Verdict: FLUX.2 [max] is the clear winner as it followed all instructions, especially the critical requirement to keep the person's face and hair completely unchanged. FLUX.2 [dev] failed the core identity preservation task by blending the faces of the individuals in Image 1 and Image 2.

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 [max]

AI Judge Analysis

FLUX.2 [dev]

  • + Successfully renders animal paws on the steering wheel as requested
  • + Excellent cinematic lighting and focus on the capybara's texture
  • + Perfectly captures the bored, mundane expression of the passenger
  • The scale of the capybara's head is slightly large relative to the driver's seat space

FLUX.2 [max]

  • + Great side-profile composition showing more of the car interior
  • + Realistic lighting effect from the phone screen on the passenger's face
  • Failed the anatomy prompt by giving the capybara human hands
  • The capybara's head is not properly attached to the neck/body

Verdict: FLUX.2 [dev] followed the specific anatomical instructions much better than FLUX.2 [max], which oddly gave the capybara human hands. FLUX.2 [dev] also achieved a more believable 'mundane' atmosphere through the passenger's expression and a more coherent integration of the animal into the driver's seat.

The Halloween Invitation

Text-to-Image

“Vintage gothic Halloween party invitation. Dark parchment poster, spooky border with webs and thorns, central glowing jack-o-lantern, bats, twisted trees, moody night sky. Add elegant gothic title text saying "Halloween Party Invitation", a small scroll banner saying "You are invited to a night of frights", and event details at the bottom: Date: 30.10.2026 Time: 7pm Location: The Arches, NYC Spooky but polished, cinematic lighting, square format.”

FLUX.2 [dev]
FLUX.2 [max]

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent typography and layout for all text elements
  • + Captures the vintage gothic aesthetic perfectly with moody colors
  • + High-quality, clean borders that integrate webs and thorns seamlessly
  • The jack-o-lantern is mostly black, which feels more illustrative than cinematic

FLUX.2 [max]

  • + Realistic lighting and texture on the central jack-o-lantern
  • + More atmospheric background featuring church silhouettes
  • + Good scroll detail with elegant cursive font
  • Typography for the main title looks slightly generic and less integrated into the art
  • The spider webs in the bottom corners are less detailed than those in the top

Verdict: Both models followed the prompt exceptionally well, producing perfect text and meeting all thematic requirements. FLUX.2 [dev] is the winner because its overall composition feels more like a cohesive vintage poster, whereas FLUX.2 [max] feels like a high-quality 3D render layered with text.

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 [max]

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent preservation of the original person's facial features and bone structure.
  • + Detailed hair texture with realistic curls and flyaways.
  • + The hair blends naturally with the existing beard and sideburns.
  • The hairline across the forehead appears slightly too straight and uniform.

FLUX.2 [max]

  • + Natural and realistic hairline with uneven growth patterns.
  • + Great integration of lighting and highlights on the hair strands.
  • + Preserved the background and clothing perfectly.
  • Significantly altered the facial structure, making the man look younger and thinner in the face compared to the source.

Verdict: FLUX.2 [dev] followed the instruction best by adding a full head of hair while keeping the person's original identity intact. FLUX.2 [max] produced a very realistic-looking head of hair, but failed the 'preserve facial features' requirement by smoothing the skin and altering the subject's face significantly enough to look like a different person.

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 [max]

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent text layout and vertical centering of the flag.
  • + Higher level of realism in the fish and rice texture.
  • + Clean shadows and soft, refined lighting that feels like a polished 3D render.
  • The diorama base is very simple compared to the 'miniature scene' description.

FLUX.2 [max]

  • + Better interpretation of the 'diorama base' and 'miniature scene' with a tiered platform and wooden platter.
  • + Includes logical environmental details like chopsticks and ginger.
  • + Strong adherence to the isometric perspective and cartoon-style modeling.
  • The flag icon is placed to the side of the text rather than vertically centered as implied by the layout.
  • The textures look slightly flatter and more plastic-like than Model A.

Verdict: Both models followed the prompt exceptionally well, producing clean 3D isometric designs. FLUX.2 [dev] produced higher quality textures and superior typography layout, while FLUX.2 [max] offered a better scene composition with more interesting architectural elements for the diorama base.

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 [max]

AI Judge Analysis

FLUX.2 [dev]

  • + Successfully incorporates all elements: tv anchor, dogs, and hockey in a cohesive rink-side news desk scene.
  • + Maintains recognizable facial features from the source image within the caricature style.
  • + The traditional caricature art style captures the humorous essence requested better than a generic cartoon.
  • The text on the anchor desk is garbled and illegible.
  • Includes a random male character in the upper left that wasn't requested.

FLUX.2 [max]

  • + Clean, vibrant digital illustration style with high visual clarity.
  • + The use of the scoreboard and hockey sticks frames the composition well.
  • + Includes a nod to the original attire by keeping the denim shirt on the subject.
  • The facial likeness is significantly less recognizable compared to the source image, looking more like a stock character.
  • The style leans more towards 'modern mobile game cartoon' than a classic 'exaggerated caricature'.
  • Text on the screens and desk is nonsensical.

Verdict: FLUX.2 [dev] is the winner because it successfully creates a recognizable caricature of the woman in the source image, whereas FLUX.2 [max] creates a generic character that looks nothing like her. FLUX.2 [dev] also did a much better job of integrating the humorous 'hockey' element by actually putting the dogs and people in hockey jerseys on a rink.

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 [max]

AI Judge Analysis

FLUX.2 [dev]

  • + Expertly rendered 'god rays' and backlighting that creates a warm, atmospheric glow.
  • + Individual fur strands and whiskers are exceptionally sharp and detailed.
  • + Excellent expressions on the animals that feel emotive and 'wholesome'.
  • Included two rabbits instead of the one requested in the prompt.
  • The animals are sitting relatively still rather than 'playfully chasing' or 'tumbling'.

FLUX.2 [max]

  • + Perfectly captures the 'playfully chasing' and 'tumbling' movement described in the prompt.
  • + Includes exactly one of each animal requested (puppy, kitten, bunny, fox).
  • + Dynamic composition with butterflies scattered throughout the scene.
  • The fox's front paws/legs look slightly anatomically awkward in the mid-air pose.
  • The lighting is slightly flatter and less 'magical' compared to the god rays in the other image.

Verdict: Both models produced high-quality, adorable results, but FLUX.2 [max] is the winner for its superior prompt adherence regarding both the animal count and the active movement of 'chasing and tumbling.' While FLUX.2 [dev] has slightly more impressive cinematic lighting and fur textures, it failed the specific count by adding an extra rabbit and depicted a static scene rather than an active one.

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 [max]

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent character likeness to original meme figures
  • + Accurately recreates the facial expressions of all three subjects
  • + Dreamy flower garden background fits the Ghibli theme well
  • Background diverges significantly from the original city street setting

FLUX.2 [max]

  • + Preserved the original city street background while stylizing it
  • + Warm, nostalgic lighting and color palette
  • + Good paper texture effect helps the hand-painted feel
  • The facial expressions are softened too much, losing the specific 'distracted' and 'indignant' look of the original characters
  • The man's face looks slightly generic compared to the source

Verdict: Both models did an excellent job translating the image into the Studio Ghibli style. FLUX.2 [dev] captures the character expressions and poses with higher fidelity to the original meme, although it replaces the background with flowers. FLUX.2 [max] does a better job of preserving the source environment while applying the requested style, but loses some of the specific facial characterization that makes the original image recognizable.

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 [max]

AI Judge Analysis

FLUX.2 [dev]

  • + Successfully added wind-blown hair effect.
  • + Included numerous small flying leaves throughout the scene.
  • + Maintains excellent consistency with the background and human subjects from the source image.
  • The hair flow lacks a single clear direction, looking more static than wind-swept.
  • Some leaves appear slightly blurred or low-resolution compared to the rest of the image.

FLUX.2 [max]

  • + The hair flow is much more dynamic and directional, creating a stronger sense of movement.
  • + Leaves in the foreground are sharper and more visually integrated.
  • + Excellent preservation of the source image's identity and facial details.
  • Some leaves in the extreme foreground have a slight halo or edge artifact.

Verdict: Both models followed the instructions well, maintaining high fidelity to the source image while adding motion. FLUX.2 [max] is the preferred choice because the hair rendering feels significantly more natural and energetic, and the flying leaves have better clarity and depth compared to FLUX.2 [dev].

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 [max]

AI Judge Analysis

FLUX.2 [dev]

  • + Strong vector emblem style with bold woodcut-inspired shading.
  • + Excellent rendering of text including the specific accent mark on 'Caffè'.
  • + Clean, high-contrast composition that works well for branding.
  • The 'Est. 1720' text is slightly small within the secondary banner.
  • The steam icon is very simplified, looking more like a small flame.

FLUX.2 [max]

  • + Elegant circular composition that is very classic for a restaurant logo.
  • + Superior rendering of the 'steam' effect moving above the cloche.
  • + Great use of the requested warm brown and cream color palette.
  • The 'Est. 1720' banner lacks the complexity of a true vintage design.
  • Typography on 'Caffè Florian' is a bit thinner and less impactful than Model A.

Verdict: Both models followed the prompt exceptionally well, producing high-quality minimalist logos. FLUX.2 [dev] offers a more impactful, bold vector design with great attention to typographic detail, while FLUX.2 [max] provides a more delicate and balanced circular layout with a better depiction of steam.

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 [max]

AI Judge Analysis

FLUX.2 [dev]

  • + Includes all specific icons requested in the prompt including the Saturn V and Lunar Module.
  • + Captures a very clean, modern aesthetic with high-quality vector-style illustrations.
  • + Successfully renders names of the crew members in a separate call-out box.
  • The layout for the steps is disordered and doesn't follow a logical sequence.
  • Text rendering on several labels is garbled or contains typos like 'Trarquility' and 'Ualsist Ordit'.

FLUX.2 [max]

  • + The layout is more logical and structured as an infographic with sequential steps.
  • + Excellent text legibility and spelling for all labels.
  • + Uses a consistent flat-vector style with a very professional NASA-inspired muted palette.
  • Repetitive labels (labels 'Earth Orbit' three times) and misses some distinct steps like 'Lunar Orbit'.
  • The icons for the spacecraft are more generic and less detailed than the Saturn V in the competing image.

Verdict: FLUX.2 [max] is the superior infographic because its layout is cohesive and the text is almost entirely legible and correctly spelled, which is essential for this format. While FLUX.2 [dev] features more detailed and attractive individual icons, the random placement of steps and significant spelling errors make it less functional as a poster.

Next steps

Explore each model