Head to head
Esc

Models · slot A

to navigate to pick

FLUX.1 [dev] Black Forest Labs FLUX.2 [max] Black Forest Labs

Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.

FLUX.1 [dev]

24.6 arena score

#16 of 62 in Text-to-Image

Skill signature · Text-to-Image

FLUX.2 [max]

25.8 arena score

#10 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.1 [dev]

0%

win rate

Ties

0%

FLUX.2 [max]

0%

win rate

Shared challenges 13

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.1 [dev]
FLUX.2 [max]

AI Judge Analysis

FLUX.1 [dev]

  • + Exceptional clarity and photorealistic lighting
  • + Very clean glass material rendering with realistic internal reflections
  • + Perfect adherence to the lighting direction requested
  • The glass object is more of a hollow rectangular prism frame than a solid or standard cube
  • The sphere appears to be floating without a clear point of contact

FLUX.2 [max]

  • + Accurately depicts a standard cube shape using thin glass panes
  • + Includes realistic dust particles and micro-details on the glass surfaces
  • + The sphere has a clear reflection on the bottom surface of the cube
  • The plant behind the cube is quite blurry and less integrated into the background scene
  • The shadow on the table is slightly disconnected from the base of the cube

Verdict: Both models followed the complex spatial instructions perfectly. FLUX.1 [dev] produced a more polished, high-contrast image with beautiful lighting, though the glass structure is a bit non-traditional. FLUX.2 [max] provided a more literal interpretation of the 'glass cube' and included impressive fine details like surface dust, making it feel very grounded in a real environment.

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.1 [dev]
FLUX.2 [max]

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent depiction of a rainy atmosphere with convincing street reflections.
  • + Clean, high-quality rendering of the subject's face and clothing.
  • The man is just standing and holding the bike rather than repairing it.
  • Missing the specific motion blur from passing cars requested in the prompt.

FLUX.2 [max]

  • + Strong adherence to the 'repairing' action with tools on the ground.
  • + Accurately captures the motion blur of passing cars and 'imperfect' candid framing.
  • + The bicycle type (mama-chari style) is culturally authentic to a Japanese street scene.
  • Minor anatomical artifacts where the hands interact with the wheel spokes.
  • The composition is a bit crowded compared to the cleaner look of Model A.

Verdict: While FLUX.1 [dev] produced a cleaner and more aesthetically pleasing portrait, FLUX.1 [max] followed the complex prompt instructions much more accurately. FLUX.1 [max] successfully included the motion blur, the specific act of repairing, and the 'imperfect' candid framing, making it the superior choice for this specific request.

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.1 [dev]
FLUX.2 [max]

AI Judge Analysis

FLUX.1 [dev]

  • + Exceptional eye realism and lifelike gaze
  • + Clean composition with nice bokeh effects
  • Missed several prompt instructions including the hair beads and engraved armor
  • The face looks too clean and 'pretty' for a battle-worn character despite some freckles/dirt

FLUX.2 [max]

  • + Followed all prompt details including the braids with beads and ornate engravings
  • + Excellent texture work on the weathered leather and frayed cloth underlayer
  • + Authentic battle-worn appearance with convincing scars and dirt
  • The lighting on the face is slightly harsher and less cinematic than model A

Verdict: FLUX.2 [max] followed the prompt much more accurately, incorporating the specific request for hair beads, engraved plate armor, and detailed leather textures that FLUX.1 [dev] omitted. While FLUX.1 [dev] produced a stunning face, it failed to capture the 'battle-worn' aesthetic or the specific equipment details requested.

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.1 [dev]
FLUX.2 [max]

AI Judge Analysis

FLUX.1 [dev]

  • + Clean, professional minimalist aesthetic with elegant negative space.
  • + High-quality, isolated food photography that matches the 'modern' description.
  • + Strong typographic hierarchy with clear headers and pricing alignment.
  • Missed the 'grid' layout for food photos, opting for a decorative placement.
  • Failed to include a specific section for 'Pizza', grouping items under just Appetizers and Mains.

FLUX.2 [max]

  • + Followed the 'grid' requirement perfectly with a multi-image layout.
  • + Included all three requested sections: Appetizers, Pizza, and Mains.
  • + Utilized vibrant color accents and bold sans-serif fonts as requested.
  • The 'Appetizers' header is confusingly placed above a grid containing mostly pizzas.
  • Layout feels a bit cluttered compared to Model A's cleaner approach.
  • Text rendering on smaller descriptions is slightly less legible.

Verdict: FLUX.2 [max] followed the specific structural requirements of the prompt much better, including the grid format and all three specific menu sections. While FLUX.1 [dev] produced a more sophisticated and truly minimalist design, it ignored the 'pizza' section and 'grid' layout requirements, making Model B the more accurate adherence to the prompt.

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.1 [dev]
FLUX.2 [max]

AI Judge Analysis

FLUX.1 [dev]

  • + Clean and symmetrical composition
  • + High quality food photography rendering
  • + Accurate price and secondary text rendering
  • Completely missed the primary title 'MAGIC BURGER'
  • Lacks a starburst element for the price
  • The 'exploded' effect is a vertical stack rather than dynamic motion

FLUX.2 [max]

  • + Successfully included all requested text elements including 'MAGIC BURGER'
  • + Captures dynamic motion with flying sauce and particles
  • + Correctly implemented the fiery glowing effect on the title and the starburst
  • The starburst for the price is slightly simplistic in design
  • Minor texturing artifacts on the bottom bun texture

Verdict: FLUX.2 [max] is the clear winner as it followed every instruction in the prompt, including all text elements and the starburst requirement. FLUX.1 [dev] failed to include the main product name 'MAGIC BURGER' and presented a static vertical stack instead of the 'dynamic, exploded' motion requested.

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.1 [dev]
FLUX.2 [max]

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent text legibility and accuracy of the specific menu items
  • + High contrast with clean framing
  • + Good adherence to the specific date requested
  • Text looks more like a digital marker or vector font than authentic chalk texture
  • Noticeable typos in the footer text such as 'drish' instead of 'dish'
  • The title is in all-caps print rather than the 'elegant cursive' requested

FLUX.2 [max]

  • + Superb chalk texture with realistic dust, smudges, and pressure variations
  • + Accurately renders the title in an elegant cursive style as requested
  • + Highly cinematic lighting and authentic cafe atmosphere
  • Minor spelling error at the bottom with 'gluten free' running together
  • Slightly less vertical space for the text block compared to Image A

Verdict: FLUX.2 [max] significantly outperforms FLUX.1 [dev] by capturing the authentic texture of chalk on a board, including smudges and realistic variations in strokes. While FLUX.1 [dev] is very legible, it fails the 'elegant cursive' prompt for the title and the text lacks a convincing chalk-like material finish, appearing more like a digital font. FLUX.2 [max] followed the stylistic instructions more closely and provided a much more atmospheric image.

The Reversed Rodeo

Text-to-Image

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

FLUX.1 [dev]
FLUX.2 [max]

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent lighting that makes the astronaut and horse pop against the background
  • + Dynamic pose of the horse suggests movement in space
  • + Clean, high-quality rendering with minimal clutter
  • The horse's anatomy is slightly distorted, particularly in the rear legs
  • Failed the negative constraint; the astronaut is riding the horse

FLUX.2 [max]

  • + Highly detailed environment with a beautiful galaxy and asteroid
  • + Physically plausible lighting for a cinematic space scene
  • + High resolution textures on the space suit and horse fur
  • Anatomical error with an extra leg visible behind the astronaut's leg
  • Failed the negative constraint; the astronaut is riding the horse

Verdict: Both models failed the specific prompt instruction to have the 'horse on top' of the astronaut, instead depicting the standard astronaut-on-horse trope. FLUX.1 [dev] is preferred for its cleaner composition and stronger focus on the subject, whereas FLUX.2 [max] suffered from extra limb artifacts and a somewhat generic arrangement.

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.1 [dev]
FLUX.2 [max]

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent capybara paws correctly placed on the steering wheel.
  • + The passenger is positioned correctly in the passenger seat for this camera angle.
  • + Superior lighting and bokeh effect in the background.
  • The passenger appears to be in the front seat next to the driver rather than the back seat.
  • The taxi sign is visible inside the car roof which is physically impossible.

FLUX.2 [max]

  • + Correctly places the woman in the back seat as requested in the prompt.
  • + Atmospheric 'night shift' lighting with the phone screen glowing on the passenger's face.
  • + Accurate New York taxi driver cap style.
  • Significant anatomical failure with human hands emerging from the capybara's body.
  • The capybara's snout is clipping through the jacket collar.
  • Perspective issues with the steering wheel placement relative to the driver.

Verdict: While FLUX.2 [max] correctly followed the spatial instruction of placing the passenger in the back seat, it suffered from a major anatomical error by rendering human hands on the capybara. FLUX.1 [dev] produced a much higher quality, more coherent image despite placing the passenger in the front seat, making it the preferred choice for its realistic textures and better overall composition.

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.1 [dev]
FLUX.2 [max]

AI Judge Analysis

FLUX.1 [dev]

  • + Strong illustrative style with vibrant high-contrast lighting
  • + Includes all requested elements like thorns and twisted trees in a clean layout
  • Significant text errors including 'Falloween Ranty' and 'You Tre'
  • Failed to include 'Halloween Party Invitation' as a title, placing corrupted text in a banner instead
  • Repetitive time entry '7pm, 7pm'

FLUX.2 [max]

  • + Perfect text rendering for all requested details including the complex title and date
  • + Excellent cinematic atmosphere with a realistic parchment texture and moody lighting
  • + Accurately followed all layout instructions including the scroll banner and bottom details
  • The thorns in the border are slightly less sharp than in Model A

Verdict: FLUX.2 [max] is the clear winner as it successfully rendered every piece of requested text with 100% accuracy, whereas FLUX.1 [dev] suffered from multiple spelling errors and missed the primary title text. FLUX.2 [max] also better captured the 'dark parchment' and 'cinematic' aesthetic, creating a much more professional-looking invitation.

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.1 [dev]
FLUX.2 [max]

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent soft lighting and refined, clay-like textures.
  • + Achieves a high-quality 3D diorama aesthetic with realistic depth of field.
  • Text rendering is poor with 'SUSHI' misspelled as 'SUSH CATON' and extra characters added.
  • Includes extraneous floral elements not mentioned in the prompt.

FLUX.2 [max]

  • + Perfect adherence to text requirements with clean, bold typography.
  • + Stronger isometric 45-degree perspective consistent with typical miniature icon styles.
  • + Higher variety of sushi types on the platter.
  • Lighting is slightly flatter compared to Model A.
  • The background is not purely 'solid' as it has a very subtle gradient.

Verdict: FLUX.2 [max] followed the prompt instructions much more accurately, particularly regarding the text rendering and the specific isometric perspective. While FLUX.1 [dev] produced a more visually pleasing texture with better depth, its failure to correctly spell 'SUSHI' and the inclusion of unwanted graphics makes it the weaker choice for this specific design task.

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.1 [dev]
FLUX.2 [max]

AI Judge Analysis

FLUX.1 [dev]

  • + Features very cute and wholesome expressions
  • + Bright and saturated colors enhance the joyful vibe
  • Failed to include a kitten, instead showing two puppies and two fox/rabbit hybrids
  • Stylistically shifted toward a 3D animation/cartoon look rather than hyper-photorealism
  • Animals are stationary rather than playfully chasing and tumbling

FLUX.2 [max]

  • + Successfully included all four distinct animal types from the prompt
  • + Superior realism in fur textures, lighting, and anatomy
  • + Dynamic composition that accurately captures the 'playfully chasing' and 'tumbling' request
  • The fox's back legs have a slight anatomical blurring in the grass

Verdict: FLUX.2 [max] significantly outperformed FLUX.1 [dev] by adhering to all parts of the prompt, specifically the inclusion of a kitten and the 'hyper-photorealistic' style. While FLUX.1 [dev] produced a cute image, it resembled a stylized 3D render and failed to correctly identify the specific animals requested.

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.1 [dev]
FLUX.2 [max]

AI Judge Analysis

FLUX.1 [dev]

  • + Strong vintage aesthetic with woodblock-style cross-hatching
  • + Good use of warm brown tones for a classic look
  • Failed significantly on text rendering, spelling it 'Caffé Flariláan' and 'RESEAURANT'
  • Includes random numbers like '11011' and '1941' that were not requested

FLUX.2 [max]

  • + Perfect adherence to text, including proper spelling and accent on 'Caffè'
  • + Superior vector emblem style with clean, balanced composition
  • + Accurately rendered all requested elements including the steam and banner
  • The steam is a bit faint compared to the rest of the logo
  • The texture on the background is very subtle, almost unnoticeable

Verdict: FLUX.2 [max] is the clear winner as it followed every instruction perfectly, including complex text rendering with correct spelling and accents. In contrast, FLUX.1 [dev] produced significant typos and added irrelevant numbers, making it unusable as a professional logo 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.1 [dev]
FLUX.2 [max]

AI Judge Analysis

FLUX.1 [dev]

  • + Artistically appealing layout with a central rocket motif and circular flow.
  • + Accurately follows the NASA-inspired color palette.
  • + Includes consistent custom iconography at the bottom.
  • Text consists entirely of gibberish despite clear step names in the prompt.
  • Contains factual inaccuracies like Saturn-like rings on planets.
  • Infographic flow is confusing and non-linear.

FLUX.2 [max]

  • + Excellent text rendering with accurate labels for mission steps and crew names.
  • + Clear, logical step-by-step progression that follows the prompt instructions.
  • + Successfully captures the flat-vector style with professional-looking graphics.
  • Repeats the 'Earth Orbit' label three times over different steps.
  • The 'Saturn V' rocket illustration lacks the correct proportions of the actual vehicle.
  • The crew silhouettes are wearing uniforms that look more like modern military or airline pilots than NASA astronauts.

Verdict: FLUX.2 [max] is the winner because it successfully renders legible, accurate text for the mission steps and crew members, whereas FLUX.1 [dev] produces nonsensical text. While both models struggled with some technical details of the spacecraft, FLUX.2 [max] provides a much more functional and informative infographic layout as requested.

Next steps

Explore each model