Head to head
Esc

Models · slot A

to navigate to pick

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

24.3 arena score

#19 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.1 [dev]

0%

win rate

Ties

0%

FLUX.2 [dev]

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 [dev]

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent photorealism in the book texture and lighting.
  • + Artistic interpretation of the glass cube with interesting refractions.
  • + Accurate placement of all elements according to the prompt.
  • The sphere appears to be floating mid-air inside the cube without support.
  • The 'cube' geometry is slightly inconsistent in its internal structure.

FLUX.2 [dev]

  • + Natural physics with the sphere resting on the bottom surface.
  • + High clarity in the transparency of the glass cube.
  • + Strong adherence to all spatial requirements and lighting direction.
  • The transition where the plant is seen through the glass is slightly blurry.
  • The wooden table texture is a bit harsher compared to Model A.

Verdict: Both models followed the prompt perfectly, including the lighting and object placement. FLUX.1 [dev] produced a more aesthetically pleasing and high-definition book texture, but FLUX.2 [dev] is the more logical image because the sphere sits realistically on the floor of the cube rather than floating.

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 [dev]

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent shallow depth of field and bokeh
  • + Great atmospheric lighting and reflections on the pavement
  • + Strong color contrast with the red bicycle
  • The man is holding the bicycle rather than repairing it
  • Background car is static with no motion blur as requested
  • Framing is a bit too clean and centered for 'imperfect framing'

FLUX.2 [dev]

  • + Successfully captures 'motion blur from passing cars'
  • + The subject is actively engaged in repairing the bike
  • + Excellent natural skin texture and facial details
  • + Better adherence to the 'imperfect framing' and 'no stylization' requirements
  • The bicycle geometry is slightly messy around the handlebars
  • Lower overall cinematic contrast compared to Model A

Verdict: FLUX.2 [dev] is the clear winner for its superior adherence to the specific 'candid' and 'motion blur' requirements of the prompt. While FLUX.1 [dev] produced a beautiful, clean image, it missed key technical instructions like motion blur and the action of repairing, whereas FLUX.2 [dev] looks like a genuine, unstyled street photograph.

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 [dev]

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent photographic realism in the eyes and skin texture.
  • + Strong use of bokeh sparks and dramatic close-up composition.
  • + High-quality rendering of the lighting on the face.
  • Failed to include prompt requirements like hair beads, scars, and ornate engraving.
  • The character looks more like a fashion model than a 'battle-worn paladin'.
  • Misses the specific leather strap and cloth underlayer details.

FLUX.2 [dev]

  • + Perfect adherence to all prompt details, including scars, hair beads, and engraved armor.
  • + Clearly depicts the 'battle-worn' aesthetic with realistic grime and injuries.
  • + Excellent texture on the leather straps and underlayer materials.
  • Image resolution/sharpness is slightly lower compared to the clarity of Model A.
  • The torch on the left is a bit distracting in a 'close portrait' composition.

Verdict: While FLUX.1 [dev] produced a stunningly realistic face, it ignored almost all specific thematic elements of the prompt. FLUX.2 [dev] followed every instruction perfectly, delivering a character that actually looks like a battle-worn paladin with all the requested accessories and textures.

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 [dev]

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent typography with clean, legible sans-serif fonts
  • + Elegant minimalist white layout that feels professional
  • + High-quality, clean food photography that integrates well with the negative space
  • Missed the 'grid' requirement for food photos
  • Missing a dedicated 'Pizza' section as requested in the prompt

FLUX.2 [dev]

  • + Successfully followed the 'grid' layout requirement for food photos
  • + Includes all requested sections: Appetizers, Pizza, and Mains
  • + Vibrant color accents and high-density content
  • Font choices are slightly distorted and inconsistent
  • Layout feels cluttered compared to Model A
  • Text generation is less coherent with some odd symbols

Verdict: FLUX.1 [dev] produced a much more realistic and professional-looking menu layout with superior typography, though it failed to follow the grid layout instruction. FLUX.2 [dev] followed the prompt more strictly by including a grid and all three sections, but the overall design is less polished and the text quality is lower. FLUX.1 [dev] is the better choice for a usable design starting point.

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 [dev]

AI Judge Analysis

FLUX.1 [dev]

  • + Features a very clean, high-resolution deconstructed burger with excellent macro photography details
  • + The lighting on the ingredients is professional and appetizing
  • + Includes all requested text elements with correct spelling
  • Failed to include the main title 'MAGIC BURGER'
  • The burger looks more stacked than 'exploded' or appearing to have motion
  • Missing the starburst element for the price

FLUX.2 [dev]

  • + Excellent adherence to all layout instructions, including the starburst and all three text lines
  • + Strong sense of motion with sauce droplets and dynamic ingredient positioning
  • + Perfectly executed the 'fiery, glowing effect' for the typography
  • The meat patty texture is slightly less realistic compared to the other model

Verdict: While FLUX.1 [dev] produced a cleaner image from a food photography perspective, it failed significantly on the text and layout requirements. FLUX.2 [dev] followed every detail of the prompt, including the complex text rendering, the starburst shape, and the sense of motion, making it the superior advertisement.

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 [dev]

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent text legibility and accuracy
  • + Perfect fulfillment of the specific menu items and prices requested
  • + Clean and well-framed composition
  • The text looks a bit too much like a digital 'chalk' font rather than authentic hand-writing
  • The blackboard surface lacks realistic chalk dust or smudges

FLUX.2 [dev]

  • + Superb chalk texture with realistic smudges and strokes
  • + Authentic handwritten aesthetic with varying pressure and slant
  • + Beautifully rendered chalkboard background
  • Contains minor text artifacts and smearing on the second item
  • The cursive title is slightly less 'elegant' than the style of the subsequent items

Verdict: FLUX.1 [dev] followed the text prompt more accurately, capturing every word and number correctly, though the result feels somewhat like a digital overlay. FLUX.2 [dev] provides a significantly more realistic and immersive chalkboard texture with convincing handwriting, despite having some minor rendering issues on the middle line. FLUX.2 [dev] is the winner for its superior artistic merit and realistic interpretation of chalk as a medium.

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 [dev]

AI Judge Analysis

FLUX.1 [dev]

  • + Strong cinematic lighting with a blue glow from the planet
  • + Clean, minimalist composition
  • + Detailed rendering of the white space suit and horse's coat
  • Anatomical issues with the horse's legs and hooves
  • Failed the specific negative constraint to have the horse on top of the astronaut

FLUX.2 [dev]

  • + Richly detailed background with nebula and moon
  • + More realistic textures on the horse and space suit
  • + Dynamic sense of motion with the horse's mane and tail
  • Failed the specific negative constraint to have the horse on top of the astronaut
  • Perspective of the horse's shadow on the clouds below is physically inconsistent

Verdict: Both FLUX.1 [dev] and FLUX.2 [dev] failed to follow the unusual prompt instruction to place the horse on top of the astronaut, instead opting for the common interpretation of an astronaut riding a horse. FLUX.2 [dev] is the superior image due to its more complex background, better anatomical accuracy of the horse, and higher level of detail in the textures.

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 [dev]

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent photographic quality and lighting
  • + Captures the bored, nonchalant expression of the passenger perfectly
  • + Very realistic capybara fur and facial detail
  • The passenger is sitting in the front seat beside the driver instead of the back seat
  • The capybara's paws are not fully on the steering wheel as requested

FLUX.2 [dev]

  • + Correctly places the passenger in the back seat as requested
  • + Capybara has both paws on the steering wheel
  • + Good rendering of the businesswoman's bored expression and professional attire
  • The capybara's paws look more like human hands/fingers than animal paws
  • The driver cap design is a bit generic compared to Model A

Verdict: While FLUX.1 [dev] produced a more cinematically beautiful image with higher detail, it failed a crucial spatial instruction by placing the passenger in the front seat. FLUX.2 [dev] followed the prompt more accurately by placing the passenger in the back seat and positioning the capybara's paws correctly on the wheel, despite slightly strange hand morphology.

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 [dev]

AI Judge Analysis

FLUX.1 [dev]

  • + Strong cinematic lighting with a vibrant color contrast between the orange moon and dark foreground.
  • + Includes a complex thorny border that adds to the spooky aesthetic.
  • Failed significantly on text rendering, with errors like 'Lalloween Rantcl' and 'You Tre'.
  • Did not include the spider webs requested in the prompt.
  • Poor layout for an invitation, putting the main title on a small banner instead of at the top.

FLUX.2 [dev]

  • + Perfect adherence to all text requirements, including titles, banner text, and event details.
  • + Excellent visual composition that includes all requested elements like webs, thorns, and twisted trees.
  • + Features a beautiful vintage parchment texture and professional gothic typography.
  • The lighting on the pumpkin is slightly more muted compared to the cinematic glow of the other model.

Verdict: While FLUX.1 [dev] produced a more vibrant illustration, it failed significantly on text accuracy and layout. FLUX.2 [dev] followed every instruction perfectly, including complex text strings and specific border details like spider webs, resulting in a cohesive and usable invitation design.

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 [dev]

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent soft textures and PBR lighting
  • + Stylized miniature aesthetic fits the 'cartoon scene' prompt well
  • + Creative diorama base with cherry blossom accents
  • Text rendering is poor with spelling errors ('SUSH CATON')
  • Incorrect kanji/symbol at the top
  • Less variety in the sushi types shown

FLUX.2 [dev]

  • + Perfect text rendering for both 'JAPAN' and 'SUSHI'
  • + Accurate flag icon and diorama base construction
  • + Great variety of sushi including maki and nigiri
  • Lighting is a bit flat compared to Model A
  • Text is slightly large and crowds the top of the frame
  • Shadows on the diorama base are a bit harsh for 'gentle lighting'

Verdict: Both models followed the technical aspects of the prompt well, but Model B (FLUX.2 [dev]) is the clear winner due to its perfect text rendering and accurate depiction of the requested elements. While Model A (FLUX.1 [dev]) achieved a more pleasing 'soft refined' texture and lighting, its failure to spell 'SUSHI' correctly and the inclusion of gibberish characters makes it less professional.

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 [dev]

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent vibrant lighting and bokeh effect
  • + Cute, consistent character design across the animals
  • Failed to include a kitten and a fox, instead generating two dogs and two fox-rabbit hybrids
  • Highly stylized/cartoony despite the hyper-photorealistic request
  • Animals are posing statically rather than tumbling or chasing

FLUX.2 [dev]

  • + Successfully included all requested animals: retriever, kitten, fox, and bunnies
  • + Achieved a much higher level of photorealism as requested
  • + Beautiful interaction with god rays and dew sparkles on the flowers
  • The animals are largely sitting rather than 'tumbling together' as described in the prompt

Verdict: FLUX.2 [dev] significantly outperformed FLUX.1 [dev] by accurately depicting all four requested animal species with a photorealistic texture, whereas FLUX.1 [dev] produced a set of stylized, cartoon-like characters that did not match the species list. FLUX.2 [dev] also better captured the atmospheric details like dew sparkles and realistic fur rendering.

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 [dev]

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent cloche and steam illustration
  • + Clean composition with a minimalist feel
  • Significant spelling errors in the brand name ('Flarilaan') and category ('Reseaurant')
  • Includes hallucinated numbers like '11011' and '1941' not in the prompt

FLUX.2 [dev]

  • + Perfect spelling of 'Caffè Florian' and 'Est. 1720'
  • + Beautiful vintage paper texture and era-appropriate typography
  • + Stronger adherence to the 'banner' and 'minimalist logo' request
  • The cloche is a bit thicker and less elegant than the one in Model A

Verdict: While FLUX.1 [dev] produced an aesthetically pleasing layout, it failed significantly on text rendering, misspelling the main brand name and adding random numbers. FLUX.2 [dev] followed every instruction perfectly, with correct spelling, excellent vintage texture, and a high-quality vector-emblem aesthetic.

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 [dev]

AI Judge Analysis

FLUX.1 [dev]

  • + Strong composition with a central Saturn V rocket and a logical flow of information.
  • + Clean, minimalist flat-vector aesthetic that perfectly matches the 'modern infographic' request.
  • + Excellent adherence to the specified NASA-inspired color palette.
  • The text is largely gibberish or heavily distorted.
  • The iconography is abstract and doesn't clearly represent the Moon or Earth as requested.

FLUX.2 [dev]

  • + Text rendering is significantly clearer, with legible headers and the names of the astronauts.
  • + The icons are much more detailed and more accurately represent the requested steps of the mission.
  • + Follows the grid-based infographic style well, making it easy to read.
  • Includes several duplicate or extraneous steps (e.g., 'Saturn Icon' vs 'Launch') that create redundancy.
  • The 'Saturn Icon' image contains multiple rockets, which feels like a generation artifact.

Verdict: FLUX.1 [dev] produces a more aesthetically pleasing 'poster' layout with a better color balance, but fails significantly on legibility and specific iconography. FLUX.2 [dev] is much more functional as an infographic, providing readable labels and distinct, recognizable illustrations for each mission stage, despite some minor redundancies and layout clutter.

Next steps

Explore each model