Head to head
Esc

Models · slot A

to navigate to pick

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

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] Turbo

27.9 arena score

#3 of 62 in Text-to-Image

Top 3 in Text-to-Image
Vote tally

Where the votes landed

FLUX.1 [dev]

0.0%

win rate

Ties

0.0%

FLUX.2 [dev] Turbo

100.0%

win rate

0.0% 0.0% ties 100.0%
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] Turbo

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent handling of glass thickness and internal reflections.
  • + High aesthetic quality with vibrant colors.
  • + Clean and modern composition.
  • The sphere appears to be floating unnaturally in the center.
  • The glass cube has internal vertical struts that weren't requested, making it look more like a case.

FLUX.2 [dev] Turbo

  • + Accurately depicts the plant behind the cube visible through the glass.
  • + Realistic object placement with the sphere resting on the bottom of the cube.
  • + Excellent wooden table texture and realistic window lighting.
  • Simple cube geometry compared to Model A's intricate lighting.
  • The sphere is quite small relative to the cube.

Verdict: Both models followed the prompt instructions very well. FLUX.1 [dev] produced a more stylized, clean image with impressive refractive effects, though the sphere's floating position is physically questionable. FLUX.2 [dev] Turbo provided a much more grounded and realistic interpretation, specifically excelling at showing the plant behind the glass as requested.

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] Turbo

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent shallow depth of field and bokeh
  • + Subtle but effective atmosphere with rain highlights
  • + Very realistic leather texture on the jacket
  • The man is holding the handlebars rather than repairing the bike
  • Lacks the requested motion blur from passing cars
  • The composition feels slightly too polished for a 'candid' street photo

FLUX.2 [dev] Turbo

  • + Successfully captures the man actively repairing the bicycle with tools on the ground
  • + Excellent adherence to the 'motion blur from passing cars' prompt
  • + Very realistic skin texture and age details
  • The front wheel of the bicycle is clipping through/sunk into the pavement
  • The focus is quite sharp across most of the frame, missing the requested 50mm shallow depth of field effect
  • Some minor artifacts in the background car shapes

Verdict: FLUX.2 [dev] Turbo followed the complex prompt instructions much better by showing an actual repair in progress and incorporating the motion blur from cars, though it suffers from a clipping error with the front wheel. FLUX.1 [dev] produced a cleaner, more aesthetic image with better depth of field, but the subject is simply standing next to the bike rather than repairing it as requested.

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] Turbo

AI Judge Analysis

FLUX.1 [dev]

  • + Extremely high-quality skin texture and lifelike eyes
  • + Beautiful bokeh and lighting effects on the armor
  • + Very clean and aesthetically pleasing composition
  • Missed specific details like hair beads
  • Skin looks too clean for a 'battle-worn' character, appearing more like freckles than dirt and scars

FLUX.2 [dev] Turbo

  • + Excellent adherence to specific details like hair beads and ornate engraving
  • + Captured the 'battle-worn' aesthetic with realistic scars and dirt
  • + Detailed textures on leather straps and cloth underlayers
  • The visible torch in the background is a bit distracting compared to pure bokeh
  • Slightly less 'lifelike' eye depth compared to Image A

Verdict: FLUX.2 [dev] Turbo followed the prompt much more accurately, including specific elements like hair beads and intricate armor engravings that FLUX.1 [dev] omitted. While FLUX.1 [dev] produced a more striking, high-fashion style portrait, FLUX.2 [dev] Turbo better captured the requested battle-worn atmosphere and technical details of the armor and clothing.

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] Turbo

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent minimalist typography that mimics a realistic restaurant menu layout.
  • + High clarity in text rendering, including headers and price alignments.
  • + Sophisticated use of negative space for a clean, professional look.
  • Missed the 'pizza' header requested in the sections prompt.
  • Foods are scattered decoratively rather than in the requested grid format.

FLUX.2 [dev] Turbo

  • + Successfully followed the instruction for food photos in a grid.
  • + Included all three requested sections: Appetizers, Pizza, and Mains.
  • + Vibrant color palette and accents are more prominent than in the competitor.
  • The pricing scale is wildly inconsistent and unrealistic ($260 for a pizza).
  • The composition feels slightly cluttered and less 'minimalist' than requested.

Verdict: FLUX.1 [dev] produces a much more realistic and professional design with legible typography, though it misses the specific 'grid' and 'pizza section' instructions. FLUX.2 [dev] Turbo adheres better to the structural requirements of the prompt (grid and sections) but suffers from odd pricing logic and a slightly busier aesthetic. FLUX.1 [dev] is preferred for its superior design quality and professional execution.

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] Turbo

AI Judge Analysis

FLUX.1 [dev]

  • + Clean, symmetrical composition
  • + Correct price and secondary message rendering
  • + Nice vertical stacking of ingredients
  • Completely missed the 'MAGIC BURGER' title text
  • Missing the starburst graphic for the price
  • Burger components look repetitive and less 'exploded' than requested

FLUX.2 [dev] Turbo

  • + Excellent prompt adherence including all required text
  • + Dynamic motion capture with flying sauce and embers
  • + Perfectly executed fiery, glowing effect on typography and starburst
  • The price '€6.99' inside the starburst is slightly less sharp than other text elements

Verdict: FLUX.2 [dev] Turbo is the clear winner as it followed every instruction in the prompt, including the complex text requirements and the specific starburst graphic. FLUX.1 [dev] failed to include the primary title 'MAGIC BURGER' and the starburst element, resulting in a much more static and less persuasive 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] Turbo

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent text legibility and accuracy
  • + Clean composition with consistent spacing
  • + Adheres to most specific wording requests
  • The text looks a bit too much like a digital font or vector art rather than real dusty chalk
  • Some minor spelling errors in the bottom footer ('drish', 'aur')

FLUX.2 [dev] Turbo

  • + Highly realistic chalk texture with dusty smudges and varying pressure
  • + Excellent 'handwritten' aesthetic that truly looks like it was drawn on a board
  • + Accurate rendering of the requested date and menu items
  • Slight repetition of the number '9' in the cookie price
  • Wording in the footer was slightly modified from the precise prompt

Verdict: While FLUX.1 [dev] produced very clear text, it feels slightly digital and contains more spelling artifacts in the fine print. FLUX.2 [dev] Turbo captured the 'chalkboard' brief much more effectively, providing authentic texture, dust, and varying stroke weights that feel genuinely handwritten. FLUX.2 [dev] Turbo is the winner for its superior atmospheric realism and better adherence to the requested chalk texture.

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] Turbo

AI Judge Analysis

FLUX.1 [dev]

  • + Clean, cinematic lighting that highlights the forms well.
  • + The horse has a sleek, slightly ethereal look that fits the surreal prompt.
  • Failed the specific positional prompt; the astronaut is on top of the horse.
  • The horse's hind legs and hooves have anatomical issues.

FLUX.2 [dev] Turbo

  • + Excellent level of detail in the space suit and horse's coat texture.
  • + Rich, complex background with planets and nebulae for a cinematic feel.
  • Failed the specific positional prompt; the astronaut is on top of the horse.
  • The reign/bridle physics are slightly incoherent around the astronaut's hand.

Verdict: Both FLUX.1 [dev] and FLUX.2 [dev] Turbo failed the negative constraint/positional logic to place the horse on top of the astronaut, defaulting to the common trope of an astronaut riding a horse. FLUX.2 [dev] Turbo provides a much higher level of detail, complex lighting, and environmental texture, making it the more visually impressive image despite both failing the primary logic test.

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] Turbo

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent fur texture on the capybara
  • + High photographic realism in lighting and depth of field
  • + Accurately represents the requested professional cap expression
  • The passenger is sitting in the front seat instead of the back seat
  • An extra steering wheel is visible on the right side of the car
  • The taxi sign on top is cut off and text is incomplete

FLUX.2 [dev] Turbo

  • + Perfect adherence to the composition, placing the passenger in the back seat
  • + Includes more realistic New York City background elements through the windows
  • + The capybara's paws are well-positioned on the steering wheel
  • The capybara's face is slightly less detailed compared to Model A
  • The text on the taxi sign says 'TAX' instead of 'TAXI'

Verdict: While FLUX.1 [dev] produced a more aesthetically pleasing close-up with better lighting, it failed on several key prompt details including character placement and vehicle interior logic. FLUX.2 [dev] Turbo followed the prompt much more accurately, correctly placing the businesswoman in the back seat and capturing the essence of the New York street scene.

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] Turbo
0% wins 0% ties 100% wins

AI Judge Analysis

FLUX.1 [dev]

  • + Features a beautiful, vibrant glowing center with excellent cinematic lighting.
  • + Clean thorn border that frames the central artwork well.
  • + Good use of vertical space with a stylized jack-o-lantern.
  • Significant text errors including 'Falloween Ranty' and a double time listing.
  • Missed the requirement for a spider web border.
  • The layout feels more like a poster than a cohesive invitation card.

FLUX.2 [dev] Turbo

  • + Perfect text rendering for all requested fields including the title and specific event details.
  • + Accurately includes both webs and thorns in the border as requested.
  • + Excellent 'vintage parchment' texture and atmosphere that fits the gothic theme.
  • The jack-o-lantern's light is slightly more muted compared to the prompt's 'glowing' request.
  • The banner scroll is a bit simple in design.

Verdict: FLUX.2 [dev] Turbo is the clear winner as it followed every instruction, including the complex text requirements and specific border details like spider webs. While FLUX.1 [dev] produced a more vibrant illustration, it failed significantly on the text elements, resulting in a typo-filled title and redundant time information.

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] Turbo

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent soft, cartoonish 3D mini-world aesthetic
  • + Beautiful soft lighting and color grading
  • + Creative integration of cherry blossom-like garnish
  • Text rendering is poor with spelling errors like 'SUSH CATON'
  • The sushi shapes are a bit repetitive and dough-like

FLUX.2 [dev] Turbo

  • + Perfect text rendering for both 'JAPAN' and 'SUSHI'
  • + Highly realistic PBR materials, especially on the salmon and wood texture
  • + Strict adherence to the banner and flag requirements
  • Perspective of the flag icon is slightly skewed compared to the text
  • A bit more literal and less 'cartoon' than requested

Verdict: FLUX.2 [dev] Turbo is the clear winner due to its ability to follow complex text instructions perfectly without spelling errors. While FLUX.1 [dev] captures the 'cartoon miniature' aesthetic slightly better with its soft shapes, its failure to render the requested text correctly makes it less functional for the specific prompt.

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] Turbo

AI Judge Analysis

FLUX.1 [dev]

  • + Bright, warm lighting with a clean, whimsical aesthetic
  • + Captures a joyful and wholesome mood
  • Missed the tabby kitten entirely, providing two dogs instead
  • Style is stylized/3D-animated rather than hyper-photorealistic
  • Pose is static and posed rather than 'tumbling together'

FLUX.2 [dev] Turbo

  • + Excellent adherence to the 'hyper-photorealistic' part of the prompt
  • + Captures all four specific animals (dog, cat, bunny, fox) accurately
  • + Dynamic composition showing animals actually tumbling and interacting
  • + Superb rendering of dew sparkles and golden hour god rays
  • The cat and fox expressions are slightly exaggerated, bordering on cartoonish despite the realistic fur

Verdict: FLUX.2 [dev] Turbo is the clear winner as it followed the complex multi-subject prompt perfectly, delivering all four specific animals in a photorealistic style. FLUX.1 [dev] failed the prompt's core requirements by omitting the kitten and producing a stylized, cartoon-like image instead of the requested realism.

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] Turbo

AI Judge Analysis

FLUX.1 [dev]

  • + Successfully includes the cloche dome with steam
  • + Follows the warm brown and cream color palette palette
  • + Good use of banners for the layout
  • Major spelling errors in the main name ('Flariláan') and 'Restaurant'
  • Hallucinated extra numbers like '11011' and '1941' that clutter the design
  • Typography is a bit heavy and less sophisticated

FLUX.2 [dev] Turbo

  • + Excellent spelling and typography matching the prompt exactly
  • + Superior implementation of the 'subtle texture' on the background and logo
  • + Very clean, professional vector emblem composition
  • The cloche is slightly less minimalist than a flat vector style but still fits the theme

Verdict: FLUX.2 [dev] Turbo is the clear winner as it perfectly follows the text requirements and captures the 'subtle texture' requested in the prompt. FLUX.1 [dev] suffers from significant garbled text and hallucinated numbers that detract from the professional logo 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] Turbo

AI Judge Analysis

FLUX.1 [dev]

  • + Elegant, centered composition that feels like a professional poster design.
  • + Strictly adheres to the requested muted color palette.
  • + Includes consistent flat-vector iconography and a footer section with key terms.
  • The text is largely nonsensical 'lorem ipsum' style gibberish.
  • The diagram logic is abstract and doesn't clearly represent the sequential steps of the mission.

FLUX.2 [dev] Turbo

  • + Excellent text rendering with accurate labels like 'Saturn V', 'Translunar', and 'Armstrong'.
  • + Very clear sequential flow that accurately depicts the mission stages and requested icons.
  • + High information density including crew silhouettes and NASA branding.
  • The layout is a bit cluttered and lacks the professional 'white space' of Image A.
  • The illustrations are more detailed than the 'flat-vector' request, including realistic moon patterns.

Verdict: FLUX.2 [dev] Turbo is the clear winner for its superior text rendering and adherence to the informational requirements of the prompt, correctly labeling every mission stage. While FLUX.1 [dev] produced a more aesthetically pleasing 'modern' layout, its lack of legible English text makes it non-functional as an infographic.

Next steps

Explore each model