Head to head
Esc

Models · slot A

to navigate to pick

FLUX.1 [dev] Black Forest Labs FLUX.2 [klein] 9B 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 [klein] 9B

20.6 arena score

#13 of 32 in Image Editing

Vote tally

Where the votes landed

FLUX.1 [dev]

0%

win rate

Ties

0%

FLUX.2 [klein] 9B

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 [klein] 9B

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent sharp geometric rendering of the glass cube
  • + Vibrant colors and high-end aesthetic appeal
  • + Accurate execution of lighting from the left
  • The sphere is quite large, pushing the limits of 'small' in the prompt
  • Reflections suggest a mirror-like finish rather than pure transparency

FLUX.2 [klein] 9B

  • + Realistic interpretation of a 'small' blue sphere
  • + Exceptional light refraction through the glass onto the table
  • + Very natural-looking wooden table texture and plant placement
  • The cube geometry is slightly rounded and less precise than a geometric cube
  • The sphere appears to be floating without a clear point of contact

Verdict: Both models followed the prompt instructions perfectly, including the specific spatial relationships and lighting. FLUX.1 [dev] produced a more stylized, clean, and graphically pleasing image, while FLUX.2 [klein] 9B achieved a higher degree of photographic realism, particularly in how it handled light refraction on the wooden surface and the scale of the interior object.

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 [klein] 9B

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent depiction of motion blur on the passing vehicle
  • + Very natural skin textures and realistic lighting
  • + Strong adherence to the 'reflections on wet pavement' and atmospheric depth
  • The subject is standing and holding the bike rather than actively repairing it
  • The framing is quite central despite the 'imperfect framing' prompt

FLUX.2 [klein] 9B

  • + Stronger narrative adherence with the subject crouching and using tools to repair the bike
  • + Excellent Japanese street aesthetic and background details
  • + Great textures on the man's hands and face
  • The white car in the background lacks the requested motion blur
  • The background/framing feels slightly too clean and staged for a 'candid' shot

Verdict: Images from both models are high quality, but FLUX.2 [klein] 9B is the winner for better understanding the action of 'repairing' by including tools and a crouching pose. While FLUX.1 [dev] captured the requested motion blur better, FLUX.2 [klein] 9B provided a more compelling and detailed composition that felt truer to the requested scene.

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 [klein] 9B

AI Judge Analysis

FLUX.1 [dev]

  • + Beautiful cinematic lighting and bokeh effects.
  • + Highly detailed iris and skin texture around the eyes.
  • Failed to include the beads in the hair braids.
  • Does not look battle-worn; the 'scars' look more like freckles and the skin is too clean.
  • The armor lacks the ornate engraving requested.

FLUX.2 [klein] 9B

  • + Excellent adherence to all prompt details, including small beads in hair and battle scars.
  • + Superb texture on the leather straps and the engraved plate armor.
  • + Perfect interpretation of the 'battle-worn' aesthetic with dirt and visible wounds.
  • The torch in the background is a bit generic and literal compared to the bokeh in Model A.
  • Lighting is slightly flatter across the face despite the torchlight.

Verdict: While FLUX.1 [dev] produced an aesthetically pleasing portrait, it missed several key descriptive elements like the beads and the ornate engravings. FLUX.2 [klein] 9B followed every detail of the prompt perfectly, delivering a truly battle-worn character with exceptional textures on the leather and metalwork.

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 [klein] 9B

AI Judge Analysis

FLUX.1 [dev]

  • + Elegant and professional layout with good use of white space
  • + High-quality, clean food photography
  • + Clean typography and hierarchy
  • Missed the 'grid' request for food photos
  • Missing a dedicated pizza section mentioned in the prompt
  • Text is largely gibberish

FLUX.2 [klein] 9B

  • + Strong adherence to the 'food photos in grid' requirement
  • + Includes all requested sections: Appetizers, Pizza, and Mains
  • + Bold, modern sans-serif fonts per the prompt
  • Repetitive headings (Appetizers appears twice)
  • Lower quality text rendering with significant artifacts
  • Graphic elements like lines and dollar signs are distorted

Verdict: FLUX.1 [dev] produces a much more aesthetically pleasing and realistic graphic design piece, though it failed to follow the grid layout instruction. FLUX.2 [klein] 9B adhered better to the prompt's structural requirements (grid and sections) but suffered from poor text rendering and repetitive headers. FLUX.1 [dev] is preferred for its professional finish and superior image quality.

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 [klein] 9B

AI Judge Analysis

FLUX.1 [dev]

  • + Successfully renders the price and 'Limited Time Only' text accurately.
  • + Good vertical composition emphasizing the 'exploded' nature of the burger.
  • + Clean, photorealistic textures on the ingredients.
  • Completely failed to include the primary 'MAGIC BURGER' title text.
  • Ignored the 'starburst' requirement for the price.
  • The background is static fire at the bottom rather than an immersive, fiery atmosphere.

FLUX.2 [klein] 9B

  • + Excellent adherence to all text requirements, including 'MAGIC BURGER' and the starburst.
  • + Highly dynamic sense of motion with flying embers and sauce droplets.
  • + Superior integration of the fiery, glowing theme across the text and background.
  • The burger components are less 'exploded' (separated) compared to the other model.
  • Slightly less clarity in the individual layers of the burger.

Verdict: FLUX.2 [klein] 9B is the clear winner as it followed every complex instruction, including multiple levels of text, specific graphic elements like the starburst, and the overall atmospheric tone. Although FLUX.1 [dev] produced a clean exploded view, it failed to render the main title of the advertisement entirely.

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 [klein] 9B

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent layout with centered pricing
  • + Great background depth of field showing a cozy café interior
  • + Highly legible handwriting throughout
  • Text texture looks a bit too clean/vectorized rather than having a dusty chalk feel
  • Contains minor spelling errors in the bottom footer ('drish' and 'ufor')

FLUX.2 [klein] 9B

  • + Superior chalk texture with realistic powdery smudges and eraser marks
  • + Accurately follows the 'elegant cursive' request for the title better than its competitor
  • + Very realistic variation in chalk pressure and opacity
  • One minor spelling error at the bottom ('fress')
  • Text alignment is slightly less balanced compared to the other model

Verdict: Both models demonstrated exceptional text rendering capabilities. FLUX.2 [klein] 9B is the winner due to its superior adherence to the 'chalk texture' and 'elegant cursive' requirements, creating a much more authentic-looking chalkboard with realistic smudges. FLUX.1 [dev] produced a very clean and attractive image, but the text looks slightly more like a digital font than actual chalk on a board.

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 [klein] 9B

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent anatomical rendering of the horse and lighting integration with the planet below.
  • + Clean, cinematic composition without distracting elements.
  • + Accurate interpretation of 'space' with realistic lighting on the astronaut's suit.
  • None notable, though the interpretation is less 'busy' than model B.

FLUX.2 [klein] 9B

  • + Highly detailed space background with multiple planetary bodies and nebulae.
  • + Strong surrealist feel with the inclusion of various floating moons and rings.
  • Failed to suppress nonsensical AI-generated text at the bottom.
  • The astronaut's face inside the visor looks slightly distorted compared to the rest of the image.
  • The background is somewhat cluttered, bordering on chaotic.

Verdict: FLUX.1 [dev] followed the prompt more effectively by delivering a clean, cinematic, and high-quality image without the distracting gibberish text found in the other model. While FLUX.2 [klein] 9B provided a more complex and surreal background, the presence of artifact text and a less cohesive focal point makes FLUX.1 [dev] the superior choice.

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 [klein] 9B

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent photorealism and cinematic lighting
  • + Accurately places the passenger in the back seat as requested
  • + Rendered more detailed and realistic paws for the capybara
  • The passenger's expression looks slightly intense rather than bored
  • The camera angle makes it difficult to see the full taxi interior

FLUX.2 [klein] 9B

  • + Perfectly captures the 'bored' expression of the passenger
  • + Wide-angle composition allows for more context of the city and interior
  • + Excellent rendering of the capybara's fur and the taxi driver cap
  • The passenger is sitting in the front passenger seat instead of the back seat
  • The text on the cap is slightly garbled ('NEW TALA')

Verdict: FLUX.2 [klein] 9B captured the requested atmosphere and character expressions more effectively, especially the businesswoman's bored demeanor. However, FLUX.1 [dev] is the winner for prompt adherence because it correctly placed the passenger in the back seat, whereas FLUX.2 placed her in the front, and FLUX.1 achieved a higher level of photographic realism.

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 [klein] 9B

AI Judge Analysis

FLUX.1 [dev]

  • + Strong stylized illustration style
  • + Vibrant glowing effect on the central jack-o-lantern
  • Failed significantly on text rendering with multiple typos like 'Falloween Rantcj' and 'You Ire'
  • Included repetitive text errors in the event details section
  • The border is thorns only, missing the requested spider webs

FLUX.2 [klein] 9B

  • + Perfect adherence to all text requirements with zero typos
  • + Strong composition that incorporates webs, thorns, trees, and moon effectively
  • + Captures the 'vintage parchment' and 'cinematic lighting' aesthetic perfectly
  • The jack-o-lantern is slightly less 'gothic' and more traditional than Model A's stylized version

Verdict: FLUX.2 [klein] 9B is the clear winner as it followed all complex text instructions perfectly, including the title, banner, and event details. In contrast, FLUX.1 [dev] suffered from significant spelling errors and missed the spider web element requested in the prompt. FLUX.2 [klein] 9B also better balanced the 'vintage gothic' and 'parchment' aesthetic requirements.

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 [klein] 9B

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent soft lighting and high-quality PBR material rendering
  • + Captures the diorama feel with stylized cherry blossoms
  • + Accurate Japanese flag icon
  • Text includes a misspelling ('SUSH CATON')
  • Composition is slightly off-center vertically

FLUX.2 [klein] 9B

  • + Perfect text rendering of 'JAPAN' and 'SUSHI'
  • + Clean 45 degree isometric perspective
  • + Better captures the requested 'bold' text look
  • Incorrect flag icon (resembles Yemen rather than Japan)
  • Materials look more like plastic clay than realistic PBR
  • The wood grain on the base has some texture inconsistencies

Verdict: FLUX.1 [dev] delivers a much more aesthetically pleasing image with superior lighting and materials, whereas FLUX.2 [klein] 9b excels at precise text layout but uses the wrong flag and has a flatter visual style. FLUX.1 [dev] is the better choice for its artistic quality and adherence to the 'realistic PBR' and 'Japan flag' instructions, despite a minor spelling error.

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 [klein] 9B

AI Judge Analysis

FLUX.1 [dev]

  • + Successfully includes four animals as requested.
  • + Very vibrant golden hour lighting and bokeh effect.
  • + Cohesive artistic style across all characters.
  • Fails the 'hyper-photorealistic' instruction, appearing more like a 3D animation or Disney-style illustration.
  • Anatomy is stylized and cartoonish rather than realistic.
  • Missing the tabby kitten; it appears to have generated two dogs and two fox/rabbit hybrids.

FLUX.2 [klein] 9B

  • + Excellent adherence to 'photorealistic' and 'ultra-detailed soft fur' keywords.
  • + Captures the requested 'god rays' and 'dew sparkles' much more effectively.
  • + Animal anatomy and textures (especially the fox and puppy) are highly realistic.
  • Failed to include the bunny, featuring only three of the four requested animals.
  • The kitten's facial expression is slightly unnatural compared to the other animals.

Verdict: FLUX.2 [klein] 9B is the clear winner as it followed the stylistic instruction for a hyper-photorealistic scene, whereas FLUX.1 [dev] produced a cartoonish, CGI-style illustration. Although FLUX.2 [klein] 9B missed the baby bunny, its superior texture rendering, lighting effects, and overall visual quality far surpass the stylized output of FLUX.1 [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.1 [dev]
FLUX.2 [klein] 9B

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent typography style that feels genuinely vintage
  • + Includes subtle texture that adds to the retro feel
  • + Includes all prompt elements like the steam and high-contrast warm tones
  • Significant spelling errors in the brand name ('Flarilaan') and sub-text ('Reseaurant')
  • Includes hallucinatory numbers above the brand name

FLUX.2 [klein] 9B

  • + Perfect text rendering with no spelling errors in 'Caffè Florian' or 'Est. 1720'
  • + Clean vector emblem style with a balanced circular composition
  • + Accurate representation of the cloche dome and steam
  • Minimal texture compared to Model A
  • The shadows on the cloche are slightly simplified

Verdict: While FLUX.1 [dev] captures a more authentic vintage texture and sophisticated font style, it fails significantly on the text spelling for both the brand and supporting text. FLUX.2 [klein] 9B provides a much more usable logo with perfect spelling and a clean, professional vector layout that adheres to all prompt requirements.

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 [klein] 9B

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent adherence to the 'flat-vector' aesthetic with consistent iconography.
  • + Sophisticated, balanced composition that uses a circular flow to represent the mission path.
  • + Perfect implementation of the specific NASA-inspired color palette.
  • Text rendering is largely illegible gibberish.
  • Includes extraneous planetary bodies like Saturn that were not part of the prompt.

FLUX.2 [klein] 9B

  • + Text is much more readable, successfully spelling several key words correctly.
  • + Clearer icons for the lunar module descent and landing phases.
  • + Includes creative silhouettes for the crew members at the bottom.
  • The layout is cluttered and lacks the professional 'infographic' flow of the other model.
  • The background graphics are slightly muddy and less 'crisp' than requested.
  • A few spelling errors like 'AOILLO' and 'LANNDINING'.

Verdict: FLUX.1 [dev] produced a much more visually pleasing and professional vector illustration that perfectly matched the requested creative style, though its text handling was poor. FLUX.2 [klein] 9B followed the content logic better and provided readable labels, but the overall design felt amateurish and cluttered compared to the clean layout of FLUX.1 [dev].

Next steps

Explore each model