Head to head
Esc

Models · slot A

to navigate to pick

FLUX.1 Krea [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 Krea [dev]

18.8 arena score

#48 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 Krea [dev]

0.0%

win rate

Ties

0.0%

FLUX.2 [klein] 9B

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 Krea [dev]
FLUX.2 [klein] 9B

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent internal reflections within the glass cube
  • + Sophisticated studio-like lighting and photo realism
  • + Perfectly captures the request for the plant to be visible through the glass
  • The blue sphere appears quite large relative to the prompt 'small sphere'

FLUX.2 [klein] 9B

  • + Accurate scaling of the 'small' blue sphere
  • + Very natural wood grain and window lighting texture
  • + Strong adherence to the spatial arrangement requested
  • The sphere appears to be floating mid-air inside the cube without physical support
  • The plant behind the glass is somewhat blurred and less distinct

Verdict: Both models followed the prompt instructions perfectly regarding object placement and color. FLUX.1 Krea [dev] produced a more aesthetically pleasing image with superior glass physics and reflections, while FLUX.2 [klein] 9B captured the scale of the sphere better but suffered from a logic error where the sphere appears to float.

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 Krea [dev]
FLUX.2 [klein] 9B

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Successfully captures motion blur from passing cars as requested.
  • + Realistic atmosphere with good 'candid' feel and imperfect framing.
  • + Accurate depiction of wet pavement reflections.
  • The man is just standing with the bike rather than actively repairing it.
  • The bicycle's structure is slightly simplified/warped in the rear frame area.
  • The lighting on the man feels a bit flatter compared to the environment.

FLUX.2 [klein] 9B

  • + Excellent shallow depth of field and bokeh effect.
  • + High level of detail in skin texture and tools, enhancing the realism of the 'repairing' action.
  • + The man's posture more convincingly portrays the act of repairing the bike.
  • Lacks the requested motion blur from passing cars.
  • Framing feels a bit too balanced and professional for the 'imperfect framing' prompt.
  • Presence of an extra hand/arm artifact near the bicycle's crankset.

Verdict: FLUX.1 Krea (dev) adhered better to specific technical prompt requirements like motion blur and imperfect framing, giving it a more authentic 'street photo' vibe. However, FLUX.2 [klein] 9B followed the subject prompt better by showing the man actually repairing the bike with tools, though it suffered from a significant anatomical artifact and missed the motion blur requirement. FLUX.1 Krea (dev) is the winner for its superior overall coherence and atmosphere.

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 Krea [dev]
FLUX.2 [klein] 9B

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent moody lighting and atmospheric depth
  • + Superior engraved metal texture with realistic reflections
  • + More subtle and realistic skin dirt and scarring
  • The braids feel slightly less integrated into the hairstyle
  • The background is very dark, losing some context of the torchlight source

FLUX.2 [klein] 9B

  • + Exceptional detail on the leather straps and underlayer cloth/chainmail
  • + Very clear implementation of the 'braids with beads' prompt
  • + High clarity and sharpness across the entire facial structure
  • The torch in the background looks a bit artificial/clipart-like
  • Skintone and scarring look slightly more 'makeup-like' than natural battle wear

Verdict: Both models followed the prompt exceptionally well, but FLUX.2 [klein] 9B wins on detail adherence, particularly with the textures of the leather straps and the complex braiding. While FLUX.1 Krea (dev) offers a more cinematic and moody lighting profile, FLUX.2 [klein] 9B provides a more comprehensive execution of all technical requirements in the prompt.

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 Krea [dev]
FLUX.2 [klein] 9B

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent professional layout with a vertical grid of high-quality food photography.
  • + Strong typography hierarchy with clear category headers and item pricing.
  • + Clean, minimalist aesthetic that looks like a real-world design piece.
  • Repeats the 'Appetizers' heading twice instead of including a 'Pizza' section header.
  • Text rendering for smaller items contains significant gibberish characters.

FLUX.2 [klein] 9B

  • + Successfully included all requested sections: Appetizers, Pizza, and Mains.
  • + Horizontal image grid provides a very clear visual distinction for categories.
  • + Highly legible prices and bold sans-serif header fonts.
  • The main title contains a spelling error ('Resteurant') and a character merge.
  • The layout feels slightly cramped with overlapping text and images in the center.
  • Includes a price listed as '$0' which is illogical for a menu.

Verdict: FLUX.1 Krea [dev] produces a more polished and professional-looking layout that feels ready for a casual dining environment, though it missed the specific 'Pizza' header category. FLUX.2 [klein] 9B followed the content requirements of the prompt more accurately by including all requested sections, but suffered from poorer spelling in the headline and a slightly cluttered composition. Overall, FLUX.1 Krea [dev] is the winner for its superior visual balance and high-end graphic design 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 Krea [dev]
FLUX.2 [klein] 9B

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent photographic quality and lighting on the burger components
  • + Clean, professional typography for the main title
  • + Good sense of vertical depth in the exploded view
  • Failed to put the price inside a starburst
  • Missed the fiery/glowing effect on the text
  • Includes random AI-generated watermark-like text at the bottom

FLUX.2 [klein] 9B

  • + Perfect adherence to secondary text styles, including the starburst and fiery glowing effects
  • + Highly dynamic composition with sauce droplets and embers suggesting motion
  • + Accurate interpretation of 'fiery background' with consistent lighting across all elements
  • The burger is less 'exploded' than Model A, appearing more as a tilted stack
  • The top bun is slightly less detailed compared to Model A

Verdict: FLUX.2 [klein] 9B is the clear winner as it followed every specific stylistic instruction, including the fiery glow on the text and the price starburst, which FLUX.1 Krea [dev] ignored. While FLUX.1 Krea [dev] produced a slightly more realistic burger, it failed the complex graphic design requirements of the prompt and included messy artifact text at the bottom.

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 Krea [dev]
FLUX.2 [klein] 9B

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent chalk texture on the board surface with realistic smudges.
  • + Captures the cozy café lighting and aesthetic well.
  • Failed significantly on text accuracy, hallucinating 'Gruffle Mushroom' and messy cursive.
  • The handwriting looks more like a digital marker font than authentic chalk strokes.

FLUX.2 [klein] 9B

  • + Perfect adherence to the requested menu items and text content.
  • + Highly realistic chalk texture in the lettering, showing variations in pressure and grain.
  • + Excellent cursive script that remains legible and stylish.
  • Simple lighting compared to the more atmospheric shadows in the other model.
  • Minor typo in the bottom text ('fress' instead of 'fresh').

Verdict: FLUX.2 [klein] 9B followed the prompt instructions near-perfectly, accurately rendering every specific menu item and price with a beautiful cursive chalk style. FLUX.1 Krea [dev] failed to generate the correct text, creating repeated and nonsensical menu items that were difficult to read. FLUX.2 is the clear winner for its superior text rendering and adherence to the prompt details.

The Reversed Rodeo

Text-to-Image

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

FLUX.1 Krea [dev]
FLUX.2 [klein] 9B

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent adherence to the 'cinematic' style with realistic lighting and Earth backdrop
  • + Highly detailed rendering of both the astronaut suit and the horse's musculature
  • + Unique mechanical integration of the horse and spacecraft elements
  • Failed the negative constraint: the astronaut is on top of the horse instead of the 'horse on top' requested
  • The horse's front legs and mechanical torso are anatomically confusing

FLUX.2 [klein] 9B

  • + Vibrant colors and a sense of cosmic scale with multiple celestial bodies
  • + Clear rendering of the astronaut's face through the visor
  • Complete failure to follow the 'horse on top' instruction
  • Included garbled, nonsensical text at the bottom of the image
  • Overly busy composition that lacks the 'cinematic' realism of the competitor

Verdict: Both models failed the specific prompt instruction to place the 'horse on top' of the astronaut, providing traditional riders instead. FLUX.1 Krea [dev] is the superior image due to its more realistic cinematic lighting, better technical execution, and lack of the garbled text seen in FLUX.2 [klein] 9B.

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 Krea [dev]
FLUX.2 [klein] 9B

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent fur texture on the capybara
  • + High quality cinematic lighting
  • + Clear, legible 'TAXI' text on the hat
  • Included an extra passenger in the front seat which contradicts the prompt
  • The capybara only has one paw on the wheel
  • The perspective makes it look like a two-door vehicle or a van rather than a standard NYC sedan

FLUX.2 [klein] 9B

  • + Better perspective for an interior shot
  • + Perfect bored expression on the passenger
  • + Accurate depiction of two front paws on the steering wheel
  • Garbled text on the taxi driver cap
  • The capybara's lighting is slightly inconsistent with the background
  • Capybara scale feels a bit too large for the driver's seat

Verdict: While FLUX.1 Krea [dev] has superior lighting and texture, it failed significantly on prompt adherence by adding an extra woman in the front seat and missing the 'paws on wheel' detail. FLUX.2 [klein] 9B followed the composition and character instructions much more accurately, creating the requested 'normal/bored' dynamic between the passenger and driver.

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 Krea [dev]
FLUX.2 [klein] 9B
0% wins 0% ties 100% wins

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Elegant border design with intricate cobweb corners.
  • + Strong silhouette work on the twisted trees.
  • Several significant spelling errors in the text including 'Pasty' and 'Tright'.
  • Poorly formatted event details at the bottom with garbled text.

FLUX.2 [klein] 9B

  • + Flawless text rendering for both the title and the specific event details.
  • + Excellent atmospheric depth with the moon and foggy backgrounds.
  • + Accurate adherence to all layout instructions including the scroll banner.
  • The thorn border is slightly less intricate than Model A's filigree.

Verdict: FLUX.2 [klein] 9B followed every instruction perfectly, producing clear, error-free text for the title, banner, and specific event details. In contrast, FLUX.1 Krea produced numerous typos and struggled to legibly render the smaller text at the bottom. FLUX.2 is the clear winner for its superior prompt adherence and polish.

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 Krea [dev]
FLUX.2 [klein] 9B

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Perfect adherence to the Japanese flag icon request.
  • + The PBR materials on the salmon and base are highly realistic and aesthetically pleasing.
  • + Excellent execution of the minimalist 3D cartoon style.
  • The text is a bit bubbly and lacks the 'bold' sharp look compared to Model B.

FLUX.2 [klein] 9B

  • + Clear, professional typography for the 'JAPAN' and 'SUSHI' text.
  • + Includes a more complex variety of sushi while maintaining a clean look.
  • + Good wood grain texture on the diorama base.
  • The flag icon is incorrect, appearing as a red, white, and black tricolor instead of the Japanese flag.
  • The lighting is flatter and less 'refined' than the competitor.

Verdict: FLUX.1 Krea [dev] followed the prompt more accurately by providing the correct Japanese flag and capturing the 'refined' PBR aesthetic perfectly. While FLUX.2 [klein] 9B had superior text rendering, its failure to generate the correct national flag for a country-themed prompt makes it less successful overall.

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 Krea [dev]
FLUX.2 [klein] 9B

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent fur texture rendering
  • + Dynamic pose for the jumping kitten
  • + Rich depth of field with realistic foreground blur
  • Missed the baby bunny entirely
  • Includes two kittens instead of one

FLUX.2 [klein] 9B

  • + Beautiful lighting with clear god rays and dew sparkles
  • + Very expressive facial features and poses
  • + Vibrant colors in the wildflower meadow
  • Missed the baby bunny entirely
  • Anatomic issues with the kitten's front paws
  • Fox kit looks slightly less photorealistic compared to the puppy

Verdict: Both models failed to include the baby bunny, a key part of the prompt. FLUX.1 Krea (dev) produces a more coherent and realistic style with superior fur textures, while FLUX.2 [klein] 9B captures the lighting and 'joyful' atmosphere better but suffers from minor anatomical artifacts on the kitten.

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 Krea [dev]
FLUX.2 [klein] 9B

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent vintage illustrative style with fine cross-hatching.
  • + Beautifully textured background that feels aged and authentic.
  • + Integrated composition with a complex ribbon and cloche design.
  • Significant spelling errors in the brand name ('FLANOR’IN' instead of 'Florian').
  • The typography composition is a bit cluttered and hard to read.

FLUX.2 [klein] 9B

  • + Perfect text rendering of 'Caffè Florian' and 'Est. 1720'.
  • + Clean vector-style execution that aligns well with modern logo standards.
  • + Well-balanced composition with a clear focal point.
  • Less 'vintage' character compared to Model A; feels a bit too modern/flat.
  • The steam effect is a bit simplified.

Verdict: FLUX.1 Krea (dev) captures the desired 'vintage' and 'texture' requests much more artistically, but fails significantly on text accuracy. FLUX.2 [klein] 9B provides a highly usable, clean vector logo with perfect typography, making it the more functional choice for a logo design despite being less stylistically rich.

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 Krea [dev]
FLUX.2 [klein] 9B

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent typography for the main title
  • + Clean, minimalist flat vector aesthetic
  • + Strong color palette adherence
  • Nonsensical iconography for steps (e.g., people and astronauts instead of lander)
  • Failed to follow the requested sequential steps or labels
  • Included a bizarre planet with rings that is not Earth or the Moon

FLUX.2 [klein] 9B

  • + Successfully attempted all specific stages of the mission
  • + Included the requested icons like the Saturn V and Lunar Module
  • + Good overall layout for an infographic with labels
  • Several significant spelling errors in labels (e.g., AOILLO, EARDHT, LANDINING)
  • Inconsistent icon scaling and overlapping elements
  • The 'Translural' icon is confusing and lacks the requested arc

Verdict: Both models struggled with the complexity of a multi-step infographic. FLUX.1 Krea produced a more visually polished but factually irrelevant image, failing to include almost all requested icons. FLUX.2 [klein] 9B followed the prompt's logical structure much better and included the correct hardware, but was held back by poor spelling and a slightly cluttered composition.

Next steps

Explore each model