Head to head
Esc

Models · slot A

to navigate to pick

FLUX.2 [klein] 9B Black Forest Labs FLUX1.1 [pro] Black Forest Labs

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

FLUX.2 [klein] 9B

20.6 arena score

#13 of 32 in Image Editing

Skill signature · Image Editing

FLUX1.1 [pro]

18.4 arena score

#50 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.2 [klein] 9B

0.0%

win rate

Ties

0.0%

FLUX1.1 [pro]

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.2 [klein] 9B
FLUX1.1 [pro]
0% wins 0% ties 100% wins

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent adherence to lighting instructions with realistic soft window light from the left.
  • + Highly realistic textures on the wooden table and the book pages.
  • The glass container is more of a rounded vessel than a 'cube'.
  • The sphere appears to be floating without a clear physical anchor, though the prompt didn't specify gravity.

FLUX1.1 [pro]

  • + Perfect geometric representation of a sharp-edged cube.
  • + Superior clarity and color vibrancy of the blue sphere and red book.
  • + Clean composition with very sharp glass edges.
  • The sphere is quite large relative to the cube, making the 'small blue sphere' description less accurate.
  • The lighting is a bit more generic and less dimensional than Model A.

Verdict: Both models followed the complex spatial instructions perfectly. FLUX.2 [klein] 9B followed the lighting and 'small' size descriptor better, producing a more naturalistic result, whereas FLUX1.1 [pro] followed the geometric 'cube' instruction more accurately and provided a cleaner, more stylized aesthetic.

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.2 [klein] 9B
FLUX1.1 [pro]

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent skin texture and realistic age details on the subject
  • + The bicycle anatomy is coherent and he is actively engaged in 'repairing' it
  • + Better lighting and more convincing wet pavement reflections
  • Lacks the requested motion blur on the passing cars
  • The raindrops are visible but look a bit like static noise in some areas

FLUX1.1 [pro]

  • + Strong cinematic atmosphere and color grading
  • + Captures a sense of motion in the background cars
  • The 'repair' action is poorly represented; he is just leaning on a broken-looking bike
  • Major anatomical distortions on the bicycle frame and pedals
  • Subject lacks the requested natural skin texture and looks smoother/waxy

Verdict: FLUX.2 [klein] 9B is the clear winner as it provides a realistic, coherent image where the subject is actually performing the requested action of repairing a bicycle. FLUX1.1 [pro] fails significantly on the technical details of the bicycle and the prompt adherence for 'natural skin texture,' resulting in a more stylized and less believable output despite the nice 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.2 [klein] 9B
FLUX1.1 [pro]

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent depiction of ornate engraved plate armor
  • + Clearly visible braided hair with beads as requested
  • + Better balance of lighting elements including the secondary torchlight
  • The scars look a bit like fresh surface paint rather than healed tissue
  • The face is very symmetrical and slightly lacks the 'battle-worn' character of the second model

FLUX1.1 [pro]

  • + Incredible skin texture with realistic dirt and pores
  • + Remarkable lifelike eyes with complex iris patterns
  • + Stronger cinematic feel and more convincing battle-worn appearance
  • The hair braids and beads are less distinct and partially obscured
  • The ornate engraving on the armor is mostly cropped out or blurred by the depth of field
  • The torchlight effect is less evident on the metal compared to model A

Verdict: FLUX.2 [klein] 9B followed the prompt instructions more literally, providing a clear view of the armor's engravings and the specific braided hair details. However, FLUX1.1 [pro] produced a much more photorealistic and emotive portrait with superior skin textures and lifelike eyes, even though it sacrificed some of the specific armor detail for a shallower depth of field.

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.2 [klein] 9B
FLUX1.1 [pro]

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent utilization of the grid layout for food photos.
  • + Strong, bold typography that creates clear visual hierarchy.
  • + The alignment and spacing of menu items feel professional and organized.
  • Significant text gibberish and overlapping characters in the main header.
  • The food photos lack variety, as three out of four are very similar pizzas.
  • Includes redundant headers such as repeating 'Appetizers' twice.

FLUX1.1 [pro]

  • + Elegant mockup presentation featuring various menu formats and cutlery.
  • + Includes small illustrative icons that add to a modern aesthetic.
  • + Creative use of food photography in a collage-style grid at the bottom.
  • The main text is poorly rendered and difficult to read.
  • Fails to clearly separate sections for 'pizza' and 'mains' as instructed in the prompt.
  • The layout is more of a flyer/mockup than a practical, printable menu design.

Verdict: FLUX.2 [klein] 9B followed the prompt's layout requirements more accurately, providing the specific sections for appetizers, pizza, and mains in a clear grid format, though it struggled with text legibility. FLUX1.1 [pro] produced a more visually artistic mockup with better aesthetics, but it ignored the structural requests for specific sectioning and the text is largely illegible. FLUX.2 is the winner because it actually functions as a layout for the requested components.

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.2 [klein] 9B
FLUX1.1 [pro]

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent typography with a realistic fiery texture that matches the background
  • + Great sense of motion with the burger elements visibly deconstructed and suspended
  • + Perfect adherence to all prompt elements including the starburst and price
  • The burger patties appear slightly more like generic meat slabs than premium gourmet patties

FLUX1.1 [pro]

  • + High visual quality of the burger texture and the background fire
  • + Clean text rendering for the primary titles
  • Failed to include the starburst for the price
  • Repeated the 'MAGIC BURGER' text twice, once as a neon blue sign which wasn't requested
  • The 'exploded' effect is less effective as the main burger remains mostly assembled

Verdict: FLUX.2 [klein] 9B followed the prompt much more accurately, successfully integrating all commercial design elements like the fiery starburst and the exploded deconstruction of the burger. FLUX1.1 [pro] produced a high-quality image but failed on several prompt instructions, such as the starburst price tag and the specific 'fiery glowing' style for all text, instead adding unrequested neon elements.

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.2 [klein] 9B
FLUX1.1 [pro]

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent chalk texture including realistic smear marks and variations in pressure.
  • + Near-perfect spelling for the requested items and additional footer text.
  • + Follows the capitalization prompt for 'TODAY’S SPECIALS' exactly.

FLUX1.1 [pro]

  • + Beautiful warm lighting and depth of field in the café background.
  • + Consistent and elegant cursive handwriting style.
  • + Includes decorative flourishes that match the 'cozy café' aesthetic.
  • Significant spelling errors and hallucinations, such as 'Chipkies', 'Herbss', and 'giluten'.
  • Incorrect pricing and item repetition, listing octopus twice with different costs.
  • Text lacks a realistic chalk texture, looking more like a digital font overlay.

Verdict: FLUX.2 [klein] 9B is the superior choice for this task because it captured the specific texture of chalk on a board, including dust and smudge marks, while maintaining high spelling accuracy. In contrast, FLUX1.1 [pro] produced a more atmospheric background but failed significantly on the text rendering, with multiple spelling errors and illogical price points.

The Reversed Rodeo

Text-to-Image

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

FLUX.2 [klein] 9B
FLUX1.1 [pro]

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent depiction of a galaxy backdrop with diverse celestial bodies.
  • + Very high detail in the astronaut's suit textures and the horse's musculature.
  • + Effective use of depth and cinematic lighting across the scene.
  • Failed the negative constraint; the astronaut is riding the horse, not the horse riding the astronaut.
  • Contains nonsensical AI-generated text at the bottom.

FLUX1.1 [pro]

  • + Dynamic, powerful composition with the horse rearing up.
  • + Vibrant golden lighting that enhances the cinematic feel.
  • + Clean image without unwanted generated text artifacts.
  • Failed the negative constraint; the astronaut is riding the horse instead of 'horse on top'.
  • The setting is more 'cloudy sky over mountains' than deep space.

Verdict: Both models completely failed the specific logic constraint of 'horse on top, not vice versa,' instead opting for the common 'astronaut riding a horse' trope. FLUX.2 [klein] 9B followed the environmental prompt for 'space' better, while FLUX1.1 [pro] provided a more artistic and dynamic composition albeit in an Earth-like atmosphere.

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.2 [klein] 9B
FLUX1.1 [pro]

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent photorealism with sharp textures on the capybara and clothing.
  • + Correctly places the woman in the back seat as per the prompt.
  • + Follows the instruction for front paws on the steering wheel correctly.
  • The woman is sitting on the right side which, based on the capybara's position, suggests she is in the front passenger seat rather than the back seat.
  • Text on the hat is slightly garbled as 'NEW TALA'.

FLUX1.1 [pro]

  • + Strong cinematic lighting and bokeh in the background city lights.
  • + Captures a very calm and expressive face on the capybara.
  • Failed to place the capybara's paws on the steering wheel.
  • The composition is confusing, making the passenger appear as though she is sitting in the center or front of the vehicle rather than the back seat.
  • The woman is looking at the capybara rather than displaying a bored expression focused on her phone.

Verdict: FLUX.2 [klein] 9B is the clear winner as it adheres much more closely to the specific positioning and actions described in the prompt, such as the paws on the steering wheel. While both models struggled slightly with the spatial logic of front vs. back seats, FLUX1.1 [pro] failed several key instructions regarding the capybara's pose and the woman's interaction with her environment.

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.2 [klein] 9B
FLUX1.1 [pro]

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent typography with perfect spelling of all text elements.
  • + Superior visual composition that fills the square frame effectively.
  • + Includes all requested elements like the scroll banner and specific background details.
  • The parchment texture is a bit flat compared to the illustration.

FLUX1.1 [pro]

  • + High-quality atmospheric lighting and a classic spooky aesthetic.
  • + Interesting thorn border execution.
  • Failed significantly on text, including duplicate lines and spelling errors like 'inivted'.
  • The title text 'Halloween Party Party' does not match the prompt instruction.
  • The layout is cramped at the bottom while leaving a large grey margin around the poster.

Verdict: FLUX.2 [klein] 9B followed the prompt with near-perfect accuracy, especially regarding the complex text requirements and the scroll banner. FLUX1.1 [pro] struggled with the typography, resulting in repeated words, spelling mistakes, and a poorly balanced layout that didn't fully utilize the square format.

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.2 [klein] 9B
FLUX1.1 [pro]

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent PBR material rendering on the wooden base and sushi toppings.
  • + Perfectly executed text layout with clear 'JAPAN' and 'SUSHI' titles.
  • + Accurate 45° isometric perspective and diorama style.
  • The flag icon is incorrect, resembling the flag of Yemen rather than Japan.
  • The sushi roll with salmon on top has an awkward, non-traditional structure.

FLUX1.1 [pro]

  • + More variety in sushi types and a more characteristic 'miniature' aesthetic.
  • + Pleasing, soft cartoon lighting that fits the 'soft refined textures' prompt.
  • + Includes a flag icon, though it is merged into a sushi design rather than standalone.
  • Failed to include the specific flag icon requested in the text header.
  • The 'SUSHI' text is very small and lacks the 'large bold' formatting requested.
  • The 'JAPAN' text is slightly off-center to the left.

Verdict: FLUX.2 [klein] 9B followed the text formatting and layout instructions more accurately, providing a cleaner isometric view with superior material textures. FLUX1.1 [pro] created a more charming 3D scene but struggled with the specific text hierarchy and ignored the flag icon at the top, making FLUX.2 [klein] 9B the winner despite its flag 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.2 [klein] 9B
FLUX1.1 [pro]

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent anatomical rendering of all four distinct animals
  • + Highly detailed and vibrant wildflower meadow
  • + Accurate depiction of a fox, puppy, and kitten with individual features
  • Missed the baby bunny requested in the prompt
  • Slightly less 'dreamy' lighting compared to the alternatives

FLUX1.1 [pro]

  • + Beautiful backlighting and whimsical atmosphere
  • + Expressive upward-looking poses that feel very joyful
  • + Soft, ultra-fine fur texture and 'dreamy' bokeh
  • Only included three animals instead of the four requested (no fox)
  • The kitten and bunny look very similar in facial structure

Verdict: Both models failed to include all four animals requested (golden retriever, kitten, bunny, and fox), with FLUX.2 [klein] 9B providing three and FLUX1.1 [pro] also providing three. FLUX.2 [klein] 9B is the better overall image because the animals are more distinct and anatomically accurate, whereas FLUX1.1 [pro] has a very generic 'cute' look where the kitten and bunny share almost identical facial features.

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.2 [klein] 9B
FLUX1.1 [pro]

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Perfect text rendering for 'Caffè Florian' and 'Est. 1720'.
  • + Excellently balanced vector-style composition with clean lines.
  • + Accurate interpretation of 'minimalist' and 'warm brown and cream tones'.
  • The steam element is a bit thick and less elegant than the rest of the logo.

FLUX1.1 [pro]

  • + Beautiful engraving-style texture on the cloche dome.
  • + Sophisticated use of framing and decorative corners.
  • + More delicate and realistic steam representation.
  • Significant spelling error in the main brand name ('Cafeé Fratilian').
  • Text layout is somewhat cluttered compared to the minimalist request.

Verdict: FLUX.2 [klein] 9B followed the prompt instructions much better, particularly regarding text accuracy and the 'minimalist' style. While FLUX1.1 [pro] produced a more intricate and artistic illustration, it failed to spell the brand name correctly and misinterpreted the term 'minimalist' by adding excessive flourishes.

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.2 [klein] 9B
FLUX1.1 [pro]

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Strong adherence to the flat-vector infographic style.
  • + Clear, large-scale icons for each mission step.
  • + Follows the NASA-inspired color palette effectively.
  • Numerous spelling errors in text (e.g., 'AOILLO', 'EARDHT', 'TRANSLURAL').
  • The flow of the steps is confusing and lacks a clear chronological path.

FLUX1.1 [pro]

  • + Excellent layout with a central moon and side-bar logic typical of professional infographics.
  • + Most text is spelled correctly, including the main title 'APOLLO 11'.
  • + Clean, minimalist aesthetic that feels modern and organized.
  • The icons are very small and some are repetitive or don't match the specific step descriptions well.
  • The small supporting text at the bottom and sides becomes illegible gibberish.

Verdict: FLUX1.1 [pro] produced a much more professional and coherent infographic layout, successfully spelling the main title and organizing information logically along the side. While FLUX.2 [klein] 9B captured the vector style well, its frequent spelling errors and disjointed layout make it less effective as a functional graphic.

Next steps

Explore each model