Head to head
Esc

Models · slot A

to navigate to pick

FLUX.1 [schnell] FP8 Black Forest Labs FLUX.2 [flex] Black Forest Labs

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

FLUX.1 [schnell] FP8

19.0 arena score

#46 of 62 in Text-to-Image

Skill signature · Text-to-Image

FLUX.2 [flex]

24.8 arena score

#14 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.1 [schnell] FP8

0%

win rate

Ties

0%

FLUX.2 [flex]

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 [schnell] FP8
FLUX.2 [flex]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent refraction and light play through the glass cube.
  • + High level of photo-realism and sharp textures on the wooden table.
  • + Accurately places the plant behind the glass with realistic distortion.
  • The cube is elongated, looking more like a rectangular prism than a cube.
  • The internal geometry follows a strange 'floating shelf' design rather than a simple hollow cube.

FLUX.2 [flex]

  • + Perfect adherence to the 'cube' geometry.
  • + Cleaner, more matte blue sphere which contrasts well with the glass.
  • + Accurate lighting direction from the left as requested.
  • The plant is visually behind the cube but does not show much interaction/distortion through the glass.
  • The glass edges appear slightly thick and stylized compared to the environment.

Verdict: Both models followed the complex spatial prompt accurately. FLUX.1 [schnell] FP8 produced a more visually stunning and realistic image with impressive light refraction, though it failed to make the object a true cube. FLUX.2 [flex] adhered better to the specific geometric requirement of a cube, but with slightly less sophisticated rendering of the glass material.

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 [schnell] FP8
FLUX.2 [flex]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Strong bokeh effect and vibrant red color on the bicycle.
  • + Good lighting reflections on the wet asphalt.
  • The man is just standing with the bike rather than 'repairing' it.
  • Background cars are perfectly sharp instead of having the requested motion blur.
  • The subject appears somewhat superimposed against the background.

FLUX.2 [flex]

  • + Successfully captures the requested 'repairing' action with a kneeling pose.
  • + Includes visible motion blur on the background vehicles as requested.
  • + Better 'imperfect framing' with the utility pole on the left, enhancing the candid street feel.
  • The transition between the man's hands and the bicycle chain is slightly muddled.
  • The rain is very subtle and mostly visible as streaks against dark backgrounds.

Verdict: FLUX.2 [flex] adhered much better than FLUX.1 [schnell] FP8 to the specific technical requests of the prompt, including the 'repairing' action, the motion blur on cars, and the imperfect candid framing. While Image A is visually striking, it fails to show repair work and ignores the call for motion blur.

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 [schnell] FP8
FLUX.2 [flex]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Intense, realistic skin texture and lifelike eyes
  • + Dramatic lighting that highlights facial structure
  • + Excellent shallow depth of field
  • Missed the request for 'braided' hair, showing only thin strands
  • Scars are very faint compared to the 'battle-worn' prompt

FLUX.2 [flex]

  • + Highly accurate adherence to all prompt details including braids, beads, and visible scars
  • + Superb engraving details on the armor and texture on the leather straps
  • + Effective use of bokeh sparks and torchlight ambience
  • The facial expression is somewhat neutral for a battle-worn character
  • Lighting on the face is a bit flat compared to the metal reflections

Verdict: While FLUX.1 [schnell] FP8 provides a more intense and cinematically lit portrait, FLUX.2 [flex] is the clear winner for prompt adherence. FLUX.2 [flex] successfully incorporated the complex details of the braids, beads, and armor engravings whereas FLUX.1 [schnell] FP8 ignored several key descriptive elements.

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 [schnell] FP8
FLUX.2 [flex]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Clean multi-page layout that looks like a physical menu
  • + Includes all requested sections (Appetizers, Pizza, Mains)
  • + Consistent photography style across the grid
  • Numerous spelling errors in headings ('APPTIZERS', 'PIZZAL', 'SECCER')
  • Text is largely illegible gibberish
  • The word 'MENU' at the top is clipped and poorly placed

FLUX.2 [flex]

  • + Excellent typography with relatively clean, readable text
  • + Stronger adherence to 'minimalist' and 'bold sans-serif' requirements
  • + Better visual hierarchy and use of color blocking for sections
  • Layout is a bit crowded for a single page
  • Includes some duplicate text entries ('Grilled Chicken Bowl')
  • A few minor spelling artifacts in the top header

Verdict: FLUX.2 [flex] is the clear winner as it produces a professional, legible design with high-quality typography and a logical layout. FLUX.1 [schnell] FP8 followed the prompt's layout instructions well but failed significantly on text rendering, producing multiple typos in the large headers and mostly indecipherable body text.

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 [schnell] FP8
FLUX.2 [flex]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Clean layout for the main title
  • + Good photorealism on the burger patty and bun surfaces
  • Multiple spelling errors in 'LIMITED TIME ONLY' and incorrectly stated price (€69 vs €6.99)
  • The burger is largely assembled rather than truly exploded
  • Text lacks the requested 'fiery, glowing effect'

FLUX.2 [flex]

  • + Perfect adherence to text prompts with correct spelling and price
  • + Excellent fiery/glowing effects applied to all text elements as requested
  • + Better interpretation of the 'exploded' concept with visible space between layers
  • Some sauce drips appear slightly gravity-defying or unnatural
  • The lettuce is a bit repetitive in texture

Verdict: FLUX.2 [flex] followed every instruction of the prompt, including the specific fiery text effects and the correct pricing, whereas FLUX.1 [schnell] FP8 failed significantly on text rendering and price accuracy. FLUX.2 [flex] also provided a much more dynamic 'exploded' composition that felt more like a professional 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 [schnell] FP8
FLUX.2 [flex]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Successfully rendered the full date as requested.
  • + Good chalk-like texture on the board surface.
  • Significant spelling errors and word repetitions (e.g., 'Risortto', 'Griffled', 'Octemon').
  • Did not use cursive for the title as specified.
  • Text layout is messy and contains nonsensical filler sentences at the bottom.

FLUX.2 [flex]

  • + Excellent spelling accuracy for both the main items and the additional context text.
  • + Captured the 'elegant cursive' style for the title and menu items perfectly.
  • + Very realistic chalkboard texture with authentic smudges and chalk dust.
  • The pricing for the Risotto ($24) and Octopus ($28) is slightly squashed together compared to the headers.

Verdict: FLUX.2 [flex] far outperformed FLUX.1 [schnell] FP8 by adhering strictly to the handwriting style instructions and maintaining perfect spelling throughout the menu. While FLUX.1 [schnell] FP8 struggled with hallucinations and repetitive text, FLUX.2 [flex] produced a professional, aesthetically pleasing layout that looked like actual chalk.

The Reversed Rodeo

Text-to-Image

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

FLUX.1 [schnell] FP8
FLUX.2 [flex]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent lighting and cinematic depth
  • + High degree of realism in the Earth background
  • Failed to include an astronaut, featuring only horses and mechanical boxes
  • The second horse's neck is awkwardly fused with the machinery

FLUX.2 [flex]

  • + Perfect adherence to the unusual prompt of a horse riding an astronaut
  • + Clear, high-quality rendering of both the astronaut and the horse
  • + Vibrant colors and creative use of space elements like the galaxy and asteroids
  • The astronaut's hands and the horse's legs are a bit tangled at the point of contact

Verdict: FLUX.2 [flex] successfully followed the complex and surreal prompt instruction to have the horse on top of the astronaut, whereas FLUX.1 [schnell] FP8 failed to generate an astronaut at all. FLUX.2 [flex] also provided a more imaginative and colorful space scene with better overall composition.

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 [schnell] FP8
FLUX.2 [flex]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent texture on the capybara's fur.
  • + Consistent lighting between the interior and the blurry NYC background.
  • The woman is holding two phones simultaneously, which is a hallucination.
  • The capybara's hat looks like a toy 'TAXI' sign rather than a professional driver's cap.

FLUX.2 [flex]

  • + Superior prompt adherence with a realistic taxi driver cap and jacket with a name tag.
  • + Perfectly captures the 'bored' expression of the passenger.
  • The anatomy of the capybara's paws on the steering wheel is slightly distorted.
  • A slight lighting mismatch on the capybara's head compared to the interior shadows.

Verdict: FLUX.2 [flex] is the clear winner as it followed all complex prompt instructions, including the specific type of cap and the 'bored' expression of the passenger. FLUX.1 [schnell] FP8 struggled with the passenger's logic, resulting in her strangely holding two phones, and used a more literal, less professional interpretation of the driver's hat.

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 [schnell] FP8
FLUX.2 [flex]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Strong cinematic lighting with a glowing jack-o-lantern effect
  • + Vibrant colors and a sense of depth in the background
  • + Good use of the twisted tree and bat imagery
  • Significant text errors including 'You are invite to a' and 'A ai nigh tof friights'
  • Garbled and misspelled event details at the bottom
  • The border feels more abstract and less like thorns and webs

FLUX.2 [flex]

  • + Excellent typography with perfect spelling in all requested sections
  • + The border accurately features webs, thorns, and skulls as per the 'gothic' vibe
  • + Clear 'dark parchment' texture that captures the vintage aesthetic
  • The jack-o-lantern glow is a bit more muted compared to the first image
  • The trees in the foggy background are slightly less defined

Verdict: While FLUX.1 [schnell] FP8 captures the moody atmosphere and lighting very well, it fails significantly on the text generation, producing several typos and nonsensical labels. FLUX.2 [flex] successfully captures every element of the prompt with perfect spelling and a more authentic vintage parchment feel, making it the superior functional invitation.

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 [schnell] FP8
FLUX.2 [flex]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent 3D miniature styling with high-quality PBR textures.
  • + The isometric diorama base is well-integrated and professionally rendered.
  • + Lighting and shadows create a pleasing depth.
  • The text is misspelled and repeats the word Japan twice incorrectly.
  • Fails to include the word 'SUSHI' in the text overlay.

FLUX.2 [flex]

  • + Text is perfectly accurate and follows the 'JAPAN' then 'SUSHI' instruction.
  • + Includes a clearly defined Japanese flag icon as requested.
  • + Clean composition with distinct, recognizable sushi types.
  • The black text lacks integration with the 3D scene compared to the first model.
  • The background lighting is a bit flat across the diorama.

Verdict: FLUX.2 [flex] is the clear winner because it followed the complex text and icon instructions perfectly, whereas FLUX.1 [schnell] FP8 failed significantly on spelling and text content. While FLUX.1 [schnell] FP8 had slightly more sophisticated material rendering for the sushi itself, the overall prompt adherence of FLUX.2 [flex] makes it the more successful image.

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 [schnell] FP8
FLUX.2 [flex]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent vibrant lighting and warm golden atmosphere
  • + Intricate detail on the butterflies and flower foreground
  • Failed to include the baby bunny
  • Over-generated animals with two kittens and an extra fox/caracal-like creature
  • Anatomical issues with paws blending into each other

FLUX.2 [flex]

  • + Perfect prompt adherence including all four specific animals
  • + Dynamic sense of motion capturing the 'playfully chasing' aspect
  • + Realistic lighting with distinct god rays and dew sparkles on the grass
  • The fox's front right leg has a slightly awkward, elongated anatomy
  • Background trees are a bit blurry compared to the high-detail foreground

Verdict: FLUX.2 [flex] is the clear winner as it successfully included all four requested animals (dog, cat, bunny, and fox) and captured the active 'chasing' motion described in the prompt. FLUX.1 [schnell] FP8 failed on the subject count by omitting the rabbit and adding redundant, anatomically confusing animals, although it had a very pleasant color palette.

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 [schnell] FP8
FLUX.2 [flex]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Successfully captures the requested vintage vector emblem style
  • + High-quality line work and professional layout
  • Major spelling errors in the brand name ('AFe FLAMILAN' instead of 'Caffè Florian')
  • Misinterpreted 'cloche dome' as an architectural dome

FLUX.2 [flex]

  • + Perfect adherence to text prompt with correct spelling and accents
  • + Accurately represents a 'cloche dome' as requested
  • + Clean and minimalist composition
  • Typography on the arched text is slightly uneven
  • A bit more simplistic compared to the specified emblem style

Verdict: FLUX.2 [flex] is the clear winner because it correctly follows the text instructions and accurately interprets the visual elements like the cloche dome. While FLUX.1 [schnell] FP8 has a more sophisticated aesthetic, it failed significantly on the brand name spelling and misinterpreted the main object in the prompt.

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 [schnell] FP8
FLUX.2 [flex]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Adheres strictly to the requested color palette
  • + Contains a large amount of secondary infographic elements
  • Icons do not match the labels (e.g., Saturn V icon is just a circle)
  • Text is mostly gibberish or extremely distorted
  • Composition feels cluttered and disorganized

FLUX.2 [flex]

  • + Excellent icon-to-label accuracy including a recognizable Saturn V and Lunar Module
  • + High-quality typography with legible, relevant text
  • + Clean, professional grid-based layout that follows the 'flat vector' style perfectly
  • Missing the final 6th step (Landing) in the sequence
  • The 'Translunar' icon shows a craft moving away from a moon-like object rather than toward it

Verdict: FLUX.2 [flex] is the clear winner as it produces a professional, legible infographic with accurate iconography that matches its labels. While FLUX.1 [schnell] FP8 captures the palette well, it fails significantly on icon representation and text clarity, resulting in a confusing visual output.

Next steps

Explore each model