Head to head
Esc

Models · slot A

to navigate to pick

FLUX.1 [schnell] Black Forest Labs FLUX.2 [dev] Flash fal

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

FLUX.1 [schnell]

18.7 arena score

#48 of 62 in Text-to-Image

Skill signature · Text-to-Image

FLUX.2 [dev] Flash

27.0 arena score

#7 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.1 [schnell]

0%

win rate

Ties

0%

FLUX.2 [dev] Flash

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]
FLUX.2 [dev] Flash

AI Judge Analysis

FLUX.1 [schnell]

  • + Excellent photographic clarity and vibrant colors.
  • + Creative and glass-like reflections on the table surface.
  • Failed the spatial logic by placing a second sphere on top of the book.
  • The sphere inside the cube is floating unnaturally without reason.
  • The glass cube looks more like an open frame than a solid object.

FLUX.2 [dev] Flash

  • + Perfect adherence to all spatial instructions in the prompt.
  • + Realistic glass texture with subtle imperfections like dust and fingerprints.
  • + Sophisticated lighting and convincing shadows underneath the sphere.
  • The green plant behind the cube is slightly less vibrant than in Model A.

Verdict: FLUX.2 [dev] Flash followed the complex spatial instructions perfectly, placing exactly one sphere inside the cube and the book on top. FLUX.1 [schnell] struggled with the logic, adding an extra sphere on top of the book and making the one inside float. FLUX.2 [dev] Flash also captures much more realistic glass physics and textures.

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]
FLUX.2 [dev] Flash

AI Judge Analysis

FLUX.1 [schnell]

  • + Excellent shallow depth of field with realistic bokeh in the background
  • + Great use of reflections on the wet asphalt
  • + The red tones of the vest and bike are vibrant against the cool rain
  • The cars in the background are too static and lack the requested motion blur
  • The mechanical details of the bicycle handlebars are physically impossible
  • The man's hands are mangled and merged with the bicycle frame

FLUX.2 [dev] Flash

  • + Successfully captured the requested motion blur of passing cars
  • + More realistic skin texture and facial details
  • + Accurately represents the 'repairing' aspect with tools and debris on the ground
  • The bicycle frame geometry is slightly distorted near the basket
  • Lower contrast in wet pavement reflections compared to Image A

Verdict: FLUX.2 [dev] Flash is the clear winner for its adherence to complex prompt elements like 'motion blur' and 'repairing', which FLUX.1 [schnell] largely ignored. While FLUX.1 [schnell] has a more cinematic color palette, it suffers from significant anatomical errors in the hands and structurally nonsensical bicycle parts.

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]
FLUX.2 [dev] Flash

AI Judge Analysis

FLUX.1 [schnell]

  • + Extremely high skin texture detail and realistic iris patterns
  • + Intense, cinematic lighting and perspective
  • + Strong emotional expression
  • Missed the request for beads in the hair
  • Armor is only partially visible and less ornate than requested

FLUX.2 [dev] Flash

  • + Excellent adherence to all prompt details including beads, scars, and leather straps
  • + Clear rendering of ornate, engraved plate armor
  • + Beautiful atmospheric bokeh and sparks
  • Facial expression is somewhat static and blank
  • The 'close portrait' is slightly wider than typical extreme close-ups

Verdict: FLUX.1 [schnell] creates a more visceral and high-fidelity facial portrait, but it fails to include several specific prompt requirements like the hair beads. FLUX.2 [dev] Flash captures every requested detail with high accuracy, from the engraved metalwork to the specific textures of the straps and beads, making it a more successful interpretation of 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 [schnell]
FLUX.2 [dev] Flash

AI Judge Analysis

FLUX.1 [schnell]

  • + Strong minimalist aesthetic with plenty of white space.
  • + Accurately represents the requested sections (Appetizers, Pizza, Mains).
  • + Clean typography that aligns with a professional layout.
  • The placeholder text for menu items is distorted and unreadable.
  • Includes a random heading 'ORFEFUS' that wasn't in the prompt.

FLUX.2 [dev] Flash

  • + Successfully incorporates 'vibrant accents' with the colorful border elements.
  • + Photos have better resolution and appear more realistic.
  • + Better adherence to the 'grid' structure for photos.
  • The text has significant spelling errors (e.g., 'CASSUAL', 'RIZLA').
  • The layout feels more cluttered and less 'minimalist' than requested.

Verdict: FLUX.1 [schnell] captures the minimalist professional vibe better with its clean use of white space, although its text rendering is poor. FLUX.2 [dev] Flash follows the 'vibrant accents' instruction more literally and provides higher-quality food photography, but fails significantly on text legibility and brand spelling. FLUX.1 [schnell] is likely the better base for a designer due to its superior composition and minimalist balance.

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]
FLUX.2 [dev] Flash

AI Judge Analysis

FLUX.1 [schnell]

  • + Features high contrast colors and sharp textures on the main burger.
  • + Dynamic background with realistic embers and fire effects.
  • Failed to render the full text correctly, displaying 'AGIC BURGER'.
  • The burger is largely assembled rather than 'exploded' with suspended components as requested.

FLUX.2 [dev] Flash

  • + Perfect adherence to text requirements with fiery, glowing typography.
  • + Expertly captures the 'exploded burger' concept with clear separation of ingredients.
  • + Excellent photographic detail on individual ingredients like the lettuce and tomato.
  • The lighting on the seeds of the top bun is slightly repetitive.

Verdict: FLUX.2 [dev] Flash followed the instructions much more accurately, creating a true exploded view and perfectly rendering all requested text with the specified fiery effect. FLUX.1 [schnell] failed to spell the brand name correctly and produced a mostly intact burger, missing the core concept of the prompt.

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]
FLUX.2 [dev] Flash

AI Judge Analysis

FLUX.1 [schnell]

  • + Clean layout
  • + Accurate date
  • Significant spelling errors and gibberish throughout the menu items
  • The handwriting looks more like a digital marker font than authentic chalk
  • Fails to provide elegant cursive for the title

FLUX.2 [dev] Flash

  • + Exceptional text rendering with perfect spelling for all specific menu items
  • + Highly realistic chalk texture with smudges and natural variations
  • + Successful implementation of cursive for the title and a cohesive handwriting style
  • None notable for this prompt

Verdict: FLUX.2 [dev] Flash significantly outperformed FLUX.1 [schnell] by following all instructions perfectly, including the specific menu items which had zero spelling errors. FLUX.2 [dev] Flash also captured a much more authentic 'chalk' aesthetic compared to the clean, digital-looking output of FLUX.1 [schnell].

The Reversed Rodeo

Text-to-Image

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

FLUX.1 [schnell]
FLUX.2 [dev] Flash

AI Judge Analysis

FLUX.1 [schnell]

  • + Perfectly adhered to the difficult instruction for the horse to be on top of the astronaut.
  • + Excellent cinematic lighting with a dramatic backlighting effect from the planet.
  • + Creative and surreal interpretation of the prompt.
  • The horse appears to have two heads or a strange anatomical merging error.
  • The astronaut's suit is fragmented and lacks structural coherence.

FLUX.2 [dev] Flash

  • + Very high detail in the astronaut suit and horse fur texture.
  • + Coherent and well-balanced composition.
  • + Crisp resolution and clear background elements.
  • Completely failed the negative constraint to put the horse on top.
  • Produces a generic 'astronaut on a horse' image seen in many AI benchmarks.

Verdict: While FLUX.2 [dev] Flash produced a higher quality and more anatomically correct image, it completely ignored the specific instruction to have the horse on top. FLUX.1 [schnell] successfully followed the surreal logic of the prompt, making it the winner for prompt adherence despite the anatomical glitching on the horse.

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]
FLUX.2 [dev] Flash

AI Judge Analysis

FLUX.1 [schnell]

  • + Excellent texture on the capybara's fur
  • + Good cinematic lighting and focus depth
  • + Clear and legible 'TAXI' text on the cap
  • The capybara only has one paw on the wheel instead of both front paws
  • The capybara is looking at the camera rather than the road
  • The capybara's head looks slightly disproportionate to its body

FLUX.2 [dev] Flash

  • + Adhered perfectly to the prompt by having both front paws on the steering wheel
  • + Excellent composition showing both the driver and the passenger through the windshield
  • + Very realistic 'bored' expression on the passenger
  • The text on the taxi driver cap is garbled following a 'TX' logo
  • The lighting is slightly flatter compared to Model A

Verdict: FLUX.2 [dev] Flash is the clear winner for its superior prompt adherence, accurately placing both paws on the steering wheel and capturing the specific 'bored' expression of the passenger. While FLUX.1 [schnell] has slightly better fur textures, it fails the instruction to have both paws on the wheel and the capybara's direct eye contact with the viewer breaks the professional 'driving' immersion.

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]
FLUX.2 [dev] Flash

AI Judge Analysis

FLUX.1 [schnell]

  • + Strong cinematic lighting with a vibrant glowing jack-o-lantern.
  • + Captures the moody night sky and twisted trees well.
  • Several typos and text hallucinations in the details section (e.g., 'firiichts', 'butistigtion').
  • Includes multiple redundant time fields and lacks the thorn/web border requested.

FLUX.2 [dev] Flash

  • + Perfect adherence to the complex border request including both webs and thorns.
  • + Excellent text rendering for the title and the secondary scroll banner.
  • + Better overall composition that feels like a coherent vintage poster.
  • One small garbled word before 'Time' in the details section.
  • The scroll banner is slightly less 'small' than requested, though it looks professional.

Verdict: FLUX.2 [dev] Flash significantly outperforms FLUX.1 [schnell] in every category, particularly in text accuracy and border detailing. While FLUX.1 [schnell] creates a nice glow, its text becomes a repetitive mess of typos and nonsensical fields, whereas FLUX.2 [dev] Flash delivers a clean, usable invitation with the specific gothic elements requested.

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]
FLUX.2 [dev] Flash

AI Judge Analysis

FLUX.1 [schnell]

  • + Excellent ultra-clean aesthetic with professional white and red base
  • + High-clarity text rendering for 'JAPAN'
  • + Perfectly centered and minimal composition
  • Completely missed the secondary text 'SUSHI'
  • The sushi piece itself looks slightly flat and less like a 3D miniature
  • Small red artifacts on the salmon topping

FLUX.2 [dev] Flash

  • + Successfully included all text elements including 'JAPAN' and 'SUSHI'
  • + Superior 3D miniature feel with excellent PBR textures on the wood and wasabi
  • + Dynamic lighting and soft shadows add great depth
  • Background color is a bit saturated compared to the 'light blue' request
  • Slightly less 'ultra-clean' than the flat vector-style diorama of the other model

Verdict: FLUX.2 [dev] Flash is the clear winner for its better adherence to the text requirements, including both requested words and the flag icon. While FLUX.1 [schnell] captures a very clean aesthetic, FLUX.2 [dev] Flash excels in creating realistic PBR materials and a more convincing 3D miniature scene.

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]
FLUX.2 [dev] Flash

AI Judge Analysis

FLUX.1 [schnell]

  • + Successfully captures the warm sunrise lighting and god rays
  • + Vibrant colors and a very clean, high-resolution aesthetic
  • + Expressive facial features on the animals
  • Failed to include a rabbit in the scene
  • One of the cats looks like a hybrid creature rather than a standard kitten
  • Has a slightly more AI-stylized, painterly look rather than hyper-photorealistic

FLUX.2 [dev] Flash

  • + Successfully included all four requested animal types: puppy, kitten, bunny, and fox
  • + Excellent rendering of dew sparkles on the grass
  • + Captures a playful and tumbling dynamic with multiple animals
  • The fox's face appears slightly distorted in the bottom foreground
  • Includes extra animals (two bunnies, two foxes) not specifically requested in the count
  • The butterflies look somewhat pasted onto the image rather than integrated

Verdict: FLUX.2 [dev] Flash is the winner as it adhered to the prompt by including the bunny, which FLUX.1 [schnell] missed entirely. While both models struggled with the 'hyper-photorealistic' constraint, opting for a more whimsical 'greeting card' style, FLUX.2 [dev] Flash better captured the fine details of the dew and the group interaction requested.

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]
FLUX.2 [dev] Flash

AI Judge Analysis

FLUX.1 [schnell]

  • + Clean vector-style execution
  • + Good color coordination with the brown and cream palette
  • Significant spelling errors in the main name ('Cafeé Framilan' instead of 'Caffè Florian')
  • Incorrect year ('7720' instead of '1720')
  • Missing the steam element requested in the prompt

FLUX.2 [dev] Flash

  • + Perfect text rendering for both the name and the date
  • + Accurately includes all prompt elements including steam and the banner
  • + Superior vintage texture and shading on the cloche dome
  • Slightly less 'minimalist' than a flat vector, leaning more towards an illustration

Verdict: FLUX.2 [dev] Flash followed the instructions perfectly, providing accurate text for 'Caffè Florian' and 'Est. 1720' along with the requested steam element. FLUX.1 [schnell] failed significantly on text accuracy, misspelling the brand name as 'Framilan' and getting the date wrong by six thousand years.

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]
FLUX.2 [dev] Flash

AI Judge Analysis

FLUX.1 [schnell]

  • + Elegant, minimalist layout that feels like a polished vector illustration.
  • + Strong adherence to the requested flat-vector style and navy color palette.
  • Text is completely illegible gibberish.
  • The rocket icon looks more like a cartoon spaceship than the Saturn V specified.

FLUX.2 [dev] Flash

  • + Excellent text rendering, correctly naming the crew and mission phases.
  • + Highly accurate icons for the Saturn V and Lunar Module.
  • + Includes all requested steps in a clear logical flow.
  • Less 'flat-vector' in some areas, with more complex shading on the lunar surface and Earth.
  • Contains some redundant labels like 'Descent' and 'Lunar Orbit' appearing twice.

Verdict: FLUX.2 [dev] Flash is the clear winner for its superior ability to handle text and follow the specific technical requirements of the prompt, such as including the correct crew names and mission phases. While FLUX.1 [schnell] creates a more stylish minimalist composition, it fails completely on legibility and technical accuracy.

Next steps

Explore each model