Head to head
Esc

Models · slot A

to navigate to pick

FLUX.1 [schnell] FP8 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] FP8

19.0 arena score

#47 of 62 in Text-to-Image

Skill signature · Text-to-Image

FLUX.2 [dev] Flash

27.1 arena score

#5 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.1 [schnell] FP8

0.0%

win rate

Ties

0.0%

FLUX.2 [dev] Flash

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 [schnell] FP8
FLUX.2 [dev] Flash

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Features a highly vibrant and aesthetic color palette.
  • + Excellent lighting and refraction effects within the glass.
  • + The glass object has a unique, artistic geometric design.
  • The 'cube' is a tall rectangular prism rather than a cube.
  • The sphere appears to be floating on an invisible shelf/bisecting plane within the glass.

FLUX.2 [dev] Flash

  • + Perfect adherence to the geometry of a cube.
  • + Realistic texture on the red book with visible spine details.
  • + Naturalistic lighting and realistic glass imperfections (reflections and dust).
  • The sphere is slightly larger than 'small' relative to the cube.
  • The overall tone is slightly more muted compared to the vibrancy of Model A.

Verdict: Both models followed the prompt instructions well, including the specific spatial relationships between objects. FLUX.2 [dev] Flash is the winner for its superior realism and more accurate interpretation of a 'cube', whereas FLUX.1 [schnell] FP8 produced a tall rectangular object and introduced an odd internal dividing line.

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 [dev] Flash

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent handling of wet pavement reflections
  • + Cinematic color grading and lighting
  • + Strong shallow depth of field effect
  • The man is holding the bicycle rather than repairing it
  • Cars in the background are static with no motion blur
  • Rain is not clearly visible

FLUX.2 [dev] Flash

  • + Successfully captures motion blur on passing cars
  • + Shows a clear 'repairing' action with tools on the ground
  • + Visible rain droplets and authentic 'candid' framing
  • Anatomy and tool interaction is a bit messy
  • Bicycle geometry has some inconsistencies
  • The face and hands have slightly exaggerated texture

Verdict: FLUX.2 [dev] Flash followed the technical requirements of the prompt much more closely, specifically capturing the motion blur and the actual act of repairing. While FLUX.1 [schnell] FP8 produced a more polished, cinematic aesthetic, it failed on the specific 'motion blur' and 'repairing' keywords by showing a man simply standing with a bike among static cars.

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 [dev] Flash

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent intensity in the eyes and facial expression
  • + Strong lighting contrast that creates a dramatic mood
  • + High resolution textures on the skin and facial hair
  • Missed the request for hair braids with beads
  • Armor is dark and lacks visible ornate engraving compared to Model B
  • Fails to show bokeh sparks clearly

FLUX.2 [dev] Flash

  • + Perfect adherence to specific details like beaded braids and ornate engravings
  • + Accurate depiction of bokeh sparks and torchlight
  • + Outstanding detail on leather straps and clothing texture
  • Slightly softer facial features compared to the sharpness of Model A
  • Composition is very centered and symmetrical, which can feel less dynamic

Verdict: FLUX.2 [dev] Flash is the clear winner for its superior prompt adherence, successfully incorporating specific elements like the beaded braids, bokeh sparks, and highly detailed ornate armor. While FLUX.1 [schnell] FP8 captures a more intense emotional expression, it failed on several key descriptive requirements 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] FP8
FLUX.2 [dev] Flash

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent structure with detailed menu item lists and corresponding prices
  • + Very clean, professional layout that closely mimics a real physical menu
  • + Matches the requested categories including pizza and mains perfectly
  • Text contains several spelling errors in headers like 'APPTIZERS' and 'ORCETERS'
  • Food photography is a bit repetitive and less realistic in style

FLUX.2 [dev] Flash

  • + High-quality, realistic food photography with vibrant colors
  • + Strong use of bold sans-serif fonts and colorful accents as requested
  • + Better spelling of specific headers like 'APPETIZERS' and 'PIZZA'
  • The 'grid' requested takes up too much space, leaving very little room for actual menu text
  • Nonsensical text at the top and bottom of the page
  • Layout feels more like a flyer than a functional restaurant menu

Verdict: FLUX.1 [schnell] FP8 (Model A) provides a much more functional and realistic menu layout with clear columns for items and prices, despite some minor spelling errors in headers. FLUX.2 [dev] Flash (Model B) has superior image quality and better adherence to the 'vibrant accents' and 'sans-serif' requests, but fails to create a practical design by prioritizing images over the menu content.

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 [dev] Flash

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Features a vivid and colorful palette
  • + Displays good photorealism on the texture of the meat and bun
  • Significant spelling errors including 'LIIMITED' and 'NEEY'
  • Failed to achieve the 'exploded' view, showing a mostly assembled burger
  • Incorrect price and poor text rendering in the starburst

FLUX.2 [dev] Flash

  • + Excellent adherence to the 'exploded' layout with clearly separated components
  • + Accurate and high-quality rendering of all requested text
  • + Perfectly implemented the fiery, glowing effect on the typography and starburst
  • The bottom bun appears slightly thin or flattened compared to the top

Verdict: FLUX.2 [dev] Flash is the clear winner as it followed every instruction in the prompt, including the complex request for an exploded view and specific fiery text effects. In contrast, FLUX.1 [schnell] FP8 failed significantly on the text rendering, with multiple typos and a failure to separate the burger components as requested.

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 [dev] Flash
0% wins 0% ties 100% wins

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent chalk board texture and lighting.
  • + Readable date and primary title.
  • Significant spelling errors throughout the menu items such as 'Traffle', 'Mushnroom', and 'Octopuss'.
  • Hallucinates extra lines of gibberish text and incorrect prices.
  • Fails the 'elegant cursive' requirement for the title.

FLUX.2 [dev] Flash

  • + Exceptional text rendering with near-perfect spelling and handwriting style.
  • + Accurately represents 'elegant cursive' chalk handwriting for the headers.
  • + Maintains high visual realism with smudges and natural variations in chalk pressure.
  • The date is in a print-style sans-serif rather than the requested handwritten style.
  • Minor repetition of the price on the third item.

Verdict: FLUX.2 [dev] Flash is the clear winner as it demonstrates superior text rendering and adherence to specific menu item descriptions. While FLUX.1 [schnell] FP8 struggles with severe spelling hallucinations and formatting issues, FLUX.2 [dev] Flash creates a professional, realistic chalkboard with only minor stylistic deviations.

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 [dev] Flash

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Successfully followed the difficult 'horse on top' prompt instruction
  • + Strong surreal atmosphere and unique composition
  • + Dynamic lighting and high-quality textures
  • Anatomical confusion with the horse heads and bodies merging into the machinery
  • The 'astronaut' is represented more as a box of equipment than a recognizable person

FLUX.2 [dev] Flash

  • + Excellent visual clarity and cinematic lighting
  • + Higher level of background detail with multiple planets and nebulae
  • + Clearer rendering of the astronaut suit
  • Failed the core prompt reversal instruction (the astronaut is riding the horse)
  • Traditional interpretation instead of the requested surreal subversion

Verdict: FLUX.1 [schnell] FP8 is the clear winner for following the complex prompt requirement of having the horse on top, resulting in a truly surreal image. While FLUX.2 [dev] Flash produced a higher quality, more aesthetically pleasing cinematic image, it completely ignored the specific instruction to reverse the typical roles of the horse and rider.

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 [dev] Flash

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent photographic lighting on the capybara's fur
  • + Good text rendering on the hat
  • + Clear depiction of the jacket requested
  • The passenger is holding two phones simultaneously
  • Composition feels less realistic due to the strange side-angle perspective through the door frame
  • Paws are not positioned naturally on the wheel

FLUX.2 [dev] Flash

  • + Perfect adherence to the 'bored expression' prompt for the passenger
  • + Realistic cinematic framing through the windshield
  • + Very high level of detail on the capybara's paws and the vehicle dashboard
  • Minor text artifacts on the driver's hat
  • Slightly less 'yellow' interior lighting than requested

Verdict: FLUX.2 [dev] Flash is the clear winner for its superior composition and emotional accuracy. While FLUX.1 [schnell] FP8 produced a high-quality animal render, it failed on basic human anatomy by giving the passenger two phones and chose a confusing perspective. FLUX.2 [dev] Flash perfectly captured the mundane, bored atmosphere requested in the prompt.

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 [dev] Flash

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Features a bold, high-contrast jack-o-lantern.
  • + Captures the parchment aesthetic for the border.
  • Multiple spelling errors in the scroll banner and event details.
  • Text layout is messy with redundant banners and hallucinated timestamps.
  • Composition feels slightly empty in the lower half.

FLUX.2 [dev] Flash

  • + Excellent text rendering with almost zero spelling errors in the main requested fields.
  • + Beautiful gothic border with thorns and cobwebs that perfectly matches the prompt.
  • + Superior atmosphere and more detailed background with twisted trees.
  • Small minor hallucination on the 'Price' or 'Back' field before the time.
  • The jack-o-lantern is slightly off-center.

Verdict: FLUX.2 [dev] Flash is the clear winner as it followed all instructions including specific text, border elements, and artistic style with high accuracy. While FLUX.1 [schnell] FP8 captured the general mood, it failed significantly on text legibility and included several spelling mistakes.

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 [dev] Flash

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent 3D cartoon stylization with soft textures
  • + Perfectly centered isometric diorama base
  • + Consistent lighting and color palette
  • Failed to render the word 'SUSHI'
  • Text is overlapping and messy
  • Sushi roll in the back has a strange, non-traditional texture

FLUX.2 [dev] Flash

  • + Perfect text rendering of 'JAPAN' and 'SUSHI'
  • + Includes the requested flag icon accurately
  • + Higher realism in the PBR materials for the wood and fish
  • Lighting is slightly harsher compared to the requested 'gentle' style
  • The background is not the 'solid light blue' requested, leaning more towards a medium blue

Verdict: While FLUX.1 [schnell] FP8 captured the 'cartoon' and 'soft' aesthetic beautifully, it failed significantly on the text requirements. FLUX.2 [dev] Flash followed every part of the prompt, including the specific text strings and the flag icon, while providing superior texture quality for the isometric miniature.

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 [dev] Flash

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Saturated and vibrant lighting creates a very joyful mood.
  • + Excellent rendering of soft, backlit fur textures.
  • + Captures the 'god rays' and 'golden sunrise' atmosphere very effectively.
  • Completely failed to include the baby bunny requested in the prompt.
  • Included redundant/ambiguous animals that look like kitten-fox hybrids.
  • Composition feels a bit more cluttered and AI-typical.

FLUX.2 [dev] Flash

  • + Successfully includes all requested animals: puppy, kitten, bunnies, and fox kits.
  • + Clearer, more balanced composition with a distinct foreground and background.
  • + Excellent inclusion of requested 'dew sparkles' on the grass.
  • The kitten's facial expression is a bit stiff compared to the others.
  • Lighting is slightly more muted than the 'vibrant' feel of the first image.

Verdict: While FLUX.1 [schnell] FP8 captured the lighting and 'glow' of the prompt more intensely, it failed to follow the specific instructions regarding the variety of animals. FLUX.2 [dev] Flash is the better overall image because it successfully included every requested animal (including the bunnies which the other model missed) while maintaining high technical quality and beautiful sunrise details like dew sparkles.

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 [dev] Flash

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Successfully captures the warm brown and cream color scheme.
  • Fails significantly on text rendering, spelling the name as 'AFe FLAMILAN'.
  • The cloche looks more like a building dome or a coffee pot top than a restaurant cloche.
  • Layout is cluttered with overlapping text and decorative elements.

FLUX.2 [dev] Flash

  • + Excellent text accuracy, perfectly spelling 'Caffè Florian' and 'Est. 1720'.
  • + Perfectly interprets the 'retro cloche dome' with subtle steam as requested.
  • + Effective use of subtle texture on the background to enhance the vintage feel.
  • The shading on the cloche is slightly heavy for a strictly minimalist vector logo.

Verdict: FLUX.2 [dev] Flash is the clear winner as it followed every instruction, specifically accurately spelling the restaurant name and providing a clear cloche icon. FLUX.1 [schnell] FP8 failed both in its interpretation of the central icon and in basic text generation, resulting in a garbled and messy logo.

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 [dev] Flash

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Strong minimalist vector aesthetic
  • + Excellent adherence to the color palette constraints
  • + Clean layout with a professional, graphic design feel
  • Nonsense text throughout the infographic
  • Icons are overly abstract and don't clearly represent the steps (e.g., Earth and Moon look identical)

FLUX.2 [dev] Flash

  • + Legible and accurate text labels for mission phases
  • + Detailed icons that clearly represent the Saturn V and Lunar Module
  • + Includes creative additions like the crew silhouettes and Tranquillity Base label
  • Composition is cluttered and lacks a clear logical flow
  • Includes significant repetition of terms like 'Lunar Orbit' and 'Descent'
  • The style leans towards illustrative rather than the requested flat-vector infographic style

Verdict: FLUX.1 [schnell] FP8 followed the stylistic 'modern vector' and 'flat' constraints much better than FLUX.2 [dev] Flash, but failed completely on text legibility and icon logic. FLUX.2 [dev] Flash produced a more informative poster with accurate labels and recognizable spacecraft, despite a messy layout and repetitive elements. FLUX.2 [dev] Flash is the winner for providing actual utility and adherence to the mission steps, whereas FLUX.1 [schnell] FP8 is mostly placeholder text.

Next steps

Explore each model