Head to head
Esc

Models · slot A

to navigate to pick

FLUX.1 [schnell] FP8 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.1 [schnell] FP8

19.0 arena score

#46 of 62 in Text-to-Image

Skill signature · Text-to-Image

FLUX1.1 [pro]

18.4 arena score

#50 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.1 [schnell] FP8

0%

win rate

Ties

0%

FLUX1.1 [pro]

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
FLUX1.1 [pro]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent handling of light and refractions through the glass
  • + Realistic material texture on the book and table
  • + Natural daylight aesthetic from the left window
  • The glass container is more of a rectangular prism than a cube
  • The blue sphere appears more like a glass marble than a simple sphere

FLUX1.1 [pro]

  • + Perfectly centered composition
  • + Clear adherence to the 'blue sphere' instruction with a solid matte finish
  • + Highly realistic fabric texture on the book cover
  • The glass container is a tall rectangular prism instead of a cube
  • The sphere appears to be levitating without a clear physical support
  • Reflections on the sphere slightly conflict with the lighting on the leaves

Verdict: FLUX.1 [schnell] FP8 produces a more cohesive and natural scene with superior light interaction, particularly how the plant is refracted through the glass. FLUX1.1 [pro] captures the texture of the book and the simplicity of the blue sphere better, but the levitating sphere feels less grounded in reality compared to the shelf-supported one in the other image.

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
FLUX1.1 [pro]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent realism in the man face and skin texture
  • + Strong color saturation on the red bicycle and wet pavement reflections
  • + Follows the 50mm lens and shallow depth of field request accurately
  • Fails to include the motion blur for passing cars
  • Anatomical error where the man's leg appears to merge into the bicycle frame

FLUX1.1 [pro]

  • + Better captures the rainy atmosphere and wet environment
  • + Includes realistic lens effects and bokeh from the city lights
  • + Provides a more believable 'candid street' composition
  • Severe structural failure of the bicycle geometry
  • Hands are poorly formed with blurred finger details
  • The man's posture is unnatural given how he is holding the bike

Verdict: FLUX.1 [schnell] FP8 produces a much cleaner and more realistic human subject with natural skin, whereas FLUX1.1 [pro] struggles significantly with the physics and logic of the bicycle. While FLUX1.1 [pro] captures the requested atmosphere and 'candid' feel better, FLUX.1 [schnell] FP8 is the superior image due to the lack of major structural hallucinations.

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
FLUX1.1 [pro]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Strong implementation of warm torchlight highlights on the face
  • + Ornate engravings on the armor are clear and well-defined
  • + Captures an intense, lifelike expression in the eyes
  • The hair lacks the specific braids and beads requested in the prompt
  • Skin texture appears slightly airbrushed/plastic compared to the other model

FLUX1.1 [pro]

  • + Excellent adherence to the 'braided hair with small beads' detail
  • + Superior grit with realistic dirt, grime, and skin texture
  • + Dynamic bokeh sparks and realistic shallow depth of field
  • Lighting is somewhat cooler than the 'warm torchlight' requested
  • The armor details are slightly less crisp than those in Model A

Verdict: FLUX1.1 [pro] is the overall winner for its superior attention to detail, specifically the braids, beads, and battle-worn skin textures that feel more realistic. While FLUX.1 [schnell] FP8 handles the warm lighting and armor engravings beautifully, it fails to include several key elements of the prompt like the braided hair.

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
FLUX1.1 [pro]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Exhibits a clean, symmetrical grid that follows the minimalist prompt well.
  • + The hierarchy of headers and price listings is very professional and easy to read.
  • + Accurately includes sections for pizza and apps as requested.
  • Several spelling errors in headers (e.g., 'APPTIZERS', 'PIZZAL', 'ORCETERS').
  • The 'MENU' text at the top is partially cut off and incorrectly placed.

FLUX1.1 [pro]

  • + Features more vibrant and realistic food photography.
  • + The composition including cutlery and layered papers creates a nice presentation for a mockup.
  • + Highly legible main 'MENU' and 'APPETIZERS' headers with better spelling accuracy.
  • The grid is less organized than Model A, with images of varying sizes.
  • Includes more gibberish text in the body sections.

Verdict: FLUX.1 [schnell] FP8 offers a superior layout that feels like a functional, minimalist restaurant menu, whereas FLUX1.1 [pro] feels more like a stylistic brand presentation with better photo quality. While FLUX.1 [schnell] FP8 has several small spelling errors, its adherence to the 'grid' and 'professional layout' requirements makes it more useful for design inspiration.

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
FLUX1.1 [pro]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Successfully integrated a starburst element for the price.
  • + Vibrant color palette and good use of floating secondary ingredients.
  • Severe text rendering issues with multiple typos ('LIIMITED', 'NEEY').
  • Incorrect price representation with the large '€69' text.
  • Burger is not 'exploded' as requested, but mostly assembled.

FLUX1.1 [pro]

  • + Excellent text legibility and accuracy for 'MAGIC BURGER' and 'LIMITED TIME ONLY'.
  • + High-quality photorealistic textures on the meat and bun.
  • + Correct price formatting ('€6.99') as requested.
  • Failed to include the 'starburst' for the price.
  • Text effects are neon blue/white rather than the requested 'fiery, glowing' effect.
  • Burger is also mostly assembled rather than 'exploded' into constituent layers.

Verdict: FLUX1.1 [pro] is the clear winner due to its superior text rendering and adherence to the price amount, whereas FLUX.1 [schnell] FP8 produced significant typos and an incorrect price. While FLUX1.1 [pro] missed the starburst and fiery text effects, its overall image quality and professionalism far exceed the messy typography of the other model.

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
FLUX1.1 [pro]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent chalk texture on the individual letters.
  • + Realistic wooden frame and lighting.
  • Weak text coherence with numerous repetitions and spelling errors like 'Risortto' and 'Octemon'.
  • Failed to use cursive for the title as requested.
  • Prices do not match the prompt.

FLUX1.1 [pro]

  • + Successfully applied elegant cursive handwriting for the title.
  • + Much higher text accuracy and legibility throughout the menu.
  • + Better overall composition and cozy café aesthetic with background elements.
  • The pricing for the octopus is an illogical $228.
  • The 'handwriting' looks a bit too much like a consistent digital font compared to the requested varied chalk style.

Verdict: FLUX1.1 [pro] is the clear winner as it followed the complex formatting instructions, including the requirement for a cursive title and specific menu items, with far fewer spelling errors than FLUX.1 [schnell] FP8. While FLUX.1 [schnell] FP8 had more realistic chalk texture, its inability to maintain word coherence resulted in a messy and repetitive board.

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
FLUX1.1 [pro]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Successfully placed the horse on top of the equipment/astronaut element as requested
  • + Clean and cinematic lighting with a clear planetary background
  • + High resolution textures on the horse's fur and mane
  • Anatomy is nonsensical with a second horse head emerging from the back
  • The 'astronaut' is represented as a piece of machinery rather than a person
  • Lower half of the composition feels cut off and confusing

FLUX1.1 [pro]

  • + Excellent lighting and cinematic atmospheric effects
  • + High level of detail in the astronaut suit and horse's hair
  • + Classic heroic composition with good color balance
  • Failed the negative constraint: the astronaut is riding the horse instead of vice versa
  • The 'in space' setting looks more like a cloudy mountain range with a space-themed sky
  • Horse's front leg anatomy is slightly distorted

Verdict: FLUX.1 [schnell] FP8 was the only model to attempt the difficult spatial reasoning of placing the horse on top of the astronaut, though it resulted in a surreal, anatomical mess with two heads. FLUX1.1 [pro] produced a much higher quality and more aesthetically pleasing image, but it completely ignored the core prompt instruction to have the horse riding the astronaut. FLUX.1 [schnell] FP8 wins for prompt adherence despite its visual flaws.

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
FLUX1.1 [pro]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Successfully places both paws on the steering wheel as requested.
  • + The 'TAXI' text on the cap is clear and correctly oriented.
  • + Captures a wider interior shot that clearly shows the yellow car door frame.
  • The woman is holding two phones simultaneously, which is a logical error.
  • The interior layout is a bit cramped and less realistic for a standard taxi.

FLUX1.1 [pro]

  • + Excellent photorealistic lighting and depth of field in the city bokeh.
  • + The woman's expression is very natural and fits the 'bored' prompt well.
  • + The textures on the capybara's fur and the woman's coat are highly detailed.
  • Fails to place the capybara's paws on the steering wheel; they appear to be in its lap.
  • The capybara is positioned in what appears to be the back seat area or a middle bench rather than the driver's seat.

Verdict: FLUX1.1 [pro] produced a much higher quality image in terms of lighting, texture, and realism, but it failed to follow the specific positioning instructions regarding the capybara's paws and driving status. FLUX.1 [schnell] FP8 stuck closer to the prompt's layout requirements, specifically the paws on the wheel, but suffered from a major anatomical/logical error where the woman is holding two phones.

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
FLUX1.1 [pro]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent atmospheric lighting around the central jack-o-lantern
  • + Creative use of a parchment-style border
  • + Captures the vintage gothic aesthetic well through background silhouettes
  • Significant text hallucinations and spelling errors throughout the body text
  • Failed to render the date correctly as specified
  • Text layout is cluttered and difficult to read

FLUX1.1 [pro]

  • + Near-perfect adherence to specific event details like date, time, and location
  • + Highly detailed thorny border and background composition
  • + Clean and readable typography compared to the competitor
  • Repeated the title word 'Party' and duplicated the location/time lines
  • The parchment effect is less obvious, opting for a black background

Verdict: FLUX1.1 [pro] is the clear winner as it successfully rendered almost all specific text details, including the correct date and location, whereas FLUX.1 [schnell] FP8 suffered from heavy hallucinations. While FLUX1.1 [pro] had some repetition issues in the text layout, its visual quality and prompt adherence make it a much more 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
FLUX1.1 [pro]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent high-clarity 3D rendering with soft lighting
  • + Accurate miniature diorama base following the isometric perspective
  • Failed the text generation significantly, repeating 'JAPAN' with errors and missing 'SUSHI'
  • Includes a strange hybrid flag icon merged into the text

FLUX1.1 [pro]

  • + Perfectly followed the text prompt including 'JAPAN' and 'SUSHI'
  • + Variety of well-rendered sushi types that fit the 'cartoon miniature' aesthetic
  • + Precise layout on a raised diorama base
  • Missed the explicit request for a flag icon
  • Contains slightly more garnish than the 'minimal' request specified

Verdict: While FLUX.1 [schnell] captures the 3D 'PBR' material look slightly better, it completely fails the text and flag requirements. FLUX1.1 [pro] adheres much more accurately to the text instructions and captures the playful miniature diorama style without errors.

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
FLUX1.1 [pro]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Includes all four requested animals (dog, cat, rabbit, fox).
  • + Vibrant colors and highly detailed fur textures.
  • + Good use of 'god rays' and warm golden lighting.
  • Anatomy errors including a creature that appears to be a kitten/fox hybrid with three ears.
  • The layout feels slightly cramped with too many subjects in close proximity.

FLUX1.1 [pro]

  • + Superior photographic realism and cleaner composition.
  • + Captures the 'wholesome' and 'joyful' vibe perfectly with expressive faces.
  • + Exquisite handling of backlighting and translucent fur details.
  • Failed to include the fox kit requested in the prompt.
  • Missing the 'chasing' or 'tumbling' action, as animals are mostly sitting still.

Verdict: FLUX.1 [schnell] FP8 followed the prompt more closely by including all four distinct animals, but suffered from significant anatomical defects and overcrowding. FLUX1.1 [pro] produced a much higher quality, more aesthetically pleasing image with better lighting, though it missed the fox kit entirely.

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
FLUX1.1 [pro]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Successfully included the Est. 1720 text clearly.
  • + Captures the warm brown and cream color scheme well.
  • + Emblem shape is balanced and symmetric.
  • Significant spelling errors in the brand name ('AFe FLAMILAN').
  • The steam effect looks more like an architectural flourish or antenna.
  • The typography is messy and overlapping within the banner.

FLUX1.1 [pro]

  • + Exceptional vintage illustration style with fine hatching details.
  • + Realistic steam effect and a well-rendered cloche dome.
  • + High-quality vector aesthetic with a tasteful border and subtle texture.
  • Misspelled the name as 'Cafeé FRATILIAN' instead of 'Caffè Florian'.
  • The typography for the brand name is slightly fragmented.

Verdict: FLUX1.1 [pro] is the winner due to its superior artistic execution, providing a refined vintage illustration with better texture and detail than the competition. While both models struggled with spelling the specific brand name, FLUX.1 [schnell] FP8 produced much more jarring layout errors and a less convincing interpretation of the requested steam and cloche.

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
FLUX1.1 [pro]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Strong layout that clearly communicates a step-by-step process left-to-right.
  • + Adheres strictly to the requested NASA-inspired navy and light gray palette.
  • + Crisp vector-style icons that feel professional and modern.
  • Generated text contains gibberish instead of meaningful supporting information.
  • Confused the specific steps, labeling an airplane-like icon as 'Earth Orbit'.

FLUX1.1 [pro]

  • + Excellent visual balance with a central lunar focal point.
  • + Successfully incorporated the red accent color from the NASA palette onto the rocket and moon markers.
  • + Creative use of a dotted line to show the trajectory through the steps.
  • Numbered steps are repetitive and out of sequence (e.g., repeating '1').
  • Failed to stop at the landing as requested, creating a more generic space poster than a specific timeline.

Verdict: FLUX.1 [schnell] FP8 produced a more logical infographic layout that follows the left-to-right progression requested in the prompt, despite significant text gibberish. FLUX1.1 [pro] created a more aesthetically pleasing and balanced poster, but struggled with the sequential numbering and the specific timeline constraints of the prompt.

Next steps

Explore each model