Head to head
Esc

Models · slot A

to navigate to pick

FLUX.1 [schnell] FP8 Black Forest Labs Stable Diffusion 3.5 Large Stability AI

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

Stable Diffusion 3.5 Large

22.9 arena score

#29 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.1 [schnell] FP8

0%

win rate

Ties

0%

Stable Diffusion 3.5 Large

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
Stable Diffusion 3.5 Large

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent adherence to the spatial arrangement of a red book on top of the cube.
  • + High photorealistic quality with beautiful bokeh and lighting.
  • + Accurately places the plant behind the glass cube.
  • The cube is elongated, looking more like a rectangular prism than a perfect cube.
  • The interior shelf is an added detail not present in the prompt.

Stable Diffusion 3.5 Large

  • + The glass box is closer to a cube shape.
  • + The sphere has a very clean, matte blue texture.
  • Failed the spatial prompt by putting the red book inside the cube instead of on top.
  • The plant is behind the chair/couch rather than directly behind the cube as requested.
  • The lighting is quite harsh rather than 'soft window light'.

Verdict: FLUX.1 [schnell] FP8 correctly follows all spatial instructions, including the specific placement of the red book on top of the cube and the plant behind it. Stable Diffusion 3.5 Large fails on the primary layout by placing the book inside the cube and the sphere on top of the book, which contradicts the prompt's hierarchy.

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
Stable Diffusion 3.5 Large

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent wet pavement reflections that look physically accurate
  • + The red bicycle is rendered with high structural detail
  • + Realistic skin texture and lifelike lighting on the subject
  • Lack of visible rain drops despite the wet surfaces
  • Background cars are static and lack the requested motion blur
  • The framing is very centered and lacks the 'imperfect' candid feel requested

Stable Diffusion 3.5 Large

  • + Successfully captures visible rain falling through the light
  • + Excellent 'imperfect framing' with a wide, candid composition
  • + Skin textures look weathered and age-appropriate
  • The man's foot and some bike components blend into the wet ground
  • Background vehicles lack significant motion blur
  • The subject is quite far from the camera, losing some '50mm' intimacy

Verdict: Stable Diffusion 3.5 Large followed the prompt's stylistic cues better, capturing the visible rain and the 'imperfect' framing of a candid street photo. FLUX.1 [schnell] FP8 produced a cleaner, more detailed primary subject and better reflections, but it missed the atmospheric elements like falling rain and 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
Stable Diffusion 3.5 Large

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Exceptional fine skin texture and lifelike eye details
  • + Intense and high-contrast dramatic orange lighting
  • + Clean, modern digital portrait composition
  • Failed to include the requested hair braids
  • The plate armor is mostly cropped out and lacks ornate engraving detail

Stable Diffusion 3.5 Large

  • + Excellent adherence to technical details like hair braids and ornate armor engravings
  • + Clearly visible scars and dirt consistent with a battle-worn look
  • + Good environmental storytelling with the bokeh sparks and surrounding army
  • Lighting is somewhat flat compared to the dramatic request
  • Skin texture is slightly less realistic than its competitor

Verdict: FLUX.1 [schnell] FP8 produces a more visceral and high-fidelity close-up portrait with stunning eyes, but it misses several key prompt elements like the braids and the specific ornate armor. Stable Diffusion 3.5 Large is the better overall responder, accurately rendering the braided hair, intricate engravings, and battle-worn scars, making it more faithful to the original request.

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
Stable Diffusion 3.5 Large

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent adherence to the 'grid' prompt for both text and images
  • + Clean, professional layout that closely resembles a real printable menu
  • + High resolution for the food photography used within the menu
  • Several spelling errors in header text like 'ORCETERS', 'PIZZAL', and 'APPTIZERS'
  • Food photography is a bit repetitive with mostly circular shapes

Stable Diffusion 3.5 Large

  • + Vibrant food photography with high appetite appeal
  • + Strong execution of bold sans-serif typography for the main title
  • + Creative use of a vertical center column layout
  • Text is largely unintelligible gibberish, especially in the item descriptions
  • The layout feels more like a social media graphic than a functional restaurant menu
  • Header spelling is poor, featuring words like 'MAIMAES' and 'APPTIZRS'

Verdict: FLUX.1 [schnell] FP8 is the winner as it produces a more functional and realistic menu design that adheres to the request for layout sections and a white professional background. While Stable Diffusion 3.5 Large features more vibrant photography, its layout is less practical for a physical menu and the text rendering is significantly less coherent than FLUX.1.

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
Stable Diffusion 3.5 Large

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Crisp and professional food photography style
  • + Followed all text requirements including price and secondary message
  • + Excellent separation of burger components creating a dynamic feel
  • Multiple spelling errors in the secondary text
  • The price in the starburst is incorrect and cut off
  • The lighting on the text is flat white rather than fiery and glowing

Stable Diffusion 3.5 Large

  • + Highly detailed burger textures with realistic melting cheese
  • + Excellent fiery background with cinematic lighting and embers
  • + Strong sense of heat and atmosphere
  • Completely failed to include any of the requested text
  • The burger is not 'exploded' as requested, but mostly assembled
  • The bottom bun appears to be melting into fire rather than suspended

Verdict: FLUX.1 [schnell] FP8 captured the layout of a commercial ad much better, including the 'exploded' view and all required text elements, despite several typos. Stable Diffusion 3.5 Large produced a more visually stunning and atmospheric image with superior textures, but it failed the prompt's core instructions regarding text integration and the specific 'exploded' composition. FLUX.1 is the winner for better following the complex prompt structure.

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
Stable Diffusion 3.5 Large

AI judge analysis unavailable for this challenge.

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
Stable Diffusion 3.5 Large

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Successfully follows the logic of the horse being on top
  • + Clean and sharp visual clarity
  • + Strong cinematic lighting and composition
  • The astronaut is depicted as a piece of equipment or machinery rather than a clear human suit
  • Anatomical strangeness with multiple horse heads and a building in the corner

Stable Diffusion 3.5 Large

  • + Excellent atmospheric rendering of space and nebulae
  • + High level of detail on the astronaut suit
  • Failed the negative constraint; the astronaut is riding the horse
  • Clipped composition with the horse's tail and back leg

Verdict: FLUX.1 [schnell] FP8 is the only model that attempted the complex logical constraint of the horse riding the astronaut, whereas Stable Diffusion 3.5 Large defaulted to the common trope of an astronaut riding a horse. While FLUX.1 has some surreal anatomical glitches, it captures the prompt's paradoxical intent much better than the high-quality but traditional interpretation from Stable Diffusion.

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
Stable Diffusion 3.5 Large

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent adherence to the full prompt, including both the driver and the passenger.
  • + Natural, professional capybara expression with paws correctly placed on the steering wheel.
  • + High-quality rendering of the city background and interior lighting.
  • The passenger appears to be holding two phones for no apparent reason.
  • Minor clipping of the capybara's paw through the steering wheel.

Stable Diffusion 3.5 Large

  • + High level of texture detail in the capybara's fur and clothing.
  • + Vibrant colors and sharp details on the taxi interior.
  • Failed to include the human passenger requested in the prompt.
  • The 'front paws' are floating and not grasping the steering wheel as requested.
  • The capybara's body and legs are anatomically confused, appearing more like human legs in pants.

Verdict: FLUX.1 [schnell] FP8 is the clear winner as it followed all instructions, capturing both the capybara driver and the bored businesswoman passenger in the back seat. Stable Diffusion 3.5 Large failed to include the passenger entirely and struggled with the capybara's anatomy and interaction with the steering wheel.

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
Stable Diffusion 3.5 Large

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Includes all specific event details including Date, Time, and Location.
  • + Clean, centered composition with a high-quality jack-o-lantern.
  • + Captures the moody night sky and twisted tree silhouettes well.
  • Significant spelling errors throughout the banner and details text (e.g., 'Tine', 'Theaches').
  • The border feels more like a fabric frame than gothic webs and thorns.

Stable Diffusion 3.5 Large

  • + Excellent parchment paper aesthetic with torn edges and detailed cobwebs.
  • + High quality illustration of bats, moon, and twisted trees.
  • + Legible banner text and main title.
  • Missing all specific event details (Date, Time, Location) requested in the prompt.
  • The text layout is slightly disorganized at the bottom of the scroll.

Verdict: FLUX.1 [schnell] FP8 followed the prompt's instructions for specific event details much more closely, although it struggled with the spelling of those details. Stable Diffusion 3.5 Large produced a much more visually appealing and thematic 'vintage gothic' illustration with superior textures, but failed to include the required date, time, and location information.

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
Stable Diffusion 3.5 Large

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent adherence to the 'cartoon' and 'soft refined texture' style requirements.
  • + Perfect isometric viewpoint and minimalist diorama base.
  • + Extremely clean and simple composition that matches the requested aesthetic.
  • Failed the text prompt, repeating 'JAPAN' incorrectly as 'JAPAN JADAN' and omitting 'SUSHI'.
  • The flag icon is integrated into the misspelled text rather than being a separate icon or flag.

Stable Diffusion 3.5 Large

  • + Successfully included all requested text ('JAPAN', 'SUSHI') and a flag icon.
  • + Higher level of detail in the sushi textures (rice grains and fish).
  • + Accurate 45-degree isometric angle.
  • Ignored the 'minimal garnish' instruction, adding excessive details like chopsticks, salt bowls, and multiple garnishes.
  • The text placement and presentation (on a card) do not match the 'top-center large bold text' requirement.
  • The scene feels cluttered compared to the 'ultra-clean' request.

Verdict: FLUX.1 [schnell] FP8 perfectly captured the aesthetic style, lighting, and 'cartoon' feel requested, but failed significantly on the text rendering. Stable Diffusion 3.5 Large followed the text instructions more literally but failed the stylistic requirement for a 'minimal' look, creating a cluttered image that ignored the 'solid background' and 'minimal garnish' constraints. FLUX.1 is the preferred choice for its superior composition and style adherence, despite the typographical 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
Stable Diffusion 3.5 Large

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent fur texture and lighting consistency
  • + Vibrant colors and high-quality butterfly renderings
  • + Expressive facial features on the animals
  • Failed to include the baby bunny
  • Generated two kittens and an ambiguous fox/dog hybrid instead of distinct species
  • Anatomical oddity with a small extra animal floating in the bottom right

Stable Diffusion 3.5 Large

  • + Successfully included all four requested species: puppy, kitten, bunny, and fox kit
  • + Captured the sense of movement and 'playfully chasing' much better
  • + Effective use of bokeh, dew sparkles, and golden hour lighting
  • The fox kit in the background is slightly blurry and less detailed
  • Minor artifacts where the puppy's paw meets the grass

Verdict: Stable Diffusion 3.5 Large is the clear winner because it correctly followed the prompt's species list, including the bunny which FLUX.1 [schnell] FP8 missed entirely. Additionally, Stable Diffusion 3.5 Large better captured the 'tumbling' and 'chasing' action, whereas FLUX.1 [schnell] FP8 produced a more static, posed portrait with several anatomical errors.

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
Stable Diffusion 3.5 Large

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Successfully captured a vector emblem style
  • + Clean warm color palette as requested
  • Major spelling errors in the main name ('Afe Flamilan')
  • Incorrect iconography, showing a building dome instead of a food cloche

Stable Diffusion 3.5 Large

  • + Excellent typography with correct spelling of 'Caffè Florian'
  • + Accurate representation of a cloche dome with steam
  • + Beautiful subtle texture and vintage background effects
  • Extra symbol at the bottom feels slightly cluttered

Verdict: Stable Diffusion 3.5 Large followed the prompt much more accurately, correctly depicting a food cloche and spelling the name 'Caffè Florian' perfectly. FLUX.1 [schnell] FP8 failed both on the text requirements and the specific iconography, providing a architectural dome instead of a restaurant-style 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
Stable Diffusion 3.5 Large

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Successfully follows the horizontal infographic timeline structure requested.
  • + Captures the modern flat-vector style with a clean layout and consistent iconography.
  • + Legible main header and color-coded elements following the NASA palette.
  • Nonsense filler text for sub-headers and descriptions.
  • The 'Saturn V' icon is a simple circle rather than a rocket silhouette.

Stable Diffusion 3.5 Large

  • + Excellent detailed illustrations of the Moon and celestial bodies.
  • + Unique artistic style that feels like a vintage technical layout.
  • Fails the style prompt by including a Space Shuttle instead of a Saturn V rocket.
  • Does not follow the 6-step linear process requested in the prompt.
  • Overly cluttered composition that lacks the 'clean, modern' infographic aesthetic requested.

Verdict: FLUX.1 [schnell] FP8 is the clear winner because it correctly follows the structural and stylistic instructions for a step-by-step infographic, maintaining a clean vector look. In contrast, Stable Diffusion 3.5 Large produces an aesthetically pleasing but inaccurate poster that includes a Space Shuttle (anachronistic to Apollo 11) and fails to organize the information into the requested timeline.

Next steps

Explore each model