Head to head
Esc

Models · slot A

to navigate to pick

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

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

Stable Diffusion 3.5 Large Turbo

10.7 arena score

#61 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.1 [schnell]

0%

win rate

Ties

0%

Stable Diffusion 3.5 Large Turbo

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]
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.1 [schnell]

  • + Successfully placed the red book on top of the cube.
  • + High level of photo-realism and natural lighting.
  • + Accurate glass refraction and reflections including the plant through the glass.
  • Included a second blue sphere on top of the book which was not in the prompt.

Stable Diffusion 3.5 Large Turbo

  • + Strong composition with sharp lines and high contrast.
  • + Good adherence to the color palette requested.
  • Failed to place the red book on top of the cube, putting it inside instead.
  • The blue sphere is inside the book/cube base rather than sitting freely.
  • The lighting looks more synthetic compared to Model A.

Verdict: FLUX.1 [schnell] followed the difficult spatial instructions of placing the book on top and the sphere inside much better than SD 3.5 Large Turbo, which placed the book inside. While FLUX.1 [schnell] hallucinated an extra sphere on top, its overall realism and adherence to the physical layout make it the better generated 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]
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.1 [schnell]

  • + Excellent adherence to aesthetic prompts like light rain, wet pavement reflections, and cinematic lighting.
  • + Realistic skin textures and complex bike mechanics.
  • + Captures the 'candid' and 'street photo' atmosphere perfectly with environmental storytelling.
  • The rear wheel of the bicycle is slightly distorted/elongated.
  • The man's hands on the handlebars are somewhat merged and anatomically unclear.

Stable Diffusion 3.5 Large Turbo

  • + Successfully includes the requested red bicycle and elderly man.
  • + Clearer separation between the foreground subject and background.
  • Failed to render realistic rain, reflections, or motion blur from cars.
  • The bicycle geometry is broken, with the frame missing a top tube and merging into the man.
  • The man's hair and clothes have a plastic, CG-like texture that lacks realism.

Verdict: FLUX.1 [schnell] followed the prompt much more effectively, delivering a moody, cinematic image with realistic wet pavement and atmosphere. Stable Diffusion 3.5 Large Turbo failed on almost every technical and environmental requirement, producing a generic image with significant anatomical and mechanical errors.

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]
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.1 [schnell]

  • + Excellent skin texture with realistic pores, scars, and micro-details
  • + Dramatic lighting that correctly interacts with the facial contours and armor
  • + Very lifelike, intense eyes with clear reflections
  • The braids are somewhat blended into the background hair and less distinct
  • Does not show much of the asked-for leather straps or cloth underlayers

Stable Diffusion 3.5 Large Turbo

  • + Very clearly defined braids and ornate engraving on the plate armor
  • + Good inclusion of 'dirt' (appearing more as dried blood smears) and cloth underlayers
  • + Solid shallow depth of field effect
  • Skin texture appears plastic and smoothed, losing the 'battle-worn' realism
  • Ear anatomy and the hair-to-head transition look slightly unnatural
  • The lighting on the face feels like a digital 'glow' rather than reflections from an actual torchlight source

Verdict: FLUX.1 [schnell] is the superior image due to its incredible textural realism and lifelike character rendering, capturing the soul of a 'battle-worn' warrior. While Stable Diffusion 3.5 Large Turbo followed the prompt's structural elements well (like braids and armor engravings), its output suffers from a waxy, artificial skin finish and less convincing lighting.

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]
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.1 [schnell]

  • + Excellent typography rendering for headers
  • + Clear implementation of a grid layout for food photos
  • + Clean and realistic professional menu aesthetic
  • Small body text is gibberish
  • The 'ORFEFUS' section replaces the requested 'Mains' header

Stable Diffusion 3.5 Large Turbo

  • + Highly vibrant and colorful food photography
  • + Clean layout with dotted line price guides
  • + Good spatial separation between menu cards
  • Failed the 'grid' layout for food photos as requested
  • Misspelled 'Mains' as 'Mians'
  • Food items look slightly more like plastic/CGI than real food

Verdict: FLUX.1 [schnell] followed the prompt's layout request much more effectively, producing a cohesive single-sheet menu with a proper grid and sharp headers. While Stable Diffusion 3.5 Large Turbo offers more vibrant colors, it failed to organize the photos in a grid and contained a notable spelling error in a primary header, making FLUX.1 [schnell] the more practical choice for design tasks.

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]
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.1 [schnell]

  • + Excellent photorealistic texture on the bun and meat.
  • + Accurately includes and renders the requested text strings.
  • + Strong adherence to the fiery background and glowing embers requirement.
  • Failed the 'exploded' requirement as the core burger is still assembled.
  • Text has a minor spelling error ('AGIC' instead of 'MAGIC').
  • The starburst price is duplicated and messy.

Stable Diffusion 3.5 Large Turbo

  • + Creates a very vibrant, high-contrast fiery atmosphere.
  • + Good sense of suspension in mid-air with melting elements.
  • + Artistic use of smoke and sparks.
  • Completely failed to include any of the requested text.
  • Failed the 'exploded' requirement as the burger is a solid stack.
  • The burger looks more like a 3D render than a photorealistic image.

Verdict: FLUX.1 [schnell] is the winner because it successfully integrated the majority of the complex text requirements, even with a small typo, whereas Stable Diffusion 3.5 Large Turbo ignored the text entirely. While neither model achieved a true 'exploded' view where components are separated by space, FLUX.1 [schnell] provided much higher photorealistic detail on the food textures.

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]
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.1 [schnell]

  • + Excellent chalk texture that looks authentically handwritten.
  • + High degree of legibility for most of the specified menu items.
  • + Consistent café environment in the background with realistic lighting.
  • Several spelling errors like 'Taffle', 'Pril', and 'Octtoopus'.
  • The prices do not match the prompt exactly (e.g., $4 instead of $24).

Stable Diffusion 3.5 Large Turbo

  • + Clean aesthetic composition with nice interior design elements.
  • + Includes a variety of items on the menu board.
  • Text is heavily garbled and nonsensical (e.g., 'trulale', 'ocotpg').
  • The font looks like a digital brush rather than authentic chalk on a board.
  • Fails to include the full date and correct prices.

Verdict: FLUX.1 [schnell] is the winner because it adheres much more closely to the prompt's request for realistic chalk texture and specific menu items. While it has some spelling issues, Stable Diffusion 3.5 Large Turbo produces mostly unintelligible text and a digital-style font that fails the 'no printed or digital fonts' requirement.

The Reversed Rodeo

Text-to-Image

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

FLUX.1 [schnell]
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.1 [schnell]

  • + Perfectly follows the specific constraint of the horse being on top
  • + Excellent cinematic lighting and textures
  • + Creative visual interpretation of a surreal concept
  • The horse has two neck/head sections merged together
  • The astronaut's anatomy is slightly fragmented

Stable Diffusion 3.5 Large Turbo

  • + Clean, high-resolution rendering
  • + Good composition with the planet and moon
  • + Coherent astronaut suit details
  • Completely failed the negative constraint/positional instruction
  • Generic interpretation of the prompt
  • Anatomical issues with the horse's rear legs

Verdict: FLUX.1 [schnell] is the winner because it successfully followed the difficult logical constraint of having the horse ride the astronaut. While it has some anatomical merging issues with the horse, Stable Diffusion 3.5 Large Turbo completely ignored the core instruction of the prompt, resulting in a standard 'astronaut on horse' image.

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]
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.1 [schnell]

  • + Excellent fur texture and lighting on the capybara.
  • + Successfully captured the businesswoman in the back seat looking at her phone.
  • + High quality text rendering on the hat and interior taxi sun visor signage.
  • The capybara only has one paw near the steering wheel while the other is in its lap.
  • The capybara is looking directly at the camera rather than the road.

Stable Diffusion 3.5 Large Turbo

  • + Perfect adherence to the instruction for both paws to be on the steering wheel.
  • + The capybara's profile and gaze accurately reflect a professional driver focusing on the road.
  • + The composition feels more like a cinematic side-view shot of a taxi.
  • The passenger in the back is blurry and not clearly looking at a phone.
  • The text on the hat is slightly garbled/cut off compared to model A.
  • The capybara's fur looks slightly less realistic and more like a solid surface near the neck.

Verdict: FLUX.1 [schnell] produced a much cleaner and more detailed interior scene with a clear passenger, but it failed to follow the specific posing instruction for the capybara's paws. Stable Diffusion 3.5 Large Turbo followed the posing and driving orientation better, but the passenger in the back Seat is indistinct and lacks the 'looking at phone' detail. FLUX.1 [schnell] is preferred for its overall clarity and successful rendering of all requested characters.

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]
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.1 [schnell]

  • + Successfully included all the required event details such as the date and location.
  • + High-quality cinematic lighting with a moody atmosphere.
  • + Accurate gothic font choices and a dark parchment aesthetic.
  • Contains significant typos and repetitions in the small banner and event details text.
  • The composition feels slightly cluttered with several text layers overlapping.

Stable Diffusion 3.5 Large Turbo

  • + Clean, readable central graphic and well-designed thorny/web border.
  • + Good interpretation of the parchment request with clear borders.
  • Failed to include the specific event details (date, time, location) at the bottom.
  • Missing the required scroll banner and part of the title text.
  • The overall image looks more like a generic clipart than a cinematic invitation.

Verdict: FLUX.1 [schnell] is the winner because it adhered much more closely to the complex text requirements, including the specific date and location, despite some spelling errors. Stable Diffusion 3.5 Large Turbo completely ignored the event details and banner, resulting in a generic image that fails the technical requirements of the prompt.

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]
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.1 [schnell]

  • + Excellent typography for the word 'JAPAN'.
  • + Perfectly clean and minimalist aesthetic following the light blue background prompt.
  • + High clarity and professional graphic design feel.
  • Completely omitted the secondary text 'SUSHI'.
  • The red mark on top of the nigiri looks slightly messy compared to the rest of the render.

Stable Diffusion 3.5 Large Turbo

  • + Effective miniature 3D diorama style with good PBR material feel.
  • + Included both required text elements, though with a spelling error.
  • + Shows multiple types of sushi which adds visual interest.
  • Text 'SUSHI' is misspelled as 'SIIHI'.
  • The flag icon is incorrect, appearing more like a red and white bicolour flag rather than the Japanese flag.
  • Layout feels a bit cluttered compared to the 'ultra-clean' requirement.

Verdict: FLUX.1 [schnell] produced a much cleaner and more professional graphic that adheres strictly to the lighting and background requests, though it failed to include the word 'SUSHI'. Stable Diffusion 3.5 Large Turbo captured the 'diorama' and 'text placement' prompts more literally, but suffered from a spelling error and an incorrect flag design. FLUX.1 [schnell] is preferred for its superior aesthetic quality and accurate flag representation.

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]
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.1 [schnell]

  • + Successfully included all four distinct animal species (puppy, kitten, bunny, fox).
  • + Excellent lighting with clear god rays and a warm sunrise atmosphere.
  • + Cohesive and natural integration of the animals within the meadow environment.
  • The bunny and fox morphologies are slightly hybridized with feline features.
  • The butterflies appear somewhat flatly rendered compared to the fur.

Stable Diffusion 3.5 Large Turbo

  • + Bright, high-contrast colors and very sharp focus on the central characters.
  • + Intense backlit glow around the fur edges.
  • Failed to include a rabbit/bunny as requested in the prompt.
  • The animals look more like 3D digital art than the requested 'hyper-photorealistic' scene.
  • Anatomical issues, particularly with the puppy's paws and the fused bodies of the smaller animals.

Verdict: FLUX.1 [schnell] is the clear winner as it successfully rendered all four animal types requested and captured the 'god rays' lighting efekt much better. Stable Diffusion 3.5 Large Turbo failed to include the bunny and produced images with significant anatomical distortions and a more plastic, CGI-like aesthetic.

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]
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.1 [schnell]

  • + Clean vector emblem style
  • + Perfectly centered and balanced composition
  • + Good color palette adherence
  • Major text spelling errors: 'FRAMILAN' instead of 'Florian'
  • Incorrect year: '7720' instead of '1720'
  • Missing the 'steam' element requested in the prompt

Stable Diffusion 3.5 Large Turbo

  • + Successfully included all elements: cloche, steam, and banner
  • + Accurate date (1720) and much closer spelling
  • + Excellent vintage texture and shading
  • Small typo in 'Caffeé' (extra 'e')
  • The symbol is a hybrid of a cloche and a coffee mug, which is slightly confusing
  • Artifacts around the last letter of 'Florian'

Verdict: Stable Diffusion 3.5 Large Turbo followed the prompt instructions much more accurately, including specific details like the steam and the correct establishment year. While FLUX.1 [schnell] produced a cleaner vector look, its complete failure to spell the name correctly or provide the right date makes it an unsuccessful logo generation.

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]
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.1 [schnell]

  • + Successfully follows the requested infographic layout with a centralized trajectory and numbered steps.
  • + Clean, minimalist flat-vector aesthetic that matches the requested style.
  • + Better adherence to the 'navy, white, and muted red' NASA color palette.
  • Text consists entirely of gibberish, failing to render the requested step labels.
  • Iconography for the Saturn V and Earth is overly simplified to the point of being abstract.
  • The central rocket icon is strangely mirrored/duplicated.

Stable Diffusion 3.5 Large Turbo

  • + High-quality illustration components with more polished vector rendering.
  • + Creative layout that feels more like a commercial poster.
  • + Good legibility on primary headers like 'Apoll.o' and 'Landing'.
  • Fails to include all 6 requested steps in the sequence.
  • Includes an astronaut on a ladder which was not requested and clutters the technical infographic feel.
  • The composition is fragmented into multiple panels rather than a single cohesive diagram.

Verdict: FLUX.1 [schnell] followed the structural logic of the prompt much better, creating a centralized diagram that attempts to show all steps of the mission, whereas Stable Diffusion 3.5 Large Turbo missed several steps and included unrequested elements. However, FLUX.1 [schnell] suffered from poor text rendering and abstract icons, while Stable Diffusion 3.5 Large Turbo produced much cleaner, more professional-looking vector art. FLUX.1 [schnell] is the likely winner for better adhering to the specific 'infographic sequence' instructions.

Next steps

Explore each model