Head to head
Esc

Models · slot A

to navigate to pick

FLUX.1 Kontext [dev] 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 Kontext [dev]

17.2 arena score

#54 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 Kontext [dev]

100.0%

win rate

Ties

0.0%

Stable Diffusion 3.5 Large Turbo

0.0%

win rate

100.0% 0.0% ties 0.0%
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 Kontext [dev]
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Perfectly follows the spatial instruction of placing the red book on top of the cube.
  • + Excellent material rendering with realistic light reflections on the glass and sphere surface.
  • + Accurately depicts the soft window lighting from the left as requested.
  • The plant is behind the cube but its leaves could be slightly more 'partially visible through' the glass rather than just behind it.

Stable Diffusion 3.5 Large Turbo

  • + High contrast and clean, sharp rendering of the scene elements.
  • + Successfully places the plant behind the objects and creates a clear blue sphere.
  • Fails the spatial instruction by putting the red book inside the cube rather than on top of it.
  • The 'glass cube' has a black metal frame which was not requested.

Verdict: FLUX.1 Kontext [dev] followed all spatial and material instructions perfectly, correctly placing the red book on top of the glass cube and the blue sphere inside. Stable Diffusion 3.5 Large Turbo failed to follow the vertical relationship of the objects, placing the book at the bottom inside the cube, and added an unrequested frame to the glassware.

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 Kontext [dev]
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent handling of complex wet road reflections and lighting
  • + Realistic skin textures and clothing fabrics
  • + Higher adherence to the specific '50mm shallow depth of field' request
  • The man is appearing to sit/straddle the bike rather than actively 'repairing' it
  • The rain effect looks like static digital noise rather than falling droplets

Stable Diffusion 3.5 Large Turbo

  • + Better logic for the 'repairing' action with the figure hunched over the handlebars
  • + Good representation of the red bicycle frame
  • Significant anatomical issues with the man's head and hair blending into his jacket
  • The background cars and road lines are extremely distorted and low quality
  • Fails to capture the bokeh or cinematic depth of field requested

Verdict: FLUX.1 Kontext [dev] produced a far superior image in terms of realism, texture, and lighting, even though the subject is posing with the bike rather than fixing it. Stable Diffusion 3.5 Large Turbo struggled with basic anatomy and background coherence, resulting in a distorted and muddy image that lacks the requested cinematic quality.

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 Kontext [dev]
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent torchlight lighting effects with realistic warm rim lighting.
  • + Subtle and sophisticated armor engraving texture.
  • + Very lifelike, intense facial features and skin texture.
  • Failed to include the requested hair braids and beads.
  • Skin appears slightly clean for a battle-worn soldier.

Stable Diffusion 3.5 Large Turbo

  • + Successfully included braided hair as requested.
  • + Highly detailed engraving on the armor plate.
  • + Good representation of dirt and scars on the skin.
  • Lighting is overly flat and bright, failing the torchlight requirement.
  • The background contains daylight green tones inconsistent with torchlight lighting.
  • Skin and hair textures have a slightly unnatural, waxy smoothing effect.

Verdict: While Stable Diffusion 3.5 Large Turbo followed the prompt instructions more closely regarding the hair braids and facial scars, FLUX.1 Kontext [dev] produced a significantly higher quality image. FLUX.1 Kontext [dev] captured the atmospheric torchlight and depth of field much more effectively, whereas Stable Diffusion resulted in a bright, somewhat artificial-looking composite with inconsistent 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 Kontext [dev]
Stable Diffusion 3.5 Large Turbo

AI judge analysis unavailable for this challenge.

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 Kontext [dev]
Stable Diffusion 3.5 Large Turbo
100% wins 0% ties 0% wins

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent text integration and spelling
  • + Accurate rendering of the price in a starburst sticker
  • + Solid photorealistic textures on the lettuce and burger bun
  • Failed the 'exploded' requirement as the burger is fully assembled
  • Minor typo in the word 'ONLY' as it looks like 'LNHLY'

Stable Diffusion 3.5 Large Turbo

  • + Strong sense of motion with fire and smoke trails
  • + Creative lighting and embers
  • + Good visual quality with high contrast
  • Completely ignored all required text elements
  • Failed the 'exploded burger' requirement; the burger is mostly assembled
  • Includes a strange artifacts like the vertical stick through the top bun

Verdict: FLUX.1 Kontext [dev] followed the text instructions almost perfectly, including the specific price and starburst element, whereas Stable Diffusion 3.5 Large Turbo completely failed to include any text at all. While both models failed to truly 'explode' the burger components into suspension, FLUX.1 Kontext [dev] produced a usable advertisement layout.

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 Kontext [dev]
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent text rendering with very few spelling errors
  • + Accurately represents the chalk texture and handwritten feel
  • + Correctly included all requested menu items and prices
  • The date 'APRIL' is malformed and difficult to read
  • Some repetition in the text, e.g., 'Mushroom Mashroom' and 'with with'

Stable Diffusion 3.5 Large Turbo

  • + Aesthetically pleasing café environment and composition
  • + Consistent handwritten style across the board
  • Severe spelling hallucinations and garbled text across the entire menu
  • Failed to follow the specific menu item and pricing instructions
  • The text looks more like a digital font than actual chalk on a board

Verdict: FLUX.1 Kontext [dev] significantly outperformed Stable Diffusion 3.5 Large Turbo in prompt adherence and text legibility. While FLUX.1 had minor repetition issues and a messy date line, it successfully rendered the complex menu items and prices, whereas Stable Diffusion 3.5 produced mostly unintelligible text and failed to include the specific requested content.

The Reversed Rodeo

Text-to-Image

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

FLUX.1 Kontext [dev]
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Successfully followed the difficult spatial reasoning of 'horse on top'
  • + High clarity in the astronaut's face and suit details
  • + Clean, minimalist composition with a cinematic lighting feel
  • The horse appears to be standing behind the astronaut rather than truly riding him
  • Some anatomical awkwardness in the horse's back legs

Stable Diffusion 3.5 Large Turbo

  • + Classical aesthetic with vibrant colors
  • + Strong sense of motion and scale against the planet background
  • Completely failed the negative constraint to put the horse on top
  • Anatomical errors in the horse's front legs and hoof shape
  • The earth in the background looks like a low-resolution texture

Verdict: FLUX.1 Kontext [dev] is the winner because it successfully interpreted the unconventional 'horse on top' request, creating a surreal image where the horse is positioned above/riding the astronaut. Stable Diffusion 3.5 Large Turbo completely ignored that specific instruction, providing a generic astronaut on a 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 Kontext [dev]
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent photorealism with convincing fur texture and human skin tones.
  • + Captures the woman's bored expression and interaction with her phone perfectly.
  • + Superior lighting and depth of field that feels like a real movie still.
  • The capybara only has one paw on the steering wheel instead of two as requested.
  • The capybara's head is shaped slightly more like a squirrel or generic rodent than a blocky-headed capybara.

Stable Diffusion 3.5 Large Turbo

  • + Successfully placed both paws on the steering wheel as requested.
  • + The capybara's facial structure is more biologically accurate to the species.
  • + The 'TAXI' text on the hat is clear and legible.
  • Failed to show the woman looking at her phone; she is just looking forward.
  • The human character and background are significantly more blurred and less detailed than Model A.
  • The composition feels tighter and less 'cinematic' than the first image.

Verdict: FLUX.1 Kontext [dev] creates a far more convincing and high-quality photorealistic scene, capturing the specific bored expression of the passenger perfectly despite missing the 'both paws' instruction. Stable Diffusion 3.5 Large Turbo adheres better to the mechanical steering wheel instruction but fails the secondary character action and produces a less polished overall image. FLUX.1 Kontext [dev] is the winner for its superior visual quality and effective storytelling.

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 Kontext [dev]
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Successfully included all the requested text details including date, time, and specific location.
  • + Captures the moody, dark atmosphere very well with the thorn-like border.
  • + Good central glowing jack-o-lantern and silhouettes of trees and bats.
  • Text in the scroll banner and the location name is slightly garbled and contains spelling errors.
  • The 'dark parchment' looks more like a plain black background.

Stable Diffusion 3.5 Large Turbo

  • + Excellent application of the 'parchment' texture and 'spooky border with webs' requirement.
  • + Clean and aesthetically pleasing layout with high visual clarity.
  • Failed significantly on text adherence, missing the specific invitation subtitle and all the event details (date, time, location).
  • The central jack-o-lantern is black rather than a traditional orange pumpkin style as implied by 'glowing'.

Verdict: FLUX.1 Kontext [dev] is a much better invitation designer here because it actually includes the requested event details like the date, time, and location, even if some of the smaller text has minor spelling artifacts. Stable Diffusion 3.5 Large Turbo created a beautiful graphic with a better parchment texture, but it completely ignored the specific information and the mandatory scroll banner, making it non-functional as a specific 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 Kontext [dev]
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent typography with perfect spelling and placement.
  • + Clean, minimalist aesthetic that follows the 'soft refined textures' prompt.
  • + Consistent lighting and shadow on a solid light blue background.
  • The flag icon is stylized incorrectly and doesn't resemble the Japanese flag.
  • The sushi design is overly simplified, looking more like a toy than a food miniature.

Stable Diffusion 3.5 Large Turbo

  • + Beautiful 3D diorama feel with realistic rice and food textures.
  • + Great use of the requested isometric perspective and raised base.
  • + Creative interpretation of the flag as a physical miniature within the scene.
  • Includes a significant spelling error ('SIIHI' instead of 'SUSHI').
  • The background is a gradient grey-blue rather than the requested solid light blue.

Verdict: FLUX.1 Kontext [dev] followed the text requirements perfectly but produced a very simplistic, almost abstract version of sushi. Stable Diffusion 3.5 Large Turbo created a much more visually impressive 3D miniature with better textures, but failed on basic spelling and background color. FLUX.1 Kontext [dev] is preferred for graphic design tasks where text accuracy is paramount, whereas Stable Diffusion is better for artistic detail.

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 Kontext [dev]
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Successfully captures a dynamic action scene of animals chasing butterflies
  • + Excellent lighting with a warm golden hour glow and soft bokeh
  • + Accurate rendering of a golden retriever puppy and kitten species
  • Failed to include the baby bunny and red fox kit as requested
  • Anatomical issues with the center kitten's paws

Stable Diffusion 3.5 Large Turbo

  • + Good detail on the fur texture and 'expressive eyes' mentioned in the prompt
  • + Vibrant colors and high contrast
  • Static composition that ignores the 'chasing' and 'tumbling' action requested
  • Missing multiple animals (bunny, fox) and species look more like hybrids than specific domestic breeds
  • Anatomical glitches including an extra leg/paw coming out of the dog's chest

Verdict: FLUX.1 Kontext [dev] is the winner as it much better captures the 'joyful' and 'playful' energy of the prompt, showing the animals in motion within a convincing environment. While both models failed to include all four requested animals, Stable Diffusion 3.5 Large Turbo produced a static, awkwardly composed image with significant anatomical errors in the foreground.

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 Kontext [dev]
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent typography with perfect spelling and accent marks.
  • + Clean vector aesthetics that fully embody the minimalist request.
  • + Strong adherence to the warm brown and cream color palette.
  • The cloche dome is very abstract and slightly resembles a building dome.
  • Lacks the 'banner' requested in the prompt, opting for plain text.

Stable Diffusion 3.5 Large Turbo

  • + Successfully includes the banner and steam elements as requested.
  • + Effective use of vintage textures and shading to create a retro feel.
  • + Closer interpretation of a 'cloche' dome shape.
  • Incorrect spelling of 'Caffé' (added an extra 'e' and incorrect accent).
  • Visual artifacts or glitches present in the typography on the banner.
  • The illustration is a bit cluttered, leaning away from the 'minimalist' requirement.

Verdict: FLUX.1 Kontext [dev] produced a superior professional logo with perfect typography and a true minimalist vector feel, though it missed the banner element. Stable Diffusion 3.5 Large Turbo captured more of the specific decorative elements like the steam and banner, but failed on basic spelling and text clarity. FLUX.1 Kontext [dev] is the likely winner for its clean, usable design and correct text rendering.

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 Kontext [dev]
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Stronger adherence to the flat-vector infographic style requested.
  • + Follows the step-by-step sequential numbering instruction more closely.
  • + Uses the specified navy and muted red palette effectively.
  • Significant spelling errors throughout the text including the header.
  • The icons are somewhat abstract and poorly formed.

Stable Diffusion 3.5 Large Turbo

  • + Excellent visual composition and professional illustration quality.
  • + Captures the mid-century NASA aesthetic perfectly with high clarity.
  • + Text is cleanly rendered and readable, despite some creative spelling.
  • Failed to provide the six specific numbered steps requested in the prompt.
  • Included an astronaut character which was not requested in the flat-vector icon prompt.

Verdict: FLUX.1 Kontext [dev] followed the logical structure of the prompt by attempting all six specific mission steps in a flat-vector format, but suffered from poor icon clarity and severe typos. Stable Diffusion 3.5 Large Turbo produced a much more visually appealing and coherent poster that feels professional, although it failed to follow the specific step-by-step instructions for the icons.

Next steps

Explore each model