Head to head
Esc

Models · slot A

to navigate to pick

FLUX.2 [dev] Flash fal 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.2 [dev] Flash

27.1 arena score

#5 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.2 [dev] Flash

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.2 [dev] Flash
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.2 [dev] Flash

  • + Excellent adherence to the spatial requirements of the prompt.
  • + Highly realistic lighting and material textures for the glass and table.
  • + Natural-looking plant integration with realistic depth of field.
  • The red book is a bit large compared to the cube's top surface area.

Stable Diffusion 3.5 Large Turbo

  • + Sharp, clean rendering with high contrast.
  • + Good interpretation of the 'soft window light' via shadow patterns on the table.
  • Failed the spatial prompt: the red book is inside the cube rather than on top.
  • The plant is positioned to the side rather than behind the cube, losing the 'visible through glass' effect.
  • The blue sphere is sitting on the book instead of the table.

Verdict: FLUX.2 [dev] Flash perfectly followed all spatial instructions, placing the sphere inside, the book on top, and the plant behind the glass with realistic refraction. Stable Diffusion 3.5 Large Turbo failed multiple spatial relationships, placing the book inside the cube and the sphere on top of the book.

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.2 [dev] Flash
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.2 [dev] Flash

  • + Excellent adherence to the 'candid' and 'imperfect framing' request
  • + Highly realistic skin textures and wet pavement reflections
  • + Accurate depiction of motion blur on passing vehicles and shallow depth of field
  • The bicycle frame geometry is slightly warped near the pedals
  • The tools on the ground look a bit like digital artifacts

Stable Diffusion 3.5 Large Turbo

  • + Successfully captured a red bicycle and an elderly man
  • + Clean composition with minimal distractions
  • Failed the 'motion blur' request as background cars are static
  • Skin and clothing textures look plastic and over-processed
  • The man's anatomy and interaction with the bike are physically incoherent

Verdict: FLUX.2 [dev] Flash significantly outperformed the other model by capturing the stylistic nuances of the prompt, specifically the cinematic realism, 'natural skin texture', and motion-blurred background. Stable Diffusion 3.5 Large Turbo produced an image that looked highly artificial and failed to incorporate several key instructions like motion blur and realistic rain interaction.

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.2 [dev] Flash
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.2 [dev] Flash

  • + Excellent adherence to the braided hair with beads requirement.
  • + Highly detailed engraving and realistic metal texture for the plate armor.
  • + Superior lighting and atmospheric effect with convincing bokeh sparks and torch reflections.
  • The leather straps slightly intersect with the armor in a physically impossible way.
  • The blood marks on the forehead look a bit repetitive in pattern.

Stable Diffusion 3.5 Large Turbo

  • + Clean composition with a strong profile angle.
  • + Vibrant colors and high contrast.
  • Missed the prompt requirement for beads in the hair.
  • Armor texture looks plastic and smoothed over rather than engraved metal.
  • Skin lacks the requested grit, dirt, and lifelike texture, appearing overly airbrushed.

Verdict: FLUX.2 [dev] Flash significantly outperformed the competition by adhering to every specific detail of the prompt, particularly the beads in the braids and the weathered texture of the armor. Stable Diffusion 3.5 Large Turbo produced a much cleaner, more 'digital' image that lacked the requested realism, grit, and fine decorative details like the beads.

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.2 [dev] Flash
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.2 [dev] Flash

  • + Perfectly follows the request for a singular, cohesive menu layout.
  • + Specifically includes all requested sections: appetizers, pizza, and mains.
  • + Maintains professional formatting with recognizable bold sans-serif fonts and clear alignment.
  • The text becomes garbled and nonsensical in the smaller item descriptions.
  • One image in the grid is misaligned with its colored border.

Stable Diffusion 3.5 Large Turbo

  • + Highly vibrant and saturated colors that catch the eye.
  • + Very clean rendering of individual food items and bowls.
  • Failed the layout prompt by creating a collage of separate elements rather than a unified menu design.
  • Missing specific sections (Appetizers) and includes significant typos like 'Mians'.
  • Does not include the requested grid-within-menu design, opting for a scattered top-down aesthetic.

Verdict: FLUX.2 [dev] Flash successfully followed the complex layout instructions, creating a single professional menu with the specific sections and a logical grid of food photos. In contrast, Stable Diffusion 3.5 Large Turbo produced a visually striking but disorganized collage of assets that does not function as a cohesive menu design.

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.2 [dev] Flash
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.2 [dev] Flash

  • + Excellent adherence to all text requirements with correct spelling and styling.
  • + Very photorealistic rendering of food textures, especially the meat patty and fresh lettuce.
  • + Perfect execution of the 'exploded' view requirement with clear separation of layers.
  • The 'starburst' shape around the price is slightly irregular.
  • The sauce droplets look a bit static compared to the dynamic floating ingredients.

Stable Diffusion 3.5 Large Turbo

  • + Strong vibrant colors and high-contrast lighting.
  • + Good representation of a fiery background with embers.
  • Completely failed to include any of the requested text.
  • Failed the 'exploded' burger requirement as the burger is mostly assembled rather than separated.
  • The aesthetic is overly digital/illustrative rather than photorealistic.

Verdict: FLUX.2 [dev] Flash followed the prompt instructions perfectly, delivering a high-quality commercial-style image with accurate text rendering and a realistic 'exploded' view. Stable Diffusion 3.5 Large Turbo failed to include the requested text entirely and did not 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.2 [dev] Flash
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.2 [dev] Flash

  • + Excellent text rendering with accurate spelling for all items.
  • + Highly realistic chalk texture with dusty smudges and authentic handwriting variations.
  • + Perfect adherence to the prompt's layout and style requirements.
  • The bottom edge of the board slightly cuts off the bottom of the content.

Stable Diffusion 3.5 Large Turbo

  • + Bright, clean composition with good lighting effects.
  • + Includes decorative elements like plants and cafe furniture.
  • Numerous spelling errors such as 'trulale' and 'ocotpg'.
  • Text looks more like a digital brush font than authentic chalk handwriting.
  • Failed to include the correct date and prices as requested.

Verdict: FLUX.2 [dev] Flash followed the instructions nearly perfectly, producing a photorealistic chalkboard with legible, correctly spelled text and a natural hand-drawn feel. In contrast, Stable Diffusion 3.5 Large Turbo struggled significantly with the text accuracy and the specific handwriting style, resulting in a more 'clipart' aesthetic with many typos.

The Reversed Rodeo

Text-to-Image

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

FLUX.2 [dev] Flash
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.2 [dev] Flash

  • + Excellent cinematic lighting and environmental detail with realistic planet textures.
  • + High level of anatomical detail in the horse and intricacy in the spacesuit.
  • + Balanced and professional-grade composition.
  • Failed to follow the spatial instruction of placing the horse on top of the astronaut.

Stable Diffusion 3.5 Large Turbo

  • + Strong contrast and clean visual style.
  • + Good sense of motion with the dust/vapor trailing the horse's hooves.
  • Failed to follow the negative constraint to place the horse on top, instead opting for a standard rider.
  • The planet/moon in the background looks poorly rendered and unnatural.
  • The astronaut's hands and the reins have anatomical/logical clipping issues.

Verdict: Both models failed the negative constraint and spatial challenge to place the 'horse on top' of the astronaut, both defaulting to the common trope of an astronaut riding a horse. FLUX.2 [dev] Flash is the clear winner due to significantly higher visual fidelity, more realistic textures, and a much better-executed cinematic atmosphere compared to Stable Diffusion 3.5 Large Turbo.

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.2 [dev] Flash
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.2 [dev] Flash

  • + Excellent adherence to the perspective, showing both characters clearly as requested.
  • + Highly realistic textures on the capybara fur and the businesswoman's clothing.
  • + Perfectly captures the 'bored' expression and the requested phone usage.
  • The placement of the taxi light on top of the car's interior ceiling is physically impossible.
  • The capybara's paws look more like bird talons or strange human-like fingers.

Stable Diffusion 3.5 Large Turbo

  • + Vibrant bokeh lighting in the background creates a strong nighttime city atmosphere.
  • + The capybara's paws are rendered more realistically for the species compared to Model A.
  • Fails to show the businesswoman looking at her phone; she is barely visible and out of focus in the back.
  • The composition is tighter and less 'photorealistic' in terms of framing than requested.
  • The lighting on the capybara's neck is slightly overexposed and unnatural.

Verdict: FLUX.2 [dev] Flash is the clear winner as it followed all elements of the prompt, specifically the businesswoman's bored expression while looking at her phone, which Stable Diffusion 3.5 Large Turbo mostly ignored. While FLUX.2 has a logical error regarding the placement of the taxi's exterior signage, its composition and character detail are much more grounded and effective.

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.2 [dev] Flash
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.2 [dev] Flash

  • + Excellent adherence to all text requirements including specific date and location.
  • + High-quality cinematic lighting with a detailed, moody atmosphere.
  • + Beautifully rendered gothic border with thorns and spiderwebs.
  • Includes some minor gibberish text ('Hurk: 0.369...') in the middle of the event details.

Stable Diffusion 3.5 Large Turbo

  • + Clean, graphic composition with a clear central Jack-o'-lantern.
  • + Good implementation of the border requested in the prompt.
  • Failed to include the majority of the text requirements, including the date, time, and location.
  • The 'parchment' look is quite generic and lacks the 'vintage gothic' texture of the first image.
  • Missing the specific scroll banner and the full title requested.

Verdict: FLUX.2 [dev] Flash significantly outperformed Stable Diffusion 3.5 Large Turbo by following nearly all instructions, including the complex text and data fields. While Stable Diffusion 3.5 Large Turbo produced a clean graphic, it completely ignored the specific event details (date, time, location) and the small scroll banner. Model A's atmospheric detail and lighting also much better matched the 'cinematic' and 'gothic' descriptors.

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.2 [dev] Flash
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.2 [dev] Flash

  • + Perfect text rendering for both 'JAPAN' and 'SUSHI'.
  • + Clean, professional aesthetic that follows the isometric 45° angle perfectly.
  • + Higher realism in textures, particularly the grain of the wood and the translucency of the fish.
  • The sushi pieces are somewhat merged together in an unusual way.
  • Includes a Japanese flag icon but it's positioned next to the text rather than as a 'scene' element.

Stable Diffusion 3.5 Large Turbo

  • + Creative interpretation of a miniature diorama with signs and props.
  • + Good use of vibrant colors and soft lighting.
  • + Individual sushi pieces are distinct and clearly rendered.
  • Spelling error in the text, rendering 'SUSHI' as 'SIIHI'.
  • The Japanese flag is depicted incorrectly as a red and white rectangle.
  • The placement of the text on a sign rather than the background wasn't specifically requested.

Verdict: FLUX.2 [dev] Flash is the clear winner due to its perfect typography and adherence to the clean, minimalist aesthetic requested in the prompt. While Stable Diffusion 3.5 Large Turbo offers a charming miniature layout, it fails on key technical details like spelling and the correct representation of the Japanese flag.

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.2 [dev] Flash
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.2 [dev] Flash

  • + Excellent adherence to the prompt, including all four specific animal species.
  • + Beautiful lighting with clear god rays and dew drops as requested.
  • + High level of fur detail and realistic textures for a hyper-photorealistic look.
  • Generated duplicates of some animals (two foxes, two bunnies) rather than one of each.

Stable Diffusion 3.5 Large Turbo

  • + Features vibrant colors and a joyful vibe.
  • + Captures the sense of movement and 'tumbling' mentioned in the prompt.
  • Failed to include the baby bunny or the red fox kit.
  • Anatomical issues where the cat's limbs merge confusingly with the dog's body.
  • Looks more like a digital painting or 3D render than a 'hyper-photorealistic' photo.

Verdict: FLUX.2 [dev] Flash is the clear winner as it successfully included all requested animal types and followed the complex environment instructions with high fidelity. Stable Diffusion 3.5 Large Turbo failed to generate the bunny or fox and suffered from significant anatomical merging issues between the animals.

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.2 [dev] Flash
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.2 [dev] Flash

  • + Excellent typography including the correct grave accent on 'Caffè'
  • + Superior vector-style shading and texture
  • + Perfect layout with the banner properly integrating both text elements
  • The steam trails are slightly simple compared to the cloche detail

Stable Diffusion 3.5 Large Turbo

  • + Strong contrast and polished highlights
  • + Interesting hybrid of a cloche and a coffee mug
  • Incorrect spelling and punctuation in 'Caffeé Florin'
  • Included a cup handle when a cloche dome was requested
  • Text rendering on the banner is messy and inconsistent

Verdict: FLUX.2 [dev] Flash followed the instructions perfectly, delivering a clean, professional logo with accurate text and a clear cloche dome. Stable Diffusion 3.5 Large Turbo struggled with the typography and introduced an unwanted mug handle, resulting in a less cohesive design.

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.2 [dev] Flash
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

FLUX.2 [dev] Flash

  • + Strong text readability and mostly accurate spelling of major labels.
  • + Clear step-by-step layout that follows the requested narrative sequence.
  • + Excellent inclusion of specific mission details like the crew names and landing site.
  • The layout is a bit cluttered with scattered icons and lines.
  • Minor text corruption on 'Launch' and 'Moon'.
  • The Saturn V icon includes unnecessary side boosters that look more like an SLS or Shuttle configuration.

Stable Diffusion 3.5 Large Turbo

  • + Striking, professional graphic design and layout composition.
  • + Very consistent flat-vector art style and color palette.
  • + Excellent use of negative space and clean lines.
  • Significantly fails on text accuracy with misspelled headers like 'Apoll.o' and 'Larnnar'.
  • Completely ignores the specific 6-step sequence requested in the prompt.
  • Iconography is decorative rather than informational, failing the 'infographic' requirement.

Verdict: FLUX.2 [dev] Flash is the clear winner for prompt adherence, successfully including almost all requested steps with legible text and specific mission details. Stable Diffusion 3.5 Large Turbo produces a more aesthetically pleasing 'poster' with better artistic composition, but it fails as an infographic due to significant text errors and a lack of logical sequence.

Next steps

Explore each model