Head to head
Esc

Models · slot A

to navigate to pick

FLUX.2 [max] Black Forest Labs Stable Diffusion 3.5 Medium Stability AI

Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.

FLUX.2 [max]

25.9 arena score

#10 of 62 in Text-to-Image

Skill signature · Text-to-Image

Stable Diffusion 3.5 Medium

16.8 arena score

#56 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.2 [max]

100.0%

win rate

Ties

0.0%

Stable Diffusion 3.5 Medium

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.2 [max]
Stable Diffusion 3.5 Medium
100% wins 0% ties 0% wins

AI Judge Analysis

FLUX.2 [max]

  • + Excellent photorealism with realistic textures for the book cover and wooden table.
  • + Accurate physics and lighting with light rays falling from the left as requested.
  • + Clean, sharp details on the glass cube and the blue sphere's surface reflection.
  • The glass cube has a mirrored base which wasn't specifically requested, though it adds to the aesthetic.

Stable Diffusion 3.5 Medium

  • + Successfully includes all requested elements in a coherent scene.
  • + Captures the 'plant behind the cube visible through glass' requirement well.
  • The blue sphere is inexplicably floating in the center of the cube without support.
  • Visual quality is lower with softer textures and less realistic lighting compared to Image A.
  • The book shape is somewhat distorted and lacks detailed texture.

Verdict: FLUX.2 [max] produced a much higher quality image with realistic lighting, textures, and believable physics. While Stable Diffusion 3.5 Medium followed the prompt correctly, it failed to render the sphere realistically (making it float) and had significantly more digital artifacts and lower resolution details.

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 [max]
Stable Diffusion 3.5 Medium

AI Judge Analysis

FLUX.2 [max]

  • + Excellent anatomical and mechanical detail in the hands and bicycle components.
  • + Perfect execution of the shallow depth of field and motion blur requested.
  • + Very realistic skin textures and lighting consistency.
  • The framing feels a bit more intentional than the requested 'imperfect framing'.

Stable Diffusion 3.5 Medium

  • + Good atmosphere with strong reflections on the wet pavement.
  • + Captures a sense of 'candid' street photography with a wider perspective.
  • The subject is not clearly 'repairing' the bike; he is simply leaning on it.
  • Severe anatomical issues with the man's hands and the bicycle structure.
  • Lacks the specific 50mm look, feeling more like a wide-angle shot.

Verdict: FLUX.2 [max] is the clear winner as it masterfully handles the complex interaction between the man's hands and the bicycle, while perfectly executing the requested photographic effects like motion blur and shallow depth of field. Stable Diffusion 3.5 Medium fails significantly on anatomical correctness and does not accurately portray the 'repairing' action, resulting in a disorganized and less realistic image.

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 [max]
Stable Diffusion 3.5 Medium

AI Judge Analysis

FLUX.2 [max]

  • + Exceptional level of detail on the engraved armor patterns and leather textures
  • + Photorealistic rendering of skin pores and lifelike eyes
  • + Subtle and realistic lighting that accurately suggests torchlight presence
  • The beads in the hair are present but somewhat understated compared to the armor detail

Stable Diffusion 3.5 Medium

  • + Dynamic hair braiding style that looks intentional and intricate
  • + Strong color contrast with warm lighting on one side and cool on the other
  • + Good adherence to the bokeh sparks and battle-worn skin prompts
  • Overall image has a slightly over-sharpened, digital filter appearance
  • The armor engraving lacks the depth and realism found in the competitor
  • The skin texture appears a bit muddy rather than showing distinct scars and dirt

Verdict: FLUX.2 [max] produces a significantly more realistic and technically polished image with incredible attention to the materiality of the armor and skin. While Stable Diffusion 3.5 Medium captures the prompt's elements well, it suffers from a more artificial, high-contrast digital look that lacks the fine-grained detail of FLUX.2.

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 [max]
Stable Diffusion 3.5 Medium

AI Judge Analysis

FLUX.2 [max]

  • + Excellent typography with clean, legible headers and realistic pricing structures.
  • + Well-organized two-column layout that follows professional graphic design principles.
  • + High-quality, appetizing food photography that looks consistent and professional.
  • The 'Appetizers' section contains several images that appear to be pizzas or sandwiches rather than typical starters.
  • The text in the descriptions is gibberish, though the letterforms are clear.

Stable Diffusion 3.5 Medium

  • + Successfully uses a grid-based layout as requested in the prompt.
  • + Strong variety of colorful food photos that span different categories.
  • The typography is distorted and difficult to read, lacking the 'bold sans-serif' clarity requested.
  • The layout is cluttered and lacks clear visual hierarchy between sections.
  • The food images contain visible AI artifacts and blurred textures.

Verdict: FLUX.2 [max] is the clear winner as it produces a professional, commercially viable menu layout with clean typography and high-definition photography. Stable Diffusion 3.5 Medium struggles with text rendering and overall composition, resulting in a messy design that lacks the 'professional' finish requested in the prompt.

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 [max]
Stable Diffusion 3.5 Medium

AI Judge Analysis

FLUX.2 [max]

  • + Excellent typography with a glowing fire effect as requested.
  • + Successfully created a dynamic, exploded view with separated layers.
  • + High photorealistic detail in the food textures and sauce splashes.
  • The pricing starburst looks a bit like a generic clip-art graphic compared to the rest of the scene.

Stable Diffusion 3.5 Medium

  • + Good background fire effects and embers.
  • + Correct text spelling and placement.
  • + Realistic lighting on the bun surfaces.
  • Failed to create an 'exploded' burger, showing an almost fully assembled one instead.
  • The pricing starburst is a simple black-and-white icon that lacks the 'fiery, glowing effect' requested.
  • The burger components are not clearly suspended in mid-air as requested.

Verdict: FLUX.2 [max] followed the prompt much more accurately, delivering the dynamic 'exploded' composition and the specific fiery glowing text effects. Stable Diffusion 3.5 Medium failed to separate the burger components and used a very basic, non-thematic graphic for the price starburst.

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 [max]
Stable Diffusion 3.5 Medium

AI Judge Analysis

FLUX.2 [max]

  • + Excellent text rendering with no spelling errors.
  • + Highly realistic chalk texture and natural variations in handwriting.
  • + Successfully completed the partial prompt for the third menu item with logical contents.
  • Lighting is a bit dark in the corners of the chalkboard.

Stable Diffusion 3.5 Medium

  • + Includes a nice wood texture for the frame.
  • + Captures the concept of a decorative café chalkboard.
  • Severe spelling errors and garbled text throughout.
  • The date rendering is completely incoherent and messy.
  • Fails to maintain a consistent 'elegant cursive' style for the title.

Verdict: FLUX.2 [max] followed the prompt instructions perfectly, producing legible, accurately spelled text with a convincing chalk aesthetic. Stable Diffusion 3.5 Medium struggled significantly with the text, producing illegible words and a cluttered composition that did not follow the specific content requested.

The Reversed Rodeo

Text-to-Image

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

FLUX.2 [max]
Stable Diffusion 3.5 Medium

AI Judge Analysis

FLUX.2 [max]

  • + Excellent anatomical rendering of the horse and spacesuit
  • + Cinematic lighting with a dramatic galaxy background
  • + Strong composition with the asteroid adding grounded context to the scene
  • Failed the specific spatial instruction for the horse to be on top of the astronaut

Stable Diffusion 3.5 Medium

  • + Matches the requested surrealist vibe with a floating horse
  • + Clean, high-contrast colors between the horse and space
  • Failed the specific spatial instruction for the horse to be on top of the astronaut
  • Significant anatomical errors, particularly with the horse's multiple front legs
  • Overall lower resolution and detail compared to the competitor

Verdict: Both FLUX.2 [max] and Stable Diffusion 3.5 Medium failed the negative constraint to have the horse on top of the astronaut, defaulting to the common trope of an astronaut riding a horse. However, FLUX.2 [max] is the superior image due to its exceptional technical quality, realistic anatomy, and cinematic lighting, whereas Stable Diffusion 3.5 Medium suffered from major anatomical defects in the horse's legs.

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 [max]
Stable Diffusion 3.5 Medium

AI Judge Analysis

FLUX.2 [max]

  • + Excellent photographic composition with great depth of field
  • + Detailed taxi interior including dashboard and meter
  • + Accurately depicts the businesswoman looking at her phone as requested
  • The capybara has human hands instead of paws
  • The capybara's head is not looking toward the road

Stable Diffusion 3.5 Medium

  • + Successfully depicts capybara paws on the steering wheel
  • + Stronger frontal focus on the capybara's professional expression
  • + Vibrant colors and high-quality fur texture
  • Fails to include the businesswoman's phone
  • The businesswoman's pose is awkward and does not look bored
  • Perspective is slightly claustrophobic with a less realistic interior

Verdict: FLUX.2 [max] creates a much more realistic and cinematic scene with a complex interior and perfectly follows the prompt regarding the passenger's behavior, though it fails on the specific anatomical detail of the paws by giving the animal human hands. Stable Diffusion 3.5 Medium handles the capybara's paws correctly and centers the subject well, but misses the core instruction of the passenger looking at her phone. FLUX.2 [max] is the preferred choice for its superior composition and adherence to the secondary elements of the prompt.

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 [max]
Stable Diffusion 3.5 Medium

AI Judge Analysis

FLUX.2 [max]

  • + Excellent typography with perfect spelling of all requested text.
  • + High-quality cinematic lighting with a moody, professional atmosphere.
  • + Strong adherence to the border, scroll, and central jack-o-lantern requirements.
  • The 'parchment' texture is subtle and feels more like a modern poster than a physical aged scroll.

Stable Diffusion 3.5 Medium

  • + Successfully captures a more literal 'parchment' look for the background.
  • + Follows the request for twisted trees and spider webs effectively.
  • Significant spelling errors in every piece of text ('Halloweeen','Aches', 'Timme').
  • Layout is cluttered and lacks the 'polished' look specified in the prompt.
  • Failed to include a central jack-o-lantern, instead placing them in the corners.

Verdict: FLUX.2 [max] is the clear winner as it perfectly renders all requested text and creates a professional, cinematic composition that matches the 'gothic and polished' description. Stable Diffusion 3.5 Medium struggles significantly with text spelling and layout, failing to follow the instruction for a central jack-o-lantern.

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 [max]
Stable Diffusion 3.5 Medium

AI Judge Analysis

FLUX.2 [max]

  • + Perfectly follows the 45-degree isometric diorama instruction.
  • + Excellently renders all requested text and the small flag icon.
  • + Clean 3D cartoon style with high resolution and soft, refined textures.
  • The sushi variety is a bit generic/simple, though fitting for the cartoon theme.

Stable Diffusion 3.5 Medium

  • + Textured seaweed and roe look realistic and meet the 'PBR materials' prompt.
  • + Correctly interprets the solid light blue background and plate.
  • Failed to include the requested flag icon.
  • The 'SUSHI' text has a weird translucent artifact on the 'S' and an extra dot on the 'I'.
  • Missing the 3D diorama base and specific isometric miniature layout.

Verdict: FLUX.2 [max] is the clear winner as it perfectly executed the 'isometric miniature diorama' layout requested, including the specific text and flag details. Stable Diffusion 3.5 Medium failed to create the diorama base and had noticeable artifacts in the typography and composition.

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 [max]
Stable Diffusion 3.5 Medium

AI Judge Analysis

FLUX.2 [max]

  • + Successfully included all four requested animals (dog, cat, rabbit, fox).
  • + Excellent depiction of atmospheric depth with god rays and dew sparkles.
  • + Highly realistic fur textures and natural animal anatomy.
  • The fox's front right leg has a slightly awkward joint angle.

Stable Diffusion 3.5 Medium

  • + Vibrant, saturated colors that enhance the joyful vibe.
  • + Expressive faces with large, clear eyes as requested.
  • Failed to include the bunny mentioned in the prompt.
  • The 'kitten' resembles a fox-cat hybrid with oversized ears and orange fur.
  • Art style is more illustrative and painterly rather than the requested hyper-photorealistic.

Verdict: FLUX.2 [max] is the clear winner as it followed all prompt instructions, including the specific list of four animals, while maintaining a hyper-photorealistic style. Stable Diffusion 3.5 Medium failed to include the bunny and struggled with realistic animal anatomy, resulting in a more stylized, AI-looking image.

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 [max]
Stable Diffusion 3.5 Medium

AI Judge Analysis

FLUX.2 [max]

  • + Perfect text rendering for all requested strings including accents.
  • + Clean vector emblem style that adheres well to the minimalist request.
  • + Accurate depiction of a retro cloche dome with stylized steam.
  • The 'subtle texture' on the background is very faint, appearing almost as plain paper.

Stable Diffusion 3.5 Medium

  • + Strong vintage illustration style with high-contrast brown tones.
  • + Creative use of a teacup and elaborate scrollwork.
  • Poor text spelling with 'Caffee', 'Florrian', and 'Est 170'.
  • The cloche dome is distorted and looks more like a decorative orb or hat.
  • Design is overly busy, failing the 'minimalist' requirement.

Verdict: FLUX.2 [max] followed the prompt instructions precisely, delivering a clean, professional vector logo with perfect spelling and a clear minimalist aesthetic. In contrast, Stable Diffusion 3.5 Medium failed on almost every specific detail, including multiple spelling errors and a composition that was too cluttered to be considered minimalist.

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 [max]
Stable Diffusion 3.5 Medium

AI Judge Analysis

FLUX.2 [max]

  • + Excellent typography with mostly legible and accurate labels
  • + High adherence to the flat-vector infographic style
  • + Clean and logical layout that tells a clear sequential story
  • Repeats the 'Earth Orbit' label three times instead of using the specific step names like Lunar Orbit
  • The rocket icon looks more like a shuttle than a Saturn V

Stable Diffusion 3.5 Medium

  • + Captures the requested NASA-inspired color palette well
  • + Includes stylized orbital trajectories that give a sense of motion
  • Severe spelling errors and nonsensical text throughout the image
  • Illogical sequence that does not follow the requested 6-step progression
  • Icons are messy and lack the crisp detail requested in the prompt

Verdict: FLUX.2 [max] is the clear winner as it successfully creates a coherent, modern infographic with clear sections and legible text that follows the intended flow. Stable Diffusion 3.5 Medium fails significantly on prompt adherence, producing garbled text and a disorganized layout that does not successfully convey the Apollo 11 mission steps.

Next steps

Explore each model