Head to head
Esc

Models · slot A

to navigate to pick

FLUX1.1 [pro] 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.

FLUX1.1 [pro]

18.4 arena score

#50 of 62 in Text-to-Image

Skill signature · Text-to-Image

Stable Diffusion 3.5 Medium

16.8 arena score

#57 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX1.1 [pro]

0%

win rate

Ties

0%

Stable Diffusion 3.5 Medium

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.”

FLUX1.1 [pro]
Stable Diffusion 3.5 Medium

AI Judge Analysis

FLUX1.1 [pro]

  • + Perfect prompt adherence with the red book placed correctly on top of the cube.
  • + High-quality rendering of glass reflections and refraction of the plant behind it.
  • + Excellent composition and realistic textures on the book and wooden table.
  • The glass container is more of a rectangular prism than a perfect cube.
  • The blue sphere appears to be floating mid-air inside the glass.

Stable Diffusion 3.5 Medium

  • + Good rendering of the glass material and table texture.
  • + The plant is correctly positioned behind the object.
  • Failed to place the red book on top of the cube; instead, a red platform is inside the cube.
  • The blue sphere is sitting on the red object rather than being a separate element as implied by the spatial layout.
  • The composition feels slightly cropped and less polished than Model A.

Verdict: FLUX1.1 [pro] followed all spatial instructions perfectly, including the specific placement of the red book on top of the cube. In contrast, Stable Diffusion 3.5 Medium struggled with the spatial relationships, placing the red object inside the cube instead of on top. FLUX1.1 [pro] also produced a much more photorealistic image with superior lighting and refraction.

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.”

FLUX1.1 [pro]
Stable Diffusion 3.5 Medium

AI Judge Analysis

FLUX1.1 [pro]

  • + Excellent bokeh and realistic city lights background.
  • + Realistic skin texture and garment fabric details.
  • + Good depiction of wet pavement and atmospheric reflections.
  • The bicycle structure is anatomically broken, with the frame missing its rear half.
  • The man's hands have significant anatomical errors and poor grip logic.

Stable Diffusion 3.5 Medium

  • + Successfully captures the feeling of light rain with visible streaking.
  • + Better overall bicycle structure and placement in the scene.
  • + Effective use of 'imperfect framing' which adds to the candid aesthetic.
  • Faces and hands lack fine detail and appear slightly smudged.
  • Lower resolution and more painterly texture compared to the photorealistic requirement.
  • The reflection on the ground doesn't perfectly align with the bike's position.

Verdict: While FLUX1.1 [pro] offers superior lighting, skin textures, and a convincing cinematic atmosphere, it fails significantly on the structural integrity of the bicycle and the man's hands. Stable Diffusion 3.5 Medium follows the prompt's request for 'imperfect framing' and 'light rain' more effectively, but the overall image quality and face rendering are noticeably lower. FLUX1.1 [pro] is generally preferred for its realism, despite the glaring anatomical and mechanical artifacts.

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.”

FLUX1.1 [pro]
Stable Diffusion 3.5 Medium

AI Judge Analysis

FLUX1.1 [pro]

  • + Incredible skin texture and realistic eye detail
  • + Excellent implementation of warm torchlight reflections
  • + Very high visual clarity and lifelike quality
  • The braiding is messy and lacks the requested beads
  • Extreme close-up cuts off much of the ornate armor details

Stable Diffusion 3.5 Medium

  • + Clearly defined braids that follow the prompt well
  • + Beautifully detailed engraving on the plate armor
  • + Good composition showing more of the leather straps and armor
  • Missing the specific 'beads' in the hair
  • Overall image looks more like a digital painting than a lifelike photo
  • Lighting is flatter compared to the 'warm torchlight' request

Verdict: FLUX1.1 [pro] excels in photographic realism, skin texture, and lighting, creating a much more emotive and lifelike character. Stable Diffusion 3.5 Medium follows the structural details of the prompt better, specifically the armor engravings and hair braids, but falls short on the 'lifelike' and 'torchlight' requirements. FLUX1.1 [pro] is the winner for its superior visual quality and atmospheric depth.

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.”

FLUX1.1 [pro]
Stable Diffusion 3.5 Medium

AI Judge Analysis

FLUX1.1 [pro]

  • + Excellent presentation for a menu with realistic flat-lay cutlery and professional depth of field.
  • + Clean typography that mimics a real menu layout with clearly defined categories.
  • + High-quality, appetizing food photography that looks commercially viable.
  • Text contains gibberish words and spelling errors like 'Restarnvens' and 'Dreafry'.
  • The food photo grid is a bit cramped at the bottom of the page.

Stable Diffusion 3.5 Medium

  • + Strong adherence to the grid layout request for food photos.
  • + Clean, minimalist white background across the entire design.
  • Text is highly distorted and illegible with poor character rendering.
  • The overall image quality is lower with visible noise and less refined visual details.
  • The fonts used are inconsistent and do not feel like professional sans-serif choices.

Verdict: FLUX1.1 [pro] is the clear winner as it provides a professional, polished layout with high-quality photography and realistic lighting. While Stable Diffusion 3.5 Medium followed the grid requirement well, it suffered from severe text artifacts and a lack of visual polish compared to the commercial-grade output of FLUX1.1 [pro].

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.”

FLUX1.1 [pro]
Stable Diffusion 3.5 Medium

AI Judge Analysis

FLUX1.1 [pro]

  • + Excellent photorealistic texture on the meat and bun
  • + Clean typography with correct spelling for the most part
  • + Professional commercial lighting and depth of field
  • Failed the 'exploded' instruction as the layers are mostly stacked
  • Missing the starburst for the price tag
  • Includes redundant neon text that contradicts the 'fiery' style request

Stable Diffusion 3.5 Medium

  • + Successfully included a starburst element for the price
  • + Stronger fiery background and ember effects
  • + Accurate text rendering for all requested phrases
  • Failed the 'exploded' instruction as the burger is fully assembled
  • The starburst is a simple white graphic rather than a glowing fiery effect
  • Lower resolution/clarity in the burger textures compared to the competitor

Verdict: Both models failed to deliver the 'exploded' view where components are suspended in mid-air, instead opting for a floating whole burger. FLUX1.1 [pro] produced a much more appetizing and high-quality product shot, while Stable Diffusion 3.5 Medium followed the layout instructions better by including the starburst and omitting unnecessary neon elements.

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.”

FLUX1.1 [pro]
Stable Diffusion 3.5 Medium

AI Judge Analysis

FLUX1.1 [pro]

  • + Excellent legibility with mostly correct spelling.
  • + Captures the clean, elegant cursive requested for the title.
  • + Good color and lighting for a cafe environment.
  • Repeated the Grilled Octopus line unnecessarily and hallunicated prices of $228 and $98.
  • The text looks more like a digital font overlay than physical chalk texture.

Stable Diffusion 3.5 Medium

  • + Substantial chalk texture and realistic smudge effects on the board.
  • + Excellent creative chalk calligraphy style for the headers.
  • + Followed the layout requirements including the framing/lighting.
  • Poor spelling and character rendering (e.g., 'Trodalu', 'Oocclutels').
  • The date 'APRIL 30, 2026' is garbled and unreadable.
  • Layout is a bit cluttered with redundant columns.

Verdict: FLUX1.1 [pro] followed the text instructions much more accurately, resulting in a readable and professional-looking menu, even though it repeated one item and lacks a convincing chalk texture. Stable Diffusion 3.5 Medium excelled at the artistic 'chalk' feel and texture but failed significantly at text legibility and prompt adherence for specific names and dates.

The Reversed Rodeo

Text-to-Image

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

FLUX1.1 [pro]
Stable Diffusion 3.5 Medium

AI Judge Analysis

FLUX1.1 [pro]

  • + Excellent cinematic lighting and texture detail on the space suit and horse hair.
  • + Dynamic composition with a sense of motion and scale.
  • + Highly detailed background with planets and nebulae.
  • Completely failed the negative constraint to have the horse on top.
  • Anatomical issues where the horse's front legs merge awkwardly into the body.

Stable Diffusion 3.5 Medium

  • + Features a more expansive 'space' view with the Earth's curve.
  • + Clean rendering of the astronaut suit.
  • Completely failed the negative constraint to have the horse on top.
  • Severe anatomical artifacts with the horse's legs appearing elongated and segmented.
  • The horse lacks shadow or interaction with the astronaut, appearing flatly pasted.

Verdict: Both models failed the specific prompt instruction to place the horse on top of the astronaut, showing the inherent difficulty models have with spatial relationship inversions. However, FLUX1.1 [pro] is the clear winner due to its significantly higher visual quality, cinematic atmosphere, and more coherent rendering, whereas Stable Diffusion 3.5 Medium suffered from major anatomical distortions on 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.”

FLUX1.1 [pro]
Stable Diffusion 3.5 Medium

AI Judge Analysis

FLUX1.1 [pro]

  • + Excellent composition with a natural perspective from the back seat.
  • + Superior lighting and bokeh effect in the background city lights.
  • + Accurate character placement with high-quality skin and fur textures.
  • The capybara is positioned as a passenger rather than in the driver's seat.
  • The steering wheel is not clearly visible.

Stable Diffusion 3.5 Medium

  • + Correctly places the capybara in the driver's seat with paws on the wheel.
  • + Strong adherence to the specific 'driver' role and frontal framing.
  • + Highly detailed embroidery on the taxi driver cap.
  • The human passenger in the back is out of focus and lacks detail.
  • Anatomy of the capybara's paws appears somewhat distorted.

Verdict: FLUX1.1 [pro] produces a more cinematic and high-fidelity image with superior lighting, though it fails to place the capybara in the driver's seat. Stable Diffusion 3.5 Medium adheres better to the prompt's structural requirements regarding the driving position but lacks the overall clarity and professional finish of the former.

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.”

FLUX1.1 [pro]
Stable Diffusion 3.5 Medium

AI Judge Analysis

FLUX1.1 [pro]

  • + Excellent cinematic lighting and atmosphere with a high-quality illustration style.
  • + The thorny border and twisted trees are intricately rendered and aesthetically pleasing.
  • + Correct date and location text adherence.
  • The text is repetitive, listing the date, time, and location twice.
  • Failed to include the 'Invitation' portion of the prompt's title text properly on the banner.

Stable Diffusion 3.5 Medium

  • + Clearer use of the parchment/scroll element as requested in the prompt.
  • + Captures the spiderweb and bat elements effectively within the composition.
  • Numerous spelling errors including 'Halloweeen', 'Inviloween', 'Timme', and 'Loccation'.
  • Visual quality is lower with flat, less detailed illustrations compared to the competitor.
  • The date '226' is incorrect compared to the requested '2026'.

Verdict: FLUX1.1 [pro] significantly outperforms Stable Diffusion 3.5 Medium in terms of visual polish, lighting, and legibility, despite some redundant text at the bottom. While Stable Diffusion 3.5 Medium follows the layout requirements of a light parchment centrer, it suffers from severe spelling errors and a much simpler artistic execution.

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.”

FLUX1.1 [pro]
Stable Diffusion 3.5 Medium

AI Judge Analysis

FLUX1.1 [pro]

  • + Excellent adherence to the 'miniature 3D cartoon' and 'isometric diorama' style
  • + Accurate text rendering and placement as requested
  • + Clean, soft textures that match the PBR material description
  • Missing the specific small flag icon mentioned in the prompt

Stable Diffusion 3.5 Medium

  • + Features a flag-like red circle on the sushi which nods to the Japanese flag
  • + Vibrant colors and strong lighting
  • Failed the text hierarchy, making 'SUSHI' larger than 'JAPAN'
  • Background has noticeable noise and is not a 'solid' clean light blue
  • Subject is not on a raised diorama base as requested

Verdict: FLUX1.1 [pro] followed almost every instruction, delivering a high-quality isometric diorama with a polished 3D cartoon aesthetic. Stable Diffusion 3.5 Medium struggled with the text layout, the specific diorama requirement, and produced a much noisier background. FLUX1.1 [pro] is the clear winner for its superior composition and stylistic consistency.

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.”

FLUX1.1 [pro]
Stable Diffusion 3.5 Medium

AI Judge Analysis

FLUX1.1 [pro]

  • + Exceptional backlighting and soft focus that creates a dreamlike, joyful atmosphere.
  • + Incredible detail in the fur texture and moisture in the eyes.
  • + Naturalistic composition that feels light and airy.
  • Failed to include the red fox kit as requested in the prompt.
  • The 'butterflies' appear more like glowing yellow moths or generic light particles.

Stable Diffusion 3.5 Medium

  • + Captured a wider variety of animals, including the fox and a cat-rabbit hybrid.
  • + High color saturation and clear rendering of butterflies.
  • + Good inclusion of 'god rays' in the background.
  • Anatomical issues, particularly the kitten which has oversized rabbit-like ears.
  • The fur texture appears more illustrative and 'plastic' compared to the photorealistic request.
  • Lacks the sense of 'tumbling together' action requested.

Verdict: FLUX1.1 [pro] produced a much more photorealistic and aesthetically pleasing image with superior lighting and texture, though it missed one of the four animals requested. Stable Diffusion 3.5 Medium tried harder to include all subjects but struggled with anatomical consistency, resulting in a kitten that looks like a hybrid creature. FLUX1.1 [pro] is the preferred choice for its high-quality rendering and artistic composition.

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.”

FLUX1.1 [pro]
Stable Diffusion 3.5 Medium

AI Judge Analysis

FLUX1.1 [pro]

  • + Elegant vector illustration style
  • + Excellent color palette and balance
  • + Clear typography for established date
  • Misspelled the primary name as FRANILIAN

Stable Diffusion 3.5 Medium

  • + Stronger vintage aesthetic with hatching
  • + Includes a coffee cup detail
  • + Name spelling is much closer to original prompt
  • Incorrect year in the date banner
  • Composition is a bit crowded and heavy

Verdict: Both models struggled with precise character-for-character text accuracy. FLUX1.1 [pro] produced a cleaner, more professional vector emblem, while Stable Diffusion 3.5 Medium captured a more authentic vintage texture and closer name spelling despite the incorrect year.

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.”

FLUX1.1 [pro]
Stable Diffusion 3.5 Medium

AI Judge Analysis

FLUX1.1 [pro]

  • + Strong composition with a clear central focal point and balanced info callouts.
  • + Excellent color palette adherence using navy, white, and muted red.
  • + Clean vector aesthetic with crisp lines and modern typography.
  • Text content contains several typos and repeated step numbers (e.g., multiple '6' steps).
  • The 'Saturn V' icon is misinterpreted as a cartoonish generic rocket.

Stable Diffusion 3.5 Medium

  • + Successfully used red as an accent color in the trajectory lines.
  • + Includes icons for each stage along the left margin.
  • The infographic structure is chaotic and doesn't follow a logical timeline.
  • Text is mostly gibberish or misspelled, failing on technical clarity.
  • Composition is unbalanced with a large, undetailed sphere cutting off the right side.

Verdict: FLUX1.1 [pro] produced a professional-grade poster that captures the requested 'modern vector' style perfectly, despite some minor spelling errors in the small text. Stable Diffusion 3.5 Medium failed to create a cohesive infographic, resulting in a cluttered layout and unintelligible text. FLUX1.1 [pro] is the clear winner for its superior composition, stylistic consistency, and legibility.

Next steps

Explore each model