Black Forest Labs' premium multimodal flow transformer with greatly improved prompt adherence and typography generation for in-context image generation and editing without compromise on speed
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
FLUX.1 Kontext [max]
23.7
arena score
#23 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 [max]
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 Kontext [max]
Stable Diffusion 3.5 Large Turbo
AI Judge Analysis
FLUX.1 Kontext [max]
- + Perfect adherence to object placement with the red book on top.
- + Excellent photorealistic lighting and refraction through the glass.
- + Naturalistic integration of the plant in the background.
Stable Diffusion 3.5 Large Turbo
- + Clean, sharp rendering of the wood grain and lighting shadows.
- + Accurately represents all high-level elements in the scene.
- − Failed to place the red book on top of the cube as requested.
- − The cube structure has inconsistencies where the black frame meets the glass.
- − The plant is placed to the left rather than behind the cube.
Verdict: FLUX.1 Kontext [max] followed every spatial instruction perfectly, delivering a highly realistic image with convincing glass refractions and correct object stacking. Stable Diffusion 3.5 Large Turbo failed the spatial reasoning part of the prompt by placing the book inside/under the cube and the plant to the side.
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 [max]
Stable Diffusion 3.5 Large Turbo
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent adherence to aesthetic prompts like shallow depth of field and rain reflections.
- + High level of realism in skin texture and fabric details.
- + Creative interpretation of 'candid' and 'imperfect framing' that feels like real street photography.
- − The bike chain logic is slightly flawed near the rear derailleur.
- − The rain droplets look a bit like vertical streaks rather than particles.
Stable Diffusion 3.5 Large Turbo
- + Successfully includes the red bicycle and elderly man as requested.
- + Clean, simple composition.
- − Fails significantly on photorealism, looking like a smooth 3D render rather than a 50mm photo.
- − Misses key prompt details like 'motion blur from passing cars' and 'reflections on wet pavement'.
- − Anatomical and mechanical errors including the man's hands merging with the bike and a nonsensical bike frame.
Verdict: FLUX.1 Kontext (max) successfully captured the cinematic, realistic street photography style requested, maintaining natural textures and atmospheric effects. Stable Diffusion 3.5 Large Turbo failed to follow most of the stylistic prompts, producing a plastic-like image with significant anatomical and mechanical distortions.
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 [max]
Stable Diffusion 3.5 Large Turbo
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent realism with highly detailed skin textures and lifelike eyes.
- + Superior lighting that authentically reflects torchlight and creates a cinematic atmosphere.
- + The engraving on the plate armor is intricate and matches the 'ornate' prompt perfectly.
- − The braided hair lacks the requested 'small beads'.
- − The sparks look a bit like floating orange dots rather than organic embers.
Stable Diffusion 3.5 Large Turbo
- + Captured the braided hair well with appropriate depth.
- + Clear interpretation of 'battle-worn' through the inclusion of blood/scars on the face.
- − The image has a visible 'AI plastic' look with overly smooth skin and unnatural hair texture.
- − The lighting is flat and does not convincingly portray 'warm torchlight'.
- − Missing beads in the hair braids despite the specific prompt.
Verdict: FLUX.1 Kontext [max] far outperforms Stable Diffusion 3.5 Large Turbo in terms of photographic realism and lighting. FLUX.1 Kontext [max] captured the texture of the armor and skin with great detail, whereas Stable Diffusion 3.5 Large Turbo produced a more stylized, digital-looking result with less convincing textures.
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 [max]
Stable Diffusion 3.5 Large Turbo
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent professional layout that looks like a real menu.
- + Coherent grid arrangement with clean typography.
- + Realistic food photography that matches the casual dining theme.
- − The text is largely gibberish despite the professional look.
- − Lack of clear headers for separate sections as requested in the prompt.
Stable Diffusion 3.5 Large Turbo
- + Successfully included specific headers for 'Pizza' and 'Mians'.
- + Vibrant, high-contrast food colors.
- − The composition is cluttered and lacks a professional 'menu design' feel.
- − The food looks highly artificial and rubbery.
- − Poor spatial reasoning with items overlapping and floating at odd angles.
Verdict: FLUX.1 Kontext [max] creates a much more believable and professional menu layout that adheres to the 'modern minimalist' aesthetic, whereas Stable Diffusion 3.5 Large Turbo produces a disjointed and cluttered collage. While Stable Diffusion attempted to include the requested section headers, the overall visual quality and professional composition of FLUX.1 Kontext [max] make it the superior design choice.
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 [max]
Stable Diffusion 3.5 Large Turbo
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent typography with perfect spelling and placement.
- + Realistic textures on the food items and ground.
- + Successfully included all requested text elements and the starburst icon.
- − The 'exploded' effect is minimal as the core burger is still stacked.
- − The price is missing the starburst container requested in the prompt.
Stable Diffusion 3.5 Large Turbo
- + Strong sense of heat and fire with effective lighting.
- + Good floating effect for the burger components.
- + Vibrant colors and high-contrast composition.
- − Completely failed to include any of the requested text.
- − Food textures look somewhat artificial and plastic-like compared to Model A.
- − Lacks the specific 'exploded' layout requested, keeping the burger mostly intact.
Verdict: FLUX.1 Kontext [max] is the clear winner as it followed all complex instructions, including rendering all text strings correctly and maintaining high photorealism. Stable Diffusion 3.5 Large Turbo produced a visually striking image but failed completely on all text requirements and felt more like a generic illustration than a specific ad.
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 [max]
Stable Diffusion 3.5 Large Turbo
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent text rendering with perfect spelling and realistic chalk texture.
- + Deeply followed the content prompt, including the specific date and menu items.
- + Very realistic chalkboard aesthetic with smudges and natural handwriting variations.
- − The cursive requirement for the title is not fully met, as it is mostly print-style capitals.
- − The background environment is slightly cluttered and out of focus compared to the clean board.
Stable Diffusion 3.5 Large Turbo
- + Features a stylized, cozy aesthetic with nice lighting and framing.
- + Attempts a more cursive-style font for the title.
- − Severe spelling errors throughout the text (e.g., 'trulale', 'ocotpgs').
- − Failed to include the correct date or prices specified in the prompt.
- − The text looks more like a digital font overlay than natural chalk handwriting.
Verdict: FLUX.1 Kontext [max] is the clear winner as it successfully rendered all the requested text with perfect spelling and a convincing chalk texture. In contrast, Stable Diffusion 3.5 Large Turbo failed significantly on prompt adherence, producing numerous typos and ignoring the specific menu item details.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
FLUX.1 Kontext [max]
Stable Diffusion 3.5 Large Turbo
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent photographic realism and cinematic lighting.
- + High detail in the horse's coat, mane, and the astronaut's suit.
- + Superior atmospheric composition with realistic lens flares and star field.
- − Failed the negative constraint; the astronaut is riding the horse instead of vice-versa.
Stable Diffusion 3.5 Large Turbo
- + Clean aesthetic with high contrast.
- + Good rendering of the planet's curve in the background.
- − Failed the negative constraint; the astronaut is riding the horse.
- − The horse has anatomical issues with its hooves and anatomy near the rear legs.
- − Shadows on the planet surface are inconsistent with the surrounding light.
Verdict: Both models failed the specific spatial instruction for a 'horse on top' of the astronaut, providing a standard astronaut-riding-horse image instead. However, FLUX.1 Kontext [max] is the significantly better image due to its superior photographic detail, realistic textures, and cinematic lighting compared to the anatomical errors and flatter rendering in 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.1 Kontext [max]
Stable Diffusion 3.5 Large Turbo
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent fur texture rendering on the capybara
- + Clearer text on the taxi hat
- + Better lighting integration with the night street scene
- − The passenger is holding a phone to her ear instead of looking at it
Stable Diffusion 3.5 Large Turbo
- + Successfully placed both paws on the steering wheel as requested
- + More cinematic depth of field with background bokeh
- − The capybara's face looks slightly less realistic and more like a hybrid
- − Text on the hat is distorted
- − The passenger is less clearly defined in the background
Verdict: FLUX.1 Kontext [max] produces a much more photorealistic image with superior textures and logical lighting, though it missed the specific detail of the passenger looking at the phone. Stable Diffusion 3.5 Large Turbo followed the placement of the paws better but suffered from lower facial realism on the capybara and distorted text.
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 [max]
Stable Diffusion 3.5 Large Turbo
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent typography rendering with almost perfect spelling and formatting.
- + Perfectly captures the 'dark parchment' and 'cinematic lighting' requested in the prompt.
- + Atmospheric and detailed border featuring webs and thorns.
- − Included the location twice in slightly different formats at the bottom.
- − The date uses commas as separators instead of dots/periods as requested.
Stable Diffusion 3.5 Large Turbo
- + Includes multiple glowing jack-o-lanterns with good lighting effects.
- + Clear, high-contrast composition that is easy to read.
- − Failed to include the majority of the requested text, including the scroll banner and event details.
- − The art style feels more like a modern clip-art vector than a 'vintage gothic' invitation.
- − The title text is incomplete, saying only 'Halloween Party'.
Verdict: FLUX.1 Kontext [max] is the clear winner as it successfully incorporated almost all the complex text requirements with high fidelity. While Stable Diffusion 3.5 Large Turbo created a clean image, it failed to follow the instructions for the scroll banner, specific event details, and the requested vintage gothic aesthetic.
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 [max]
Stable Diffusion 3.5 Large Turbo
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent text rendering with no spelling errors
- + Accurate 45-degree isometric perspective
- + High-quality soft lighting and 3D textures
- − Missed the small flag icon request
Stable Diffusion 3.5 Large Turbo
- + Includes a flag icon as requested
- + Good isometric diorama composition
- + Clean 3D rendering style
- − Significant spelling error in the text ('SIIHI')
- − The flag design is generic and does not accurately represent the Japanese flag
- − Text is slanted on signposts rather than floating top-center as requested
Verdict: FLUX.1 Kontext [max] produced a much higher quality image with perfect spelling and a clean, professional aesthetic that matches the 'soft refined textures' prompt perfectly. While it missed the flag icon, Stable Diffusion 3.5 Large Turbo failed significantly on text accuracy and provided a flag that bore little resemblance to Japan's, making FLUX.1 Kontext [max] the clear winner.
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 [max]
Stable Diffusion 3.5 Large Turbo
AI Judge Analysis
FLUX.1 Kontext [max]
- + Successfully includes all four requested animals (dog, cat, rabbit, fox).
- + Excellent lighting with clear god rays and a warm sunrise atmosphere.
- + Cohesive composition that captures the requested 'playful' and 'wholesome' vibe.
- − The rabbit's face looks slightly anthropomorphic compared to the other animals.
- − Some butterfly wings look a bit blurry or poorly defined.
Stable Diffusion 3.5 Large Turbo
- + Strong backlighting creates a beautiful rim light effect on the fur.
- + Very sharp focus on the central characters.
- − Fails to include the bunny and fox, showing only a puppy and two kittens.
- − The fur texture looks overly smoothed or digital, lacking true hyper-photorealism.
- − The butterfly on the right has anatomically strange wing attachment.
Verdict: FLUX.1 Kontext [max] is the clear winner as it followed the complex prompt by including all four distinct animals and capturing the specific 'god rays' lighting requested. Stable Diffusion 3.5 Large Turbo failed on prompt adherence by omitting the fox and bunny, and its overall style feels more like a digital illustration than the requested hyper-photorealistic masterpiece.
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 [max]
Stable Diffusion 3.5 Large Turbo
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent typography with clean, retro-style serif fonts.
- + Perfect adherence to the vector emblem and minimalist aesthetic.
- + High-quality subtle paper texture that matches the vintage prompt.
- − The steam icon is a bit simple compared to the rest of the illustration.
Stable Diffusion 3.5 Large Turbo
- + Stronger visual focus on the cloche dome element.
- + Rich color depth with effective use of warm brown and cream tones.
- − Misspelled name as 'Caffeé Florin' and has messy letter artifacts at the end of the text.
- − Less minimalist than requested, leaning more towards a complex illustration than a logo.
- − The design of the cloche combined with a handle makes it look confusingly like a mug.
Verdict: FLUX.1 Kontext [max] is the clear winner as it produced a professional, clean vector logo with perfect spelling and a sophisticated minimalist style. Stable Diffusion 3.5 Large Turbo failed on typography, misspelling the restaurant name and including graphical artifacts in the text banner, while also creating a confusing cloche-mug hybrid object.
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 [max]
Stable Diffusion 3.5 Large Turbo
AI Judge Analysis
FLUX.1 Kontext [max]
- + Successfully visualizes a complex trajectory diagram with multiple stages.
- + Captures a cohesive mid-century modern vector aesthetic.
- + High resolution with clean, sharp lines and a pleasing color palette.
- − Internal labels are nonsensical and factually incorrect (e.g., Earth is labeled 'Moon').
- − Includes a random ringed planet (Saturn) which confuses the Apollo 11 theme.
- − The rocket design is a generic retro rocket rather than the requested Saturn V.
Stable Diffusion 3.5 Large Turbo
- + Excellent structural layout for an infographic with clearly defined sections.
- + Strong adherence to the NASA-inspired color palette and flat-vector style.
- + Iconography is consistent and grouped logically on the left side.
- − Text rendering is very poor with several misspellings and 'lorem ipsum' style filler.
- − Failed to include all six specific steps requested in the prompt.
- − The main visual focal point is a generic astronaut rather than the mission stages.
Verdict: FLUX.1 Kontext [max] performs better at creating a complex, integrated visual narrative of a space mission, but it suffers from severe logical errors in its labeling and celestial bodies. Stable Diffusion 3.5 Large Turbo produces a more professional-looking infographic layout that adheres better to the requested style, but it fails to include most of the specific content steps requested. Stable Diffusion 3.5 Large Turbo is the likely winner for its superior composition and stylistic consistency as an infographic design.
Next steps
Explore each model
Distilled version of SD 3.5 Large that generates high-quality images in just 4 steps, offering faster inference and reduced costs