Black Forest Labs' flagship image generation model delivering state-of-the-art quality with exceptional realism, precision, and consistency for both text-to-image and advanced image editing
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
FLUX.2 [max]
25.8
arena score
#10 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 [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.2 [max]
Stable Diffusion 3.5 Large Turbo
AI Judge Analysis
FLUX.2 [max]
- + Perfect adherence to all spatial instructions in the prompt.
- + Highly realistic textures, especially the leather binding and glass thickness.
- + Natural, soft lighting and depth of field that feels like a real photograph.
- − The plant in the background is quite blurry, though it is visible through the glass as requested.
Stable Diffusion 3.5 Large Turbo
- + Clean rendering of the glass and sphere.
- + Clear visibility of the plant through the glass.
- − Failed the spatial logic by placing the book inside the cube instead of on top.
- − Unrealistic interaction between the book and the cube's frame.
- − The lighting on the wall does not match the shadows on the table.
Verdict: FLUX.2 [max] followed every detail of the prompt accurately, including the specific placement of the red book on top of the cube. Stable Diffusion 3.5 Large Turbo struggled with the spatial relationships, placing the book inside the cube and merging it into the frame, resulting in a less realistic and less accurate image.
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 Large Turbo
AI Judge Analysis
FLUX.2 [max]
- + Excellent photorealism with natural skin texture and wet surfaces.
- + Accurately depicts specific prompt details like motion blur from cars and shallow depth of field.
- + The bicycle and environment look physically coherent and grounded in reality.
- − The hands show some slight anatomical distortion during the intricate task.
Stable Diffusion 3.5 Large Turbo
- + Successfully includes the red bicycle and an elderly man as requested.
- + Attempts a cinematic color palette.
- − The bicycle frame geometry is physically impossible and nonsensical.
- − Lacks the requested motion blur, reflections, and realistic rain effects.
- − The character's posture and anatomy are unnatural, and the face is obscured.
Verdict: FLUX.2 [max] significantly outperformed the competitor by delivering a highly realistic, cinematic street photo that captured every nuance of the prompt, including the difficult-to-render textures of wet pavement and skin. In contrast, Stable Diffusion 3.5 Large Turbo failed to produce a coherent bicycle structure or a believable environment, resulting in a flat, artificial-looking image that ignored several aesthetic keywords.
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 Large Turbo
AI Judge Analysis
FLUX.2 [max]
- + Exquisite texture on the metal engravings and leather straps
- + Realistic skin detailing with believable dirt and fine scars
- + Excellent integration of warm torchlight and glowing bokeh particles
- − The transition of the hair into the beads is slightly blurry in some spots
Stable Diffusion 3.5 Large Turbo
- + Strong prompt adherence regarding the braids
- + Clean and vibrant colors
- − The blood/dirt on the face looks like flat paint rather than a battle-worn texture
- − The lighting feels artificial and lacks the warm interplay of torchlight on metal
- − Textures on the armor and skin appear plastic-like and smoothed over
Verdict: FLUX.2 [max] significantly outperforms the competition by providing a high level of cinematic realism and material accuracy; the texture on the leather and the tarnished metal feels tangible. In contrast, Stable Diffusion 3.5 Large Turbo produces a more stylized, almost airbrushed result where the 'battle-worn' elements look like makeup and the lighting lacks 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.”
FLUX.2 [max]
Stable Diffusion 3.5 Large Turbo
AI Judge Analysis
FLUX.2 [max]
- + Excellent typography with legible headers and price alignment.
- + Photorealistic food images that look appetizing and professional.
- + Clean, logical layout that functions effectively as a real-world document.
- − Small body text and descriptions are nonsensical gibberish.
- − The grid is a bit tight on the left column.
Stable Diffusion 3.5 Large Turbo
- + Creative top-down photography style.
- + Vibrant and saturated color palette.
- − Layout is cluttered and doesn't resemble a professional menu design.
- − Text is completely illegible and lacks actual section headers like Appetizers.
- − Food images look like plastic or 3D renders rather than real food.
Verdict: FLUX.2 [max] significantly outperforms Stable Diffusion 3.5 Large Turbo by creating an actual usable menu layout with clear typography and professional food photography. While the small text in FLUX.2 is gibberish, the overall structure, branding elements, and image quality are far superior to the chaotic and artificial-looking arrangement provided by Stable Diffusion 3.5.
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 Large Turbo
AI Judge Analysis
FLUX.2 [max]
- + Perfect adherence to all text requirements including price and secondary messaging.
- + Highly realistic texture on the bun, meat, and vegetables.
- + Excellent composition with dynamic movement and the 'exploded' effect requested.
- − The glowing effect on the price starburst is less 'fiery' and more of a standard graphic overlay.
Stable Diffusion 3.5 Large Turbo
- + Visually striking fire and smoke effects that create a high-drama atmosphere.
- + Vibrant colors and high-contrast lighting.
- − Completely failed to include any of the requested text elements.
- − The burger is mostly intact rather than 'exploded' into individual suspended components.
- − The bottom of the burger appears to be melting or turning into liquid rather than being food.
Verdict: FLUX.2 [max] followed the prompt instructions near-perfectly, successfully integrating all three requested text fields and the specific 'exploded' layout. Stable Diffusion 3.5 Large Turbo failed to include any text and missed the core 'exploded' structural requirement, resulting in a more generic (though atmospheric) image.
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 Large Turbo
AI Judge Analysis
FLUX.2 [max]
- + Perfect text adherence with every requested word and date spelled correctly.
- + Highly realistic chalk texture with smudges and natural variations in the wood and board.
- + Excellent lighting and atmosphere that fits the 'cozy café' prompt.
- − The cursive is more of a casual script than 'elegant cursive' as requested.
Stable Diffusion 3.5 Large Turbo
- + Includes a wider composition showing the café counter and plants.
- + Captures the concept of a chalkboard in a modern setting.
- − Extremely poor text rendering with numerous spelling errors like 'apri 3l 20-', 'trulale', and 'ocotpgs'.
- − The text looks like a digital font rather than natural handwritten chalk texture.
- − Failed to follow the requested layout and menu items.
Verdict: FLUX.2 [max] significantly outperformed Stable Diffusion 3.5 Large Turbo by delivering perfect text accuracy and a convincing hand-drawn chalk aesthetic. Stable Diffusion 3.5 Large Turbo struggled with basic legibility, failed to complete the date, and the letters lacked the requested chalk texture, appearing more like digital glyphs.
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 Large Turbo
AI Judge Analysis
FLUX.2 [max]
- + Excellent cinematic lighting and detail on the spacesuit and horse's mane.
- + Rich, detailed background with a vibrant galaxy and realistic asteroid.
- + Strong artistic composition with a clear sense of depth.
- − Failed the negative constraint; the astronaut is riding the horse instead of the horse riding the astronaut.
Stable Diffusion 3.5 Large Turbo
- + Dynamic sense of movement and speed in the composition.
- + Clean, high-contrast visual style.
- − Failed the negative constraint; the astronaut is riding the horse.
- − Significant anatomical issues with the horse's legs and hooves.
- − The planet/moon in the background looks poorly rendered and simplistic.
Verdict: Both models failed the specific instruction to have the 'horse on top' (horse riding astronaut), instead producing the common trope of an astronaut riding a horse. FLUX.2 [max] is the superior image due to its significantly higher technical quality, realistic textures, and complex background, whereas Stable Diffusion 3.5 Large Turbo suffered from anatomical distortions in the horse's limbs.
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 Large Turbo
AI Judge Analysis
FLUX.2 [max]
- + Excellent photographic lighting and textures on the capybara fur and jacket
- + Strong adherence to the businesswoman's bored expression and her interaction with the phone
- + Detailed dashboard and realistic taxi interior depth
- − The capybara has realistic human hands instead of paws as requested
Stable Diffusion 3.5 Large Turbo
- + Successfully depicted capybara paws on the steering wheel instead of human hands
- + Crisp, vibrant colors and high contrast
- − Failed to show the businesswoman looking at a phone
- − The capybara's head shape and anatomy feel less natural than model A
- − The background passenger is out of focus and lacks the requested bored expression
Verdict: FLUX.2 [max] produced a much more convincing photorealistic scene with a clear story and superior detail in the passenger seat, although it hallucinated human hands for the capybara. Stable Diffusion 3.5 Large Turbo followed the prompt regarding 'paws' more accurately, but failed on the specific details of the passenger and the overall cinematic quality of the interior.
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 Large Turbo
AI Judge Analysis
FLUX.2 [max]
- + Excellent typography rendering for both the main title and the small scroll banner
- + Authentic cinematic lighting and moody gothic atmosphere
- + Strong adherence to all requested elements including specific event details and date
- − The parchment texture is a bit dark in the bottom half, making the trees less distinct
Stable Diffusion 3.5 Large Turbo
- + Illustrative style with clean lines and high contrast
- + Good framing with the decorative thorns and webs
- − Failed to include critical prompt elements like the scroll banner and event details
- − The title is truncated and has a spelling/font artifact in the word 'Party'
- − Lighting feels flat and digital rather than 'cinematic' as requested
Verdict: FLUX.2 [max] significantly outperformed Stable Diffusion 3.5 Large Turbo by accurately including all requested text, including the specific date and location which were entirely missing from the second image. FLUX.2 [max] also captured the 'cinematic' and 'vintage gothic' aesthetic much more effectively with its use of texture and lighting, whereas Stable Diffusion 3.5 Large Turbo produced a more generic, simplified illustration with broken text.
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 Large Turbo
AI Judge Analysis
FLUX.2 [max]
- + Perfectly renders both requested text fields with clean typography.
- + Strictly adheres to the small raised diorama and light blue background instructions.
- + Accurately renders the Japanese flag icon as requested.
- − The 3D model textures are slightly more matte and simplified than true PBR materials.
- − Small gap in the 'wooden' texture on the left side of the block.
Stable Diffusion 3.5 Large Turbo
- + Excellent rice grain detail and material textures.
- + Creative use of 3D signage within the scene.
- − Spelling error in the secondary text ('SIIHI' instead of 'SUSHI').
- − Failed to include the Japanese flag (renders a red and white rectangle instead).
- − Background is a dark greyish-blue gradient rather than the requested solid light blue.
Verdict: FLUX.2 [max] followed every instruction meticulously, including difficult text rendering and specific layout requirements like the flag icon and the solid blue background. Stable Diffusion 3.5 Large Turbo had superior texture detail on the food itself, but failed on text spelling, flag accuracy, and background color.
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 Large Turbo
AI Judge Analysis
FLUX.2 [max]
- + Excellent adherence to the prompt by including all four distinct animals
- + Realistic lighting with convincing god rays and dew sparkles
- + Natural-looking fur textures and proportional anatomy
- − The fox kit has somewhat odd black front paws that look slightly detached
Stable Diffusion 3.5 Large Turbo
- + Bright, vibrant colors that pop
- + Cute, stylized expressive eyes
- − Failed to include the bunny and fox, providing only ambiguous kitten/puppy creatures
- − Low visual quality with blurred textures and a digital, CGI-like appearance
- − Proportions are warped, with floating limbs and inconsistent anatomy
Verdict: FLUX.2 [max] significantly outperformed the competition by accurately rendering all four requested animals (puppy, kitten, bunny, and fox) in a cohesive, realistic scene. In contrast, Stable Diffusion 3.5 Large Turbo failed the prompt instructions, omitting two species entirely and producing a lower-quality image with anatomical errors and a less realistic finish.
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 Large Turbo
AI Judge Analysis
FLUX.2 [max]
- + Excellent typography including the correct grave accent on the letter E.
- + Clean, minimalist vector style that perfectly follows the prompt.
- + Professional composition with balanced circular framing and an integrated banner.
- − The 'steam' lines are a bit thin and could be more stylized.
- − The texture is very subtle, almost unnoticeable.
Stable Diffusion 3.5 Large Turbo
- + Strong high-contrast shading gives the image a bold vintage feel.
- + Creative integration of a cloche lid on a coffee mug shape.
- − Text spelling error with 'Caffeé' using two Es and an incorrect accent.
- − The typography is messy with strange artifacts on the letter 'n'.
- − Less minimalist than requested, leaning more towards a complex illustration than a vector emblem.
Verdict: FLUX.2 [max] produced a high-quality, professional logo that accurately follows all prompt instructions, including precise spelling and a clean vector aesthetic. Stable Diffusion 3.5 Large Turbo failed on text accuracy and had significant artifacts in the lettering, resulting in a much less usable logo.
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 Large Turbo
AI Judge Analysis
FLUX.2 [max]
- + Excellent text legibility and spelling of key mission terms.
- + Strict adherence to the 1-6 step sequence and logical flow.
- + High-quality vector graphics that perfectly match the flat-vector style requested.
- − The rocket in the first panel looks more like a shuttle than a Saturn V.
- − Labeling conflicts where 'Earth Orbit' appears above three different icons.
Stable Diffusion 3.5 Large Turbo
- + Strong aesthetic appeal with a vintage NASA-inspired color palette.
- + Good use of space and illustrative dynamic composition.
- − Significant spelling errors and gibberish text throughout the poster.
- − Failed to follow the numbered 6-step logical sequence of the mission.
- − General iconography is messy and fails the clean vector requirement.
Verdict: FLUX.2 [max] is the clear winner as it successfully creates a functional infographic with legible text and a logical progression of the mission steps. While Stable Diffusion 3.5 Large Turbo captures a nice retro aesthetic, it fails to deliver on the required content structure and the text is largely nonsensical.
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