Black Forest Labs' state-of-the-art image generation model with maximum quality and speed, supporting text-to-image and multi-reference image editing with up to 4MP output
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
FLUX.2 [pro]
26.3
arena score
#8 of 62 in Text-to-Image
Skill signature
· Text-to-Image
Stable Diffusion 3.5 Medium
16.8
arena score
#58 of 62 in Text-to-Image
Vote tally
Where the votes landed
FLUX.2 [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.”
FLUX.2 [pro]
Stable Diffusion 3.5 Medium
AI Judge Analysis
FLUX.2 [pro]
- + Excellent photo-realistic lighting and texture rendering.
- + Perfect adherence to the spatial arrangement requested.
- + Clean, sharp edges on the glass cube and realistic wood grain.
- − The plant is very bokeh-blurred, making it slightly less 'visible through the glass' than it could be.
Stable Diffusion 3.5 Medium
- + Successfully includes all requested elements in the frame.
- + The plant is clearly visible through the glass cube.
- − The blue sphere appears to be floating unnaturally in the center without support.
- − Visual quality is lower with some digital artifacts and less realistic textures.
- − The red book looks slightly distorted where it meets the glass.
Verdict: FLUX.2 [pro] produced a high-quality, professional-looking photograph with realistic physics and lighting, whereas Stable Diffusion 3.5 Medium struggled with the weight of the objects, resulting in a floating sphere. FLUX.2 [pro] is the clear winner due to its superior texture rendering and composition.
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 [pro]
Stable Diffusion 3.5 Medium
AI Judge Analysis
FLUX.2 [pro]
- + Excellent photographic quality with realistic skin texture and rain effects.
- + Accurate bicycle mechanics including a realistic chain and gear system.
- + Superb handling of the bokeh and depth of field as requested in the 50mm prompt.
- − The 'imperfect framing' is subtle, leaning towards a very professional composition.
Stable Diffusion 3.5 Medium
- + Successfully captures a more grainier, film-like candid aesthetic.
- + Includes the requested motion blur on the passing car in the background.
- − Anatomical issues with the man's hands merging into the bicycle handlebars.
- − The bicycle geometry is nonsensical, with frame bars intersecting and disconnected parts.
- − Overall lower resolution and visible AI artifacts on the man's face.
Verdict: FLUX.2 [pro] is the clear winner, delivering a high-fidelity image that looks like an actual photograph with realistic light physics and complex mechanical details like the bicycle chain. Stable Diffusion 3.5 Medium struggles significantly with the basic structure of the bicycle and the human hands, failing to maintain coherence despite capturing the general mood of the prompt.
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 [pro]
Stable Diffusion 3.5 Medium
AI Judge Analysis
FLUX.2 [pro]
- + Excellent adherence to all prompt elements, specifically the beads in the braids.
- + Exceptional texture work on the leather straps and weathered cloth.
- + Very realistic skin tones and subtle grit/scars.
- − The bokeh sparks appear a bit overly uniform in their distribution.
Stable Diffusion 3.5 Medium
- + Strong dramatic lighting and intense facial expression.
- + High-contrast color palette with good metallic sheen.
- + Intricate engraving on the pauldrons.
- − Failed to include the requested beads in the braided hair.
- − Some lighting artifacts on the bridge of the nose look like skin texture errors.
- − Cloth underlayer is less detailed compared to Model A.
Verdict: FLUX.2 [pro] captures every detail of the prompt, including the specific request for beads in the hair and high-texture leather straps, with a very balanced and realistic composition. Stable Diffusion 3.5 Medium delivers a striking and cinematic image but misses the beads and has slightly less convincing skin and cloth 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.2 [pro]
Stable Diffusion 3.5 Medium
AI Judge Analysis
FLUX.2 [pro]
- + Excellent typography with legible headers and item names
- + Clean and organized grid layout consistent with professional graphic design
- + Accurate sections for 'Appetizers', 'Pizza', and 'Mins' (Mains)
Stable Diffusion 3.5 Medium
- + Good variety of food photography within the grid
- + Clean white background consistent with the minimalism request
- − Text is largely illegible garble or gibberish
- − The layout is cluttered and lacks hierarchical flow
- − Font is messy and does not match the 'bold sans-serif' professional requirement
Verdict: FLUX.2 [pro] followed all prompt instructions perfectly, creating a functional menu with legible typography and a logical layout. Stable Diffusion 3.5 Medium failed significantly on text rendering and general design cohesion, producing a result that looks like a rough sketch rather than a professional menu.
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 [pro]
Stable Diffusion 3.5 Medium
AI judge analysis unavailable for this challenge.
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 [pro]
Stable Diffusion 3.5 Medium
AI Judge Analysis
FLUX.2 [pro]
- + Perfect text accuracy with zero spelling errors for all requested items.
- + Highly realistic chalk texture with dusty particles and authentic handwriting variations.
- + Excellent adherence to the 'elegant cursive' style for the title and menu items.
- − The chalkboard surface is a bit small/narrow, making the layout feel slightly cramped vertically.
Stable Diffusion 3.5 Medium
- + Captures a wide-shot composition of a framed chalkboard well.
- + Decorative chalk flourishes add to the 'café' aesthetic.
- − Extremely poor text rendering with numerous spelling errors and garbled characters.
- − Failed to follow the specific date and price instructions correctly.
- − The layout is messy and incoherent compared to the prompt's request for a clear menu.
Verdict: FLUX.2 [pro] followed the prompt with near-perfect execution, rendering every word of the specific menu accurately with a beautiful, realistic chalk texture. In contrast, Stable Diffusion 3.5 Medium failed significantly on the text-rendering aspect of the challenge, producing illegible words and incorrect information throughout the board.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
FLUX.2 [pro]
Stable Diffusion 3.5 Medium
AI Judge Analysis
FLUX.2 [pro]
- + Successfully follows the logic-defying prompt of horse riding the astronaut.
- + Superior cinematic lighting and background detail with multiple galaxies.
- + High-quality rendering of the spacesuit and horse textures.
Stable Diffusion 3.5 Medium
- + Clear, high-contrast imagery.
- + Good perspective of earth from space.
- − Fails the specific prompt instruction to have the horse on top.
- − Anatomical issues with the horse's legs appearing disjointed/elongated.
- − Lower overall detail and lacks a 'cinematic' feel compared to the competitor.
Verdict: FLUX.2 [pro] followed the complex spatial instructions perfectly, depicting a horse literally standing on an astronaut/centaur hybrid in a surreal way. Stable Diffusion 3.5 Medium failed the 'horse on top' requirement, providing a standard astronaut-riding-horse image with significant anatomical errors 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 [pro]
Stable Diffusion 3.5 Medium
AI Judge Analysis
FLUX.2 [pro]
- + Excellent photorealism with realistic bokeh and interior lighting
- + Perfect adherence to the businesswoman's pose and expression regarding the phone
- + Anatomically plausible interaction between the capybara's paws and the steering wheel
- − The capybara's paws are rendered with black gloves, which wasn't specifically requested but helps with the anthropomorphic look
Stable Diffusion 3.5 Medium
- + Front-facing composition is engaging and symmetrical
- + Correctly identifiable capybara with a professional hat
- − Failed to include the businesswoman looking at her phone; she is looking forward
- − The capybara's paws are small and not physically gripping the steering wheel
- − Lower overall resolution and clarity compared to the competition
Verdict: FLUX.2 [pro] followed all prompt instructions, including the specific behavior of the passenger and the positioning of the driver's paws. Stable Diffusion 3.5 Medium missed the detail about the passenger's phone and produced a much less realistic interior and overall image quality.
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 [pro]
Stable Diffusion 3.5 Medium
AI Judge Analysis
FLUX.2 [pro]
- + Perfect text rendering of all requested information across three distinct sections.
- + Excellent cinematic lighting with a central glowing jack-o-lantern.
- + The thorny web border is intricate and fits the dark parchment theme perfectly.
- − The parchment texture is a bit dark, making the lower text contrast slightly less than the top.
Stable Diffusion 3.5 Medium
- + Good color palette for a vintage theme.
- + Nice inclusion of twisted trees and cobwebs.
- − Significant spelling errors throughout the text (e.g., 'Halloweeen Inviloween').
- − Failed to include the specific year 2026 and mangled the banner text.
- − Multiple jack-o-lanterns instead of a central one as requested.
Verdict: FLUX.2 [pro] followed every detail of the prompt, providing error-free text and a visually striking composition with high-quality cinematic lighting. Stable Diffusion 3.5 Medium struggled significantly with text legibility and failed to follow the layout instructions for a central pumpkin and specific date.
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 [pro]
Stable Diffusion 3.5 Medium
AI Judge Analysis
FLUX.2 [pro]
- + Perfectly followed text instructions with large bold 'JAPAN' and 'SUSHI' text.
- + Excellent adherence to the 'raised diorama base' and 'isometric' composition requests.
- + Clean, distinct 3D cartoon style with high-quality PBR-like textures.
- − The 45° angle is slightly more eye-level than a true top-down isometric view.
Stable Diffusion 3.5 Medium
- + Strong vibrant colors and high-contrast lighting.
- + Correct inclusion of 'JAPAN' and 'SUSHI' text, though layout is less balanced.
- − Missing requested elements like the small flag icon and the raised diorama base.
- − Text rendering is messy with a floating dot over the 'I' and a semi-transparent 'S'.
- − Background has noticeable grain/noise instead of being a solid clean color.
Verdict: FLUX.2 [pro] is the clear winner as it followed every instruction in the prompt, including the complex request for a diorama base and specific text layout. Stable Diffusion 3.5 Medium failed to produce a clean background, missed the flag icon and diorama base, and had significant artifacts in the typography.
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 [pro]
Stable Diffusion 3.5 Medium
AI Judge Analysis
FLUX.2 [pro]
- + Excellent adherence to the prompt by including all four specific animals requested.
- + Superb fur texture and realistic animal proportions.
- + Sophisticated lighting with soft god rays and atmospheric depth.
- − Physical interaction between the kitten and the puppy's ear is slightly awkward.
- − The butterflies are somewhat stationary rather than 'chasing' as requested.
Stable Diffusion 3.5 Medium
- + Strong vibrant colors and clear gold-hour lighting.
- + High contrast and sharp focus on the central characters.
- − Failed to include the requested baby bunny.
- − The animals have a saturated, slightly AI-stylized look rather than the requested hyper-photorealism.
- − The cat/fox hybrid in the center lacks clear species definition.
Verdict: FLUX.2 [pro] successfully rendered all four requested animals with a high degree of photorealism and beautiful atmospheric lighting. Stable Diffusion 3.5 Medium missed the bunny entirely and produced a more saturated, digital art style that deviated from the photorealistic requirement.
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 [pro]
Stable Diffusion 3.5 Medium
AI Judge Analysis
FLUX.2 [pro]
- + Excellent text rendering with correct spelling and accents.
- + Clean, professional vector style that matches the minimalist request.
- + Perfect adherence to all prompt elements including the banner and dates.
Stable Diffusion 3.5 Medium
- + Captures a strong vintage hand-drawn aesthetic.
- + Detailed line work gives a classic engraved feel.
- − Multiple spelling errors in the brand name ('Florrian').
- − Failed to include the correct date ('Est 170' instead of '1720').
- − The composition is cluttered and lacks' the requested minimalism.
Verdict: FLUX.2 [pro] followed the prompt with high precision, delivering a clean, professional logo with perfect typography and composition. Stable Diffusion 3.5 Medium struggled significantly with the text, introducing several spelling and numerical errors, and produced a much busier illustration than the 'minimalist' style requested.
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 [pro]
Stable Diffusion 3.5 Medium
AI Judge Analysis
FLUX.2 [pro]
- + Excellent layout that follows a logical descending flow consistent with an infographic.
- + High-quality vector aesthetic with clean iconography and professional font rendering for headings.
- + Strict adherence to the NASA-inspired color palette and requested flight stages.
- − Nonsense filler text for the small supporting descriptions.
- − The 'Launch' icon resembles a generic shuttle rather than a Saturn V.
Stable Diffusion 3.5 Medium
- + Creative use of radial composition and arcing lines to suggest orbital mechanics.
- + Successfully captures the muted red and navy palette requested.
- − Poor typography and spelling throughout the entire image.
- − Confusing iconography where 'Launch' and 'Descent' stages do not match the visual labels.
- − Overall composition feels cluttered and lacks the professional 'clean' look requested.
Verdict: FLUX.2 [pro] followed the prompt much more effectively, producing a clean and legible infographic with professional-grade vector illustrations. Stable Diffusion 3.5 Medium struggled with layout coherence, text rendering, and specific icon accuracy, making it significantly less useful as a poster.
Next steps
Explore each model
Stability AI's 2.5-billion parameter Multimodal Diffusion Transformer with improvements (MMDiT-X) text-to-image model optimized for consumer hardware, featuring improved image quality, typography, and complex prompt understanding