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
Qwen Image 2512
22.9
arena score
#30 of 62 in Text-to-Image
Vote tally
Where the votes landed
FLUX.2 [max]
70.0%
win rate
Ties
0.0%
Qwen Image 2512
30.0%
win rate
70.0%
0.0% ties
30.0%
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]
Qwen Image 2512
67% wins
0% ties
33% wins
AI Judge Analysis
FLUX.2 [max]
- + Excellent photographic realism with a high-end lens feel.
- + Accurate and aesthetically pleasing lighting from the left.
- + Clean, sharp rendering of the glass cube and its reflections.
- − The sphere appears more like a glass marble than a simple sphere, adding extra internal reflections.
Qwen Image 2512
- + Good adherence to all prompt elements.
- + Solid composition with clear visibility of the plant through the glass.
- + Realistic texture on the red book cover.
- − The glass has a heavy cyan/green tint compared to the neutral transparency of Model A.
- − Lighting feels a bit flatter and less dynamic.
Verdict: FLUX.2 [max] produces a much more professional and polished image with superior lighting and reflections. While both models followed the spatial prompt perfectly, FLUX.2 [max] has a cleaner aesthetic and more realistic glass rendering compared to the tinted glass in Qwen Image 2512.
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]
Qwen Image 2512
AI Judge Analysis
FLUX.2 [max]
- + Excellent adherence to the 'repairing' action, showing the man physically working on the wheel hub.
- + Superior rendering of wet textures and reflections on the pavement.
- + High level of anatomical and mechanical detail, including realistic hand aging and bicycle components.
- − The motion blur on the background car is slightly more static than 'passing' cars often look.
- − The framing is a bit tight on the subject, though it fits the 'imperfect' request.
Qwen Image 2512
- + Strong bokeh effect and cinematic 50mm lens look.
- + Captures the 'imperfect' and 'candid' feel with a more centered, snapshot-like composition.
- + Good skin texture and expressive facial features.
- − The subject is posing with the bike rather than 'repairing' it as requested.
- − Noticeable anatomical issues with the left hand resting on the seat.
- − The bicycle frame geometry is slightly warped/incoherent near the front.
Verdict: FLUX.2 [max] is the superior model here because it accurately captures the 'repairing' action with high technical fidelity and realistic textures. While Qwen Image 2512 captures a nice mood, the man is simply sitting next to the bike, and the image contains several AI artifacts in the hands and bicycle frame.
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]
Qwen Image 2512
0% wins
0% ties
100% wins
AI Judge Analysis
FLUX.2 [max]
- + Excellent metal texture and intricate engraving details.
- + Dynamic composition with a strong emotional gaze.
- + High fidelity on the skin texture and scars.
- − The beads in the hair are a bit small and less distinct than requested.
- − Lighting is a bit flat across the face compared to the torch effect in the background.
Qwen Image 2512
- + Strong adherence to the 'beads' and 'braided' hair portion of the prompt.
- + Atmospheric lighting with clear interaction between the torch and the character's face.
- + Accurate representation of the leather straps and buckle.
- − The facial features look slightly more generic/AI-typical.
- − Armor engraving is slightly lower resolution than Model A.
- − Some messy hair strands near the top look a bit artificial.
Verdict: Both models captured the prompt effectively, but FLUX.2 [max] produced a more striking and high-fidelity portrait with superior metalwork textures. Qwen Image 2512 followed several specific prompt keywords better, such as the beads and the physical torch presence, but the overall image quality and realism of the character in FLUX.2 [max] are more impressive.
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]
Qwen Image 2512
100% wins
0% ties
0% wins
AI Judge Analysis
FLUX.2 [max]
- + Excellent adherence to the grid layout for food photos.
- + Very clean, legible typography and high-quality font rendering.
- + Clear separation of the requested sections: Appetizers, Pizza, and Mains.
- − Small icons at the bottom and some descriptive text names are gibberish.
- − The 'Appetizers' section contains photos of pizzas and burgers, causing internal logic inconsistency.
Qwen Image 2512
- + Good use of vibrant colors and high-contrast food photography.
- + Dynamic and modern composition with a central header.
- + Follows the requested grid layout for the top half of the design.
- − Text is highly distorted and mostly illegible throughout the menu.
- − Sections are misspelled or combined incorrectly (e.g., 'Appetiizers', '/Means').
- − Overall layout feels more cluttered and less professional than the alternative.
Verdict: FLUX.2 [max] is the superior model because it produces a clean, professional, and highly legible menu layout that closely follows the design prompt. While Qwen Image 2512 has vibrant food photography, its text rendering and spelling are significantly worse, making the menu non-functional as a graphic design piece.
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]
Qwen Image 2512
AI Judge Analysis
FLUX.2 [max]
- + Excellent text legibility and alignment
- + Photorealistic food textures, especially the bun and sauce
- + Clean, professional graphic design layout
- − The 'exploded' effect is less dynamic with larger, more static gaps
- − The starburst is a bit too clean and lacks the requested fiery/glowing effect
Qwen Image 2512
- + Highly dynamic 'exploded' composition with a strong sense of motion
- + Excellent integration of fiery effects into the 'MAGIC BURGER' text and starburst
- + Visually rich background with realistic depth and embers
- − Secondary text 'LIMITED TIME ONLY' is missing the word 'TIME'
- − The patty texture looks slightly less realistic than Model A
Verdict: Both models followed the prompt well, but Qwen Image 2512 captured the 'fiery' and 'dynamic' essence much more effectively than FLUX.2 [max], despite a minor text error. FLUX.2 [max] produced a cleaner, more readable advertisement but felt more like a static assembly than an explosion.
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]
Qwen Image 2512
AI Judge Analysis
FLUX.2 [max]
- + Perfectly handles all requested text with 100% spelling accuracy
- + Excellent chalk texture and realistic smudge marks on the board
- + Maintains high resolution and realistic lighting from the overhead lamp
- − The handwriting style is a bit uniform, bordering on looking like a digital font despite the texture
Qwen Image 2512
- + The handwriting has more natural variation and charm with elegant cursive elements
- + Great use of vertical space and layout for a café setting
- + Authentic chalkboard dusty effect around the edges
- − Spelling error in 'Risitto' (should be Risotto)
- − Slightly less crisp text rendered compared to the competitor
Verdict: FLUX.2 [max] is the definitive winner due to its flawless execution of the complex text requirements, providing perfect spelling for every item. While Qwen Image 2512 has a more charming and artistic handwriting style, it fails on basic spelling for the first menu item, making FLUX.2 [max] the more reliable and high-quality choice.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
FLUX.2 [max]
Qwen Image 2512
AI Judge Analysis
FLUX.2 [max]
- + Excellent cinematic lighting and atmosphere
- + High level of detail in the astronaut suit and horse anatomy
- + Creative background with the galaxy and asteroid
- − Failed the negative spatial instruction 'horse on top'
- − Standard interpretation rather than surreal
Qwen Image 2512
- + Strong clarity in the horse's coat and equipment
- + Dynamic posing of the horse
- − Completely ignored the spatial instruction 'horse on top, not vice versa'
- − The astronaut's face inside the helmet has slight distortion
- − Less cinematic overall feel compared to Model A
Verdict: Both models failed the specific spatial challenge to have the horse on top of the astronaut, instead providing the standard 'astronaut on horse' trope. FLUX.2 [max] is the preferred winner because it offers significantly better visual quality, lighting, and a more immersive cinematic background using an asteroid and galaxy, whereas Qwen Image 2512 has a simpler, less detailed environment.
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]
Qwen Image 2512
AI Judge Analysis
FLUX.2 [max]
- + Excellent photorealistic texture on the capybara's fur and the leather jacket
- + Strong composition with a side view that clearly shows both characters and the taxi dashboard
- + Natural lighting and realistic bokeh in the background
- − The capybara's hands look more like human gloved hands than paws
Qwen Image 2512
- + The capybara's paws are more anatomically grounded for the animal
- + Captures a very specific 'bored' expression on the passenger as requested
- + Detailed taxi driver uniform hat
- − Lighting on the capybara's face feels slightly flat and less integrated with the night environment
- − The passenger's hands and phone interaction look slightly warped
Verdict: FLUX.2 [max] wins on overall visual quality and cinematic lighting, creating a very believable photorealistic scene despite the slightly human-like hands. Qwen Image 2512 followed the prompt's character descriptions well, particularly the passenger's expression, but the overall image texture feels less refined than the competition.
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]
Qwen Image 2512
AI Judge Analysis
FLUX.2 [max]
- + Excellent typography with perfect spelling in all fields
- + Sophisticated layout that feels like a professional invitation
- + Artistic lighting on the pumpkin and background trees
- − The parchment texture is a bit subtle on the edges
Qwen Image 2512
- + Strong gothic aesthetic for the small banner scroll
- + Very intricate thorns and webs in the border detail
- + Atmospheric moody sky rendering
- − Spelling error in the main title ('Hallowern')
- − The banner text is slightly uneven
Verdict: FLUX.2 [max] is the clear winner because it followed the text instructions perfectly, whereas Qwen Image 2512 included a significant typo in the main header ('Hallowern'). FLUX.2 also provided a cleaner, more readable design for an invitation while still maintaining the requested spooky atmosphere.
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]
Qwen Image 2512
50% wins
0% ties
50% wins
AI Judge Analysis
FLUX.2 [max]
- + Perfect text rendering and layout placement.
- + Matches the 'ultra-clean' and 'minimalist' aesthetic requested.
- + Excellent isometric perspective and lighting.
- − The sushi models are slightly more simplified than a 'realistic PBR' material might suggest.
Qwen Image 2512
- + Higher detail in the food textures and materials.
- + Good adherence to the diorama base and text requirements.
- + Playful 3D cartoon style.
- − The isometric perspective is slightly lower than the requested 45° angle.
- − The base includes extra foliage/garnish not explicitly requested in the 'minimal' prompt.
Verdict: Both models followed the prompt exceptionally well, including the specific text and flag requirements. FLUX.2 [max] produced a cleaner, more professional-looking graphic with a perfect 45-degree isometric view, while Qwen Image 2512 featured more detailed textures on the sushi pieces but deviated slightly from the 'minimal' requirement by adding extra plants. FLUX.2 [max] is the winner for its superior composition and adherence to the 'ultra-clean' aesthetic.
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]
Qwen Image 2512
100% wins
0% ties
0% wins
AI Judge Analysis
FLUX.2 [max]
- + Captures the active 'chasing' and 'tumbling' motion requested in the prompt.
- + Excellent sense of depth with a soft, atmospheric background and realistic bokeh.
- + Subtle, realistic lighting with dew sparkles and soft god rays that feel natural.
- − The kitten's size is a bit small relative to the bunny.
- − The 'fox kit' looks slightly more like a small adult fox proportionally.
Qwen Image 2512
- + High level of facial detail and expressive, large eyes for all animals.
- + Strong color saturation and clear butterfly silhouettes.
- + Vibrant, golden 'god rays' that create a very warm, bright atmosphere.
- − Static, posed composition fails to depict the 'chasing' and 'tumbling' actions requested.
- − Noticeable anatomical issues, specifically the puppy's paws merging awkwardly with the other animals.
- − The fox's face lacks the 'kit' features, appearing more like a compressed adult fox face.
Verdict: FLUX.2 [max] followed the prompt more closely by illustrating the animals in motion (chasing/tumbling), creating a more dynamic and believable scene. Qwen Image 2512 opted for a static, posed portrait which, while cute, ignored the behavioral aspects of the prompt and contained several anatomical clipping artifacts where the animals overlap. FLUX.2 [max] is the winner for its better composition and superior adherence to the requested action.
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]
Qwen Image 2512
100% wins
0% ties
0% wins
AI Judge Analysis
FLUX.2 [max]
- + Perfect adherence to the 'minimalist' and 'vector emblem' style requested.
- + Accurate rendering of the 'Caffè Florian' name with the correct grave accent.
- + Clean, professional composition suitable for a real-world logo.
- − The steam is very faint and simple compared to the rest of the illustration.
Qwen Image 2512
- + Excellent illustrative detail and cross-hatching texture.
- + Strong vintage aesthetic with a dynamic banner design.
- + Correct typography and placement of the 'Est. 1720' text.
- − Ignored the 'minimalist' and 'vector' part of the prompt in favor of a detailed illustration.
- − The steam is a bit heavy-handed for a clean logo design.
Verdict: FLUX.2 [max] followed the prompt more accurately by providing a minimalist vector emblem that looks like a functional logo. Qwen Image 2512 created a beautiful vintage illustration, but it is too complex for the 'minimalist vector' requirement and lacked the refined simplicity of a professional 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]
Qwen Image 2512
AI Judge Analysis
FLUX.2 [max]
- + Excellent typography with clean, readable, and correctly spelled labels.
- + Very consistent flat-vector illustration style across all icons.
- + Better adherence to the '6 steps' request with a logical visual flow.
- − The Saturn V rocket illustration is slightly stubby and less accurate to the real vehicle.
- − Includes repetitive 'Earth Orbit' labels in multiple panels.
Qwen Image 2512
- + More accurate representation of the Saturn V rocket silhouettes.
- + Stronger layout balance with a clear title and surface horizon at the bottom.
- − Poor text rendering with several misspelled words like 'TranslauraJ' and 'Desceeint'.
- − Confusing numbering system that repeats numbers and places them out of chronological order.
Verdict: FLUX.2 [max] is the preferred choice because it successfully creates a clean, usable infographic with professional-grade typography and consistent icons. While Qwen Image 2512 has a more dynamic layout and better rocket details, its severe spelling errors and disjointed numbering make it fail as a functional infographic.
Next steps
Explore each model
Improved version of Alibaba's Qwen image model with better text rendering, finer natural textures, and more realistic human generation.