Black Forest Labs' open-weights image generation model with frontier performance, available for non-commercial local deployment
Settled by community votes across 8 shared challenges, with an AI judge weighing in on each.
FLUX.2 [dev]
24.3
arena score
#19 of 62 in Text-to-Image
Skill signature
· Text-to-Image
Qwen Image Max
21.3
arena score
#35 of 62 in Text-to-Image
Vote tally
Where the votes landed
FLUX.2 [dev]
0%
win rate
Ties
0%
Qwen Image Max
0%
win rate
Shared challenges
8
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 [dev]
Qwen Image Max
AI Judge Analysis
FLUX.2 [dev]
- + Excellent realism in the glass refraction and tabletop texture
- + Accurate lighting coming from the window on the left
- + Realistic object physics with the sphere resting on the bottom
- − The sphere is slightly smaller than what might be expected
Qwen Image Max
- + Clean, modern aesthetic with sharp details
- + Strong adherence to all requested prompt elements
- − The sphere appears to be floating unnaturally in the center of the cube
- − The glass refractions are slightly confusing and inconsistent with the background
Verdict: Both models followed the prompt instructions perfectly, including the placement of the sphere, book, and plant. FLUX.2 [dev] is the winner because it provides a more photorealistic result with convincing lighting and physically believable object placement, whereas the sphere in Qwen Image Max appears to defy gravity by floating in the middle of the cube.
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 [dev]
Qwen Image Max
AI Judge Analysis
FLUX.2 [dev]
- + Excellent depiction of ornate floral engravings on the plate armor.
- + Beautifully soft bokeh and lighting that feels cinematic and warm.
- + The scars look fresh and integrated naturally with the skin texture.
- − The character looks a bit too young and clean for a 'battle-worn' veteran.
- − The hair braids are relatively simple compared to the prompt's potential.
Qwen Image Max
- + Superb facial characterization that truly captures the 'battle-worn' and weary aesthetic.
- + Exceptional detail on the leather textures, featuring visible wear, tears, and grime.
- + Intricate braiding and beadwork that aligns perfectly with the design requirements.
- − The sparks in the background look slightly more like digital noise than physical particles.
- − The torch on the left is a bit blurrier and less defined than in Model A.
Verdict: While both models followed the prompt well, Qwen Image Max is the winner for its superior interpretation of 'battle-worn,' providing a face with deep history and leather textures that actually show damage. FLUX.2 [dev] produced a very beautiful image, but the character felt slightly too much like a clean-shaven model with decorative scars rather than a seasoned warrior.
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 [dev]
Qwen Image Max
AI Judge Analysis
FLUX.2 [dev]
- + Excellent adherence to the 'exploded' request with clear separation of all layers
- + Very clean and readable typography with a consistent fiery glow theme
- + High-quality rendering of individual food textures like the patty and lettuce
- − The composition feels slightly static compared to the sense of motion in the other model
- − The bun appears a bit too perfect and smooth, lacking artisan detail
Qwen Image Max
- + Dynamic sense of motion with flying embers and a tilted perspective
- + Rich, detailed textures on the bun and grilled patty surface
- + Good integration of the starburst graphic for the price
- − Failed to follow the 'exploded' instruction as the main ingredients are mostly stacked
- − The text 'MAGIC BURGER' is slightly less legible than and more distorted than the competition
Verdict: FLUX.2 [dev] followed the prompt more accurately by providing a true exploded view where every ingredient is suspended separately. While Qwen Image Max produced a more viscerally 'dynamic' aesthetic with better texture details and cinematic lighting, it failed to separate the burger components as requested.
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 [dev]
Qwen Image Max
AI Judge Analysis
FLUX.2 [dev]
- + Excellent adherence to the 'both paws on steering wheel' instruction.
- + Clearer view of the businesswoman in the back seat with the correct bored expression.
- + Very high cinematic lighting and sharp details on the capybara's fur.
- − The paws look somewhat like human hands with hair.
- − The perspective through the front windshield makes the taxi look very small.
Qwen Image Max
- + Natural composition and authentic interior wear and tear on the ceiling.
- + The capybara's profile and expression look very realistic and professional.
- + Better integration of the background city lights with the car interior.
- − Failed to place both paws on the steering wheel correctly; the left hand is floating.
- − The businesswoman in the back is partially cut off and less distinct.
- − The capybara's paws look overly like primate hands.
Verdict: FLUX.2 [dev] is the winner for its superior prompt adherence, particularly in capturing the specific interactions of both the driver and the passenger. While Qwen Image Max has a very realistic interior aesthetic, its failure to place both paws on the wheel and the obscured passenger make it less effective at conveying the requested scene.
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 [dev]
Qwen Image Max
AI Judge Analysis
FLUX.2 [dev]
- + Excellent typography rendering with zero spelling errors
- + Followed the request for a small scroll banner accurately
- + High-contrast, polished cinematic lighting
- − The parchment edges are slightly less integrated into the composition than model B
- − The overall tone is a bit darker, making individual elements like bats less prominent
Qwen Image Max
- + Beautiful vintage parchment texture and border integration
- + Dynamic composition with more detailed bats and a moon
- + Highly thematic gothic font choice for the main title
- − Spelling error in the banner text ('frights' is misspelled as 'frights' with a stray mark and 'night' looks slightly off)
- − The event details text uses a very generic sans-serif font that clashing with the gothic theme
Verdict: FLUX.2 [dev] produced a technically superior image with perfect text rendering and a very clean, professional layout that matches the 'polished' requirement. Qwen Image Max has a more charming and detailed vintage aesthetic, but it fails on the text rendering in both the scroll and the bottom details, which are critical for an invitation.
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 [dev]
Qwen Image Max
AI Judge Analysis
FLUX.2 [dev]
- + Excellent adherence to the 'raised diorama base' request with a clean wooden stand
- + Very professional typography and flag icon layout
- + Soft, refined textures that perfectly match the 'miniature 3D cartoon' aesthetic
- − The sushi models are a bit simplified for a 'realistic PBR' request
Qwen Image Max
- + Great material work on the sushi, especially the glossy eel and rice grains
- + Creative glass diorama base adds a unique touch
- + Dynamic typography with nice drop shadows
- − The text and flag positioning is a bit cluttered compared to Model A
- − The glass base has some minor perspective inconsistencies with the plate
Verdict: FLUX.2 [dev] followed the diorama and layout instructions more faithfully, creating a perfectly balanced graphic design composition. While Qwen Image Max provided more detail on the sushi itself and interesting PBR reflections on the glass base, its overall layout feels more crowded. FLUX.2 [dev] is the winner for its superior 'clean' aesthetic and better spatial organization.
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 [dev]
Qwen Image Max
AI Judge Analysis
FLUX.2 [dev]
- + Excellent fur texture rendering and realistic lighting effects.
- + Accurate representation of all four requested species (puppy, kitten, bunny, fox).
- + High visual clarity with realistic depth of field.
- − The animals are mostly sitting still rather than 'playfully chasing' or 'tumbling' as requested.
- − Included two bunnies when the prompt implied a single baby bunny.
Qwen Image Max
- + Successfully captured the 'tumbling' and 'playful' movement requested in the prompt.
- + Beautifully rendered god rays and a vibrant, magical meadow atmosphere.
- − Failed to include the baby bunny entirely.
- − Anatomical issues with the fox's paws and the way it interacts with the puppy's head.
- − Includes two golden retriever puppies instead of one.
Verdict: FLUX.2 [dev] produces a much higher quality, photorealistic image with superior textures and species accuracy, though it missed the specific action of 'tumbling'. Qwen Image Max captured the joyful energy and movement better but failed on prompt adherence by omitting the bunny and including anatomical artifacts.
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 [dev]
Qwen Image Max
AI Judge Analysis
FLUX.2 [dev]
- + Excellent typography with proper accented characters
- + Clean minimalist vector aesthetic
- + Sophisticated use of subtle texture on the background
- − Steam is a bit small and simplistic compared to the rest of the logo
Qwen Image Max
- + Ornate and artistic steam design
- + Strong vintage color palette
- + Good alignment of logo elements
- − Incorrect placement of the accent on 'CAFFÉ' (placed over the second F instead of the E)
- − Background texture is a bit heavy and blotchy for a 'minimalist' request
Verdict: FLUX.2 [dev] followed the prompt more accurately, particularly regarding the 'minimalist' and 'vector' styling while correctly rendering the text 'Caffè'. Qwen Image Max produced a more detailed illustration with better steam, but the spelling error in the name and the overly distressed background made it feel less like a professional logo.
Next steps
Explore each model
The Max series of Tongyi Qwen’s image generation model excels across a wide range of generation tasks. Compared with the Plus series, it significantly reduces the “AI-like” feel in generated images, enhancing their realism. It delivers more lifelike material textures for human subjects, finer and more detailed natural textures, and more visually appealing text rendering.