FLUX.2 [dev] Black Forest Labs Qwen Image 2.0 Pro Alibaba

Settled by community votes across 9 shared challenges, with an AI judge weighing in on each.

FLUX.2 [dev]

24.5 arena score

#18 of 62 in Text-to-Image

Skill signature · Text-to-Image

Qwen Image 2.0 Pro

22.5 arena score

#32 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.2 [dev]

win rate

Ties

Qwen Image 2.0 Pro

win rate

Shared challenges 9

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 2.0 Pro

AI Judge Analysis

FLUX.2 [dev]

+ Excellent optical realism with accurate glass reflections and refractions
+ The small blue sphere sits naturally on the bottom of the cube with a clear reflection
+ Perfect lighting and depth of field consistent with the prompt

− None notable

Qwen Image 2.0 Pro

+ Successfully includes all requested elements in the scene
+ Clean and simple composition

− The sphere is floating unnaturally in the center of the cube without support
− The lighting inside the glass cube is somewhat inconsistent, appearing like mirrors on the side panels
− Lower contrast and less photographic texture compared to Model A

Verdict: FLUX.2 [dev] produced a highly realistic image with superior handling of physics and light; the sphere rests naturally on the glass base and shows realistic reflections. Qwen Image 2.0 Pro followed the prompt but failed on logic, as the sphere appears to be levitating inside the cube, and the glass panels look more like mirrors than transparent glass.

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 2.0 Pro

AI Judge Analysis

FLUX.2 [dev]

+ Excellent typography integrated naturally with the fiery atmosphere.
+ Beautifully rendered sauce splashes that add a sense of dynamic motion.
+ Clean, professional layout with high-quality global lighting and embers.

− The starburst for the price is very large and slightly crowds the burger.
− The bun texture is a bit too smooth and matte.

Qwen Image 2.0 Pro

+ Highly detailed textures on the patty and sesame-seed bun.
+ Dynamic composition with a sense of depth in the burger layering.
+ Strong adherence to the fiery, embers-filled background request.

− The starburst price tag looks like a flat graphic compared to the photorealistic burger.
− The text 'MAGIC BURGER' is slightly less legible due to the heavy flame overlays.

Verdict: Both models followed the prompt exceptionally well, but FLUX.2 [dev] produces a more cohesive advertisement by better integrating all text and the starburst into the 3D environment. While Qwen Image 2.0 Pro has superior texture details on the meat and seeds, the sticker-like appearance of its price tag detracts from the professional quality of the 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 [dev]

Qwen Image 2.0 Pro

AI Judge Analysis

FLUX.2 [dev]

+ Natural chalk smudge effects and realistic board texture
+ High fidelity in the letter strokes with authentic chalk grain
+ Perfect rendering of long menu item names without spelling errors

− One small section of text 'with' in the middle menu item appears slightly faded or smudged into the background

Qwen Image 2.0 Pro

+ Excellent composition with a dynamic camera angle
+ Highly consistent handwriting style across the entire board
+ Clean and legible text rendering

− The chalk effect looks slightly more digital and uniform compared to Model A
− Perspective on the chalkboard edges is slightly warped

Verdict: Both models followed the prompt exceptionally well, even completing the 'Brown Butter...' item which was cut off in the prompt text. FLUX.2 [dev] is the winner because the texture of the chalk and the smudges on the board look significantly more realistic and tangible, whereas Qwen Image 2.0 Pro has a slightly cleaner, more 'perfect' look that feels a bit more like a digital font.

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 2.0 Pro

AI Judge Analysis

FLUX.2 [dev]

+ Excellent photorealism in textures, especially the capybara's fur and the jacket fabric.
+ Perspective correctly places the capybara in the driver's seat and the human in the back seat.
+ Very clean composition that looks like a high-quality cinematic shot.

− The capybara's front paws look a bit like human hands in gloves rather than realistic capybara paws.
− The human passenger is partially obscured by the driver's headrest.

Qwen Image 2.0 Pro

+ Successfully includes specific taxi details like the 'TLC Licensed' sticker.
+ Perfect execution of the bored passenger expression and modern phone interaction.
+ Good lighting coherence between the interior cabin and the street lights.

− Confusing spatial logic where the passenger seems to be sitting next to the driver rather than in the back seat.
− Spelling error in the 'Licensed' text on the dashboard sticker.
− The steering wheel placement and size feel slightly warped in the composition.

Verdict: FLUX.2 [dev] produces a much more realistic and spatially accurate scene, correctly positioning the businesswoman in the back seat as requested. While Qwen Image 2.0 Pro includes nice specific details like the TLC badge, it fails the basic composition requirement by placing the passenger in the front seat and contains minor text artifacts.

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 2.0 Pro

AI Judge Analysis

FLUX.2 [dev]

+ Excellent typography with clean, consistent font weights
+ Perfect adherence to all requested text fields
+ Strong composition with a clear visual hierarchy and dark, moody color palette

− The jack-o-lantern is quite dark, which may reduce its impact as a central glowing element

Qwen Image 2.0 Pro

+ High level of detailed texture on the pumpkin and bats
+ Unique green lighting adds a creative 'eerie' feel to the scene
+ Border detail of thorns and webs is intricately rendered

− Typos in the main title text such as 'Inuitation'
− The layout is more cluttered, with the scroll banner overlapping the jack-o-lantern's stem

Verdict: FLUX.2 [dev] is the superior choice for this task because it followed the text instructions perfectly, producing a professional-looking invitation without typos. While Qwen Image 2.0 Pro offered impressive textures and lighting, the spelling errors in the Title and the less balanced composition make it less functional as an actual 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 2.0 Pro

AI Judge Analysis

FLUX.2 [dev]

+ Excellent PBR material rendering with realistic subsurface scattering on the fish
+ Followed the text layout instructions perfectly
+ Subtle lighting and shadows create a high-quality 3D render feel

− The 'JAPAN' text is slightly thinner compared to the bold requirement

Qwen Image 2.0 Pro

+ Strong bold typography and clean icon placement
+ Accurate isometric perspective and dioramic base
+ Consistent cartoon-style 3D modeling

− The sushi rice texture looks a bit repetitive and plastic-like
− Placed the flag icon between the words despite the prompt asking for 'SUSHI' below the flag

Verdict: FLUX.2 [dev] followed the text hierarchy more accurately and provided much more sophisticated materials, particularly in the way light interacts with the sushi. Qwen Image 2.0 Pro produced a very clean image but the textures felt more basic and the text arrangement was slightly less faithful to the prompt sequence.

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 2.0 Pro

AI Judge Analysis

FLUX.2 [dev]

+ Exceptional warmth and lighting consistency with the 'god rays' theme.
+ Highly detailed fur texture and realistic anatomy on all animals.
+ Excellent composition with the butterflies being the focus of the animals' gaze.

− Includes two bunnies instead of the requested one baby bunny.
− The animals are mostly sitting rather than 'tumbling' or 'playfully chasing'.

Qwen Image 2.0 Pro

+ Captures the 'tumbling' and 'playfully' aspects of the prompt more effectively.
+ Includes the correct number of animals (one of each).
+ Beautiful floral variety and well-defined dew sparkles on the grass.

− The fox kit has a slightly distorted, elongated tail that looks unnatural.
− The kitten's facial structure appears a bit flat and less realistic than the other animals.
− Lighting is a bit harsh/overexposed in the background compared to the foreground subjects.

Verdict: Both models followed the prompt well, but FLUX.2 [dev] produced a more aesthetically pleasing image with superior lighting and fur textures. However, Qwen Image 2.0 Pro was more accurate to the specific count of animals and better captured the dynamic 'tumbling' action requested, even though it suffered from some minor anatomical distortion on the fox and less refined facial details on the kitten.

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 2.0 Pro

AI Judge Analysis

FLUX.2 [dev]

+ Excellent typography with correct spelling and proper accent mark.
+ Strong vintage aesthetic with woodblock-style texture and high-contrast vector look.
+ Cleaner layout and composition that works better as a logo.

− Steam lines are very small and somewhat disconnected from the cloche.

Qwen Image 2.0 Pro

+ Effective integration of steam into the design of the cloche.
+ Good color palette adherence to warm brown and cream tones.

− Spelling error in the main text ('Floriian' instead of 'Florian').
− The composition feels slightly crowded within the frame compared to Model A.

Verdict: FLUX.2 [dev] is the clear winner as it correctly spells the name of the establishment and captures a more authentic vintage vector aesthetic. Qwen Image 2.0 Pro struggles with spelling and has a slightly less professional layout for a 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 [dev]

Qwen Image 2.0 Pro

AI Judge Analysis

FLUX.2 [dev]

+ Excellent vector art style with crisp, professional illustrations
+ High artistic quality in the lunar module and rocket renderings
+ Incorporates the astronauts' names effectively in a modern header design

− Layout is a disorganized grid that fails to follow a sequential mission timeline
− The text contains several spelling errors and nonsensical labels like 'Trarquility'
− Includes redundant and incorrectly labeled icons that don't match the prompt sequence

Qwen Image 2.0 Pro

+ Follows the requested sequential timeline perfectly with numbered steps
+ Text is perfectly legible and accurately spelled throughout
+ Excellent composition that creates a clear visual flow from launch to landing

− The 'Descent' phase shows the module angled in an odd way relative to the trajectory
− The vector style is slightly more generic compared to the stylistic flair of the other model

Verdict: Qwen Image 2.0 Pro is the clear winner as it correctly followed the instructional nature of the prompt, creating a logical 6-step timeline with perfect spelling. While FLUX.2 [dev] produced more visually sophisticated individual illustrations, it failed as an infographic by providing a jumbled grid with numerous typos and a lack of narrative flow.