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]
#8 of 62 in Text-to-Image
Qwen Image
#40 of 62 in Text-to-Image
Where the votes landed
FLUX.2 [pro]
0%
win rate
Ties
0%
Qwen Image
0%
win rate
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.”
AI Judge Analysis
FLUX.2 [pro]
- + Excellent photographic quality with realistic textures on the book and table.
- + Clear and coherent glass physics, including subtle reflections and distortions.
- + Accurate adherence to the lighting direction requested in the prompt.
- − The sphere is slightly matte rather than the typical glossy appearance one might expect in a studio-style setup.
Qwen Image
- + Good color saturation on the blue sphere.
- + Maintains all requested elements in a clean composition.
- − The glass cube has illogical vertical internal reflections that look like extra supports.
- − The bottom of the cube appears to be a mirror rather than clear glass, contradicting the 'glass cube' description.
- − The plant in the background lacks the realistic depth of field seen in the competitor.
Verdict: FLUX.2 [pro] is the clear winner as it produces a much more realistic photographic result with accurate glass transparency and lighting. While Qwen Image follows the prompt instructions, it suffers from internal geometric artifacts in the cube and an unnatural mirrored base that detracts from the realism.
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.”
AI Judge Analysis
FLUX.2 [pro]
- + Excellent shallow depth of field with realistic bokeh.
- + Highly realistic skin textures and clothing details.
- + Perfectly captures the 'imperfect framing' requested with a candid street photography feel.
- − The bicycle chain and mechanical assembly are slightly distorted and physically impossible.
Qwen Image
- + Accurately depicts the light rain and the standing water reflections.
- + Subject is clearly elderly and Japanese as requested.
- − The man's hands are mangled and fused into the bicycle seat.
- − Lacks the requested 'natural skin texture', appearing more smoothed and plastic-like.
- − The bicycle is floating slightly above the pavement.
Verdict: FLUX.2 [pro] is the clear winner as it successfully captures the cinematic, professional photography aesthetic requested, including natural skin textures and realistic depth of field. Qwen Image fails significantly on anatomical details (the hands) and produces a flatter, more artificial-looking image that lacks the 'no stylization' realism of its competitor.
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.”
AI Judge Analysis
FLUX.2 [pro]
- + Excellent skin texture with realistic dirt and weathering
- + Ornate engraving on the armor is highly detailed and structurally sound
- + Warm torchlight reflections are naturally integrated with the surroundings
- − The bokeh sparks are a bit large and less refined compared to the rest of the image
Qwen Image
- + Successfully captures all prompt elements including chainmail and cloth underlayers
- + Dramatic lighting with high contrast
- + Good rendering of the leather straps and buckles
- − The hair beads look like modern plastic toy beads
- − The scars appear more like face paint or superficial marks rather than healed battle wounds
- − The torch flame has a slightly digital, artificial glow compared to the subject
Verdict: FLUX.2 [pro] delivers a much more lifelike and cohesive portrait with superior skin textures and realistic battle-worn effects. While Qwen Image followed the prompt closely, including features like the chainmail, it suffers from an artificial look particularly in the hair beads and the rendering of the scars.
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.”
AI Judge Analysis
FLUX.2 [pro]
- + Excellent font rendering and readability for a menu.
- + Includes specific requested sections for appetizers, pizza, and mains.
- + Clear, professional two-column layout that feels like a real commercial product.
- − Repetitive menu items (Garlic Bread listed three times).
- − Spelling error in the 'Mins' section header.
Qwen Image
- + Strong creative visual impact with vibrant, colorful backgrounds for the food grid.
- + Modern aesthetic with bold, clean sans-serif typography.
- − Text consists of generated gibberish and illegible characters.
- − Mains and Pizza are combined into one section rather than separate as requested.
- − Layout feels more like a poster than a functional restaurant menu.
Verdict: FLUX.2 [pro] is the superior choice because it produces a functional, professional-grade menu with readable text and clear organizational sections as requested. While Qwen Image has an appealing art-style grid, it fails the basic utility of a menu due to gibberish text and less structured sectioning.
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.”
AI Judge Analysis
FLUX.2 [pro]
- + Excellent photographic texture on the burger patties and bun.
- + Superior text integration with a realistic fiery glow effect.
- + Clean, professional composition suitable for a high-end food advertisement.
- − The 'exploded' effect is more of a clean vertical stack than a dynamic explosion.
- − The starburst element is a bit flat compared to the other 3D elements.
Qwen Image
- + Stronger sense of motion with ingredients flying out in multiple directions.
- + Includes more varied toppings like red onions and sesame seeds.
- + Dynamic fiery background with high contrast.
- − The text has a slightly cartoonish, plastic feel compared to the background.
- − The burger patties look less moist and realistic than in the competing image.
- − The starburst shape is somewhat irregular and less polished.
Verdict: FLUX.2 [pro] produces a much more professional and photorealistic advertisement with sophisticated typography that perfectly matches the fiery theme. While Qwen Image offers a more dynamic 'explosion' of ingredients, its overall finish and text rendering are less refined. FLUX.2 [pro]'s superior image quality and lighting make it the better choice for a commercial design.
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.”
AI Judge Analysis
FLUX.2 [pro]
- + Excellent chalk texture with realistic dust and smudging on the slate surface.
- + Followed the specific date '2026' perfectly.
- + The elegant cursive handwriting style is consistent and convincing.
Qwen Image
- + Clear, legible text with high contrast.
- + Good composition with the board centrally framed in a café setting.
- − Failed the date prompt by writing '20026' instead of '2026'.
- − The text lacks realistic chalk texture, appearing more like a digital font or a smooth marker.
- − Minor spelling error in 'Risoto' (missing a 't').
Verdict: FLUX.2 [pro] followed all prompt instructions, including the specific date and the requirement for a realistic chalk texture with natural variations. Qwen Image struggled with the text rendering, providing a futuristic year '20026' and characters that look more like a digital overlay than actual chalk handwriting.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
AI Judge Analysis
FLUX.2 [pro]
- + Perfectly adheres to the difficult prompt instruction of the horse being on top.
- + Creates a visually stunning, surreal composition with multiple galaxies.
- + High level of detail in the astronaut's suit and the horse's anatomy.
- − The transition between the horse's hooves and the astronaut's backpack is slightly messy.
Qwen Image
- + Clean, high-resolution rendering of the astronaut and horse.
- + Good use of depth with the planetary background.
- − Fails the core prompt requirement of having the horse on top of the astronaut.
- − Produces a conventional, non-surreal interpretation of the prompt.
Verdict: FLUX.2 [pro] followed the specific logic of the prompt ('horse on top, not vice versa'), which is a common failure point for LLMs. Qwen Image produced a high-quality but generic image that ignored the specific instruction, whereas FLUX.2 [pro] embraced the surrealism 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.”
AI Judge Analysis
FLUX.2 [pro]
- + Excellent photobiological detail on the capybara's fur and the raindrop-covered window
- + Highly detailed and realistic car interior dashboard and accessories
- + Perfect adherence to the 'bored expression' of the passenger
- − The capybara's 'hands' appear somewhat human-like or gloved and anatomically confusing
Qwen Image
- + Composition provides a clear view of both the driver and the passenger
- + Clean and vibrant colors with clear branding on the cap and jacket
- − The passenger looks concerned or staring rather than 'bored/normal' with her phone
- − Lower level of texture detail compared to the other image
- − The capybara's head looks slightly composited onto the body
Verdict: FLUX.2 [pro] is the winner due to its superior photorealistic textures, including the rain on the glass and the intricate dashboard details. While Qwen Image provides a clear composition, FLUX.2 [pro] captures the specific mood of a New York night taxi ride much more effectively through its lighting and character expressions.
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.”
AI Judge Analysis
FLUX.2 [pro]
- + Excellent typography with perfect spelling in all requested sections.
- + Cinematic lighting and high-quality textures on the pumpkin and parchment.
- + Sophisticated border design that feels integrated with the theme.
- − The 'You are invited' text on the scroll banner is a bit plain compared to the main title.
Qwen Image
- + Strong composition with a clear vintage parchment aesthetic.
- + Included all requested elements like the thorn border and scroll banner.
- − Major spelling errors in the main title ('Halle Party').
- − Gibberish text added above the main title.
- − The 'You are invited' text is split awkwardly between the scroll and the background.
Verdict: FLUX.2 [pro] is the clear winner as it followed all textual instructions perfectly, providing polished typography and a professional layout. Qwen Image failed significantly on text rendering, misspelling the main header and including nonsensical characters throughout the design.
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.”
AI Judge Analysis
FLUX.2 [pro]
- + Excellent text typography with perfect centring and hierarchy.
- + Very clean, high-clarity 3D rendering with professional lighting.
- + Accurate representation of diverse sushi types with refined textures.
- − The color palette of the base and plate is a bit muted compared to a 'cartoon' aesthetic.
Qwen Image
- + Charming, vibrant cartoon aesthetic with soft lighting.
- + Good 3D miniature feel with added elements like chopsticks.
- + Clear, bright color palette that suits the theme.
- − The small flag icon at the top is positioned awkwardly off-center.
- − Minor artifacts in the textural detail of the sushi rice.
- − The 'J' in Japan is slightly cut off at the edge of the frame.
Verdict: FLUX.2 [pro] followed the layout instructions perfectly, providing clean, centered text with a professional graphic design feel and high-quality 3D assets. Qwen Image captured a slightly more playful cartoon style, but it failed on precise composition, with the top-center text elements being poorly centered and slightly clipped.
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.”
AI Judge Analysis
FLUX.2 [pro]
- + Excellent fur texture and fine details in the wildflower meadow.
- + Superior lighting with subtle, realistic golden tones and soft bokeh.
- + More natural animal anatomy and higher resolution appearance.
- − The kitten's pose is a bit stiff/upright.
- − The scale of the butterflies is slightly small and less prominent.
Qwen Image
- + Successfully captures the 'god rays' and 'dew sparkles' requested in the prompt.
- + Better sense of action and movement with the animals lunging toward the butterflies.
- + Highly expressive eyes that match the prompt's request.
- − The fox's front paws are anatomically messy and blended into the grass.
- − The butterfly on the right has a strange second wing fragment floating behind it.
- − The overall image has a slightly more artificial, 'rendered' look compared to Model A.
Verdict: FLUX.2 [pro] produces a much more realistic and high-quality image with superior textures and lighting, though it is a bit more static. Qwen Image captured specific prompt elements like the god rays and chasing action better, but suffers from significant anatomical errors and a less polished aesthetic. FLUX.2 [pro] is the winner for its professional-grade photorealism and coherence.
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.”
AI Judge Analysis
FLUX.2 [pro]
- + Excellent typography with perfect spelling and accent marks.
- + Sophisticated vector emblem style with clean lines and shading.
- + Well-balanced composition that feels like a professional logo.
- − The subtle background texture is maybe a bit too faint.
Qwen Image
- + Successfully captures the warm brown and cream color palette.
- + Includes all requested elements like the cloche, steam, and banner.
- − Major typographic errors with overlapping and garbled text.
- − Lower visual quality with fuzzy edges and inconsistent linework.
- − Unbalanced layout where the text feels cramped and poorly designed.
Verdict: FLUX.2 [pro] followed the prompt with high precision, delivering a clean, professional vector logo with perfect typography and a sophisticated vintage feel. Qwen Image struggled significantly with text rendering, producing a cluttered and illegible nameplate that fails as a logo design.
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.”
AI Judge Analysis
FLUX.2 [pro]
- + Excellent adherence to the clean, modern vector aesthetic.
- + Accurate interpretation of mission phases (descent from lunar orbit to surface).
- + High visual coherence and professional layout.
- − Nonsense filler text for descriptions.
- − Combined the 'Landing' and 'Descent' steps into a single vertical flow rather than 6 distinct items.
Qwen Image
- + Successfully applied the requested NASA-inspired color palette.
- + Includes names and silhouettes of the astronauts as requested in supplemental logic.
- − Poor typography with significant spelling errors ('Sarth Orbit', 'Apoll').
- − Incorrect ordering of mission steps and confusing labeling.
- − Literally included prompt instructions '(Stop at landing)' as part of the visual text.
Verdict: FLUX.2 [pro] produced a much more professional and aesthetically pleasing infographic that accurately reflects the specified vector style. While its descriptive text is gibberish, Qwen Image failed on basic logic by mislabeling steps and including the meta-instructions from the prompt within the design.
Explore each model
Alibaba's Qwen image model