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
Qwen Image 2.0
21.7
arena score
#34 of 62 in Text-to-Image
Vote tally
Where the votes landed
FLUX.2 [pro]
0%
win rate
Ties
0%
Qwen Image 2.0
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]
Qwen Image 2.0
AI Judge Analysis
FLUX.2 [pro]
- + Excellent photographic realism with natural depth of field.
- + Accurate and clean glass rendering with soft refractions.
- + Perfect adherence to spatial instructions including light source direction.
- − The sphere is slightly less vibrant than the one in the competing image.
Qwen Image 2.0
- + Bright, saturated colors on the sphere and book.
- + Good material texture on the book cover.
- − The glass box has strange interior reflections that look like multiple spheres.
- − The sphere appears to be floating unnaturally without a clear point of contact.
- − The glass panels are joined with thick, slightly unrealistic edges.
Verdict: FLUX.2 [pro] produced a much more realistic image with convincing glass physics and lighting. Qwen Image 2.0 struggled with the glass cube's internal reflections, creating a cluttered look, and the sphere appears to float mid-air rather than resting naturally.
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]
Qwen Image 2.0
AI Judge Analysis
FLUX.2 [pro]
- + Excellent atmospheric lighting and realistic pavement reflections.
- + Accurately depicts the requested rainy environment with visible water ripples.
- + Strong cinematic composition with a convincing shallow depth of field.
- − The structural integrity of the bike's chain and drivetrain is physically impossible.
Qwen Image 2.0
- + Natural, detailed skin texture and facial expression on the subject.
- + Effective framing that feels like a 'candid' street photo.
- + Captures the motion blur from a passing car as requested.
- − The bicycle frame geometry is broken with merging bars.
- − The background lighting looks flat and less 'cinematic' than the other model.
Verdict: FLUX.2 [pro] is the winner because it successfully captured the requested cinematic atmosphere and complex reflections, creating a much more evocative image. While both models struggled with the mechanical complexity of the bicycle, Qwen Image 2.0 produced a flatter, less artistically compelling result that didn't handle the rainy aesthetic as effectively.
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]
Qwen Image 2.0
AI Judge Analysis
FLUX.2 [pro]
- + Excellent photorealistic skin texture and lifelike eyes.
- + Engraved armor details and leather strap textures are highly refined.
- + The lighting and bokeh sparks feel organically integrated into the scene.
- − The 'paladin' identity is slightly generic, relying more on general fantasy tropes than specific iconography.
Qwen Image 2.0
- + Stronger character storytelling through the aged, battle-worn facial features.
- + Clearer representation of the 'paladin' archetype with the cross engraving on the breastplate.
- + Good inclusion of all requested elements, including the braided hair with beads.
- − The hand and sword hilt area shows significant anatomical distortion and blurring.
- − The eyes, while striking, look slightly less natural/realistic compared to Model A.
Verdict: FLUX.2 [pro] is the winner due to its superior technical execution, particularly in the rendering of skin, eyes, and the intricate textures of the armor and leather. While Qwen Image 2.0 captures a very compelling character design and clearer paladin iconography, it suffers from significant artifacts in the hand region and a less polished lighting effect.
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]
Qwen Image 2.0
AI Judge Analysis
FLUX.2 [pro]
- + Excellent typography and layout for a professional menu.
- + Clean white background with effective use of color accents.
- + Includes distinct sections for mains, pizza, and appetizers as requested.
- − Nonsense filler text for descriptions and some food names.
- − Misplaced food photos (steak under the Pizza heading).
Qwen Image 2.0
- + Clean grid layout with large, high-quality food photography.
- + Accurate categorization of images under headings.
- + Very consistent lighting and styling across all photos.
- − Text rendering is severely garbled and illegible.
- − Lacks typical menu elements like ingredient descriptions or varying price points.
Verdict: FLUX.2 [pro] is the stronger choice for menu design as it maintains the structure, typographic hierarchy, and professional layout expected of a real document. While Qwen Image 2.0 has superior food photography in a neat grid, its total failure to render legible text makes it less usable for a graphic design prompt.
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]
Qwen Image 2.0
AI Judge Analysis
FLUX.2 [pro]
- + Excellent typography with a clean, glowing neon effect.
- + Clear 'exploded' view that separates all ingredients as requested.
- + Very high-quality photorealistic textures on the buns and cheese melt.
- − The 'fiery' effect is a bit subtle compared to the prompt's request for a dark, fiery background.
Qwen Image 2.0
- + Strong 'fiery' atmosphere with intense flames and glowing embers.
- + The text 'MAGIC BURGER' has a very impressive flame-texture effect.
- + The starburst element is dynamic and matches the overall aggressive energy.
- − The burger is not fully 'exploded'; the bottom half is mostly stacked together.
- − The spacing of the text is slightly crowded in the top right corner.
Verdict: FLUX.2 [pro] followed the 'exploded' instruction much better, providing a clear view of each layer, and delivered cleaner graphic design elements. Qwen Image 2.0 captured the 'fiery' atmosphere more aggressively, but the burger composition was more static and less aligned with the mid-air suspension request.
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]
Qwen Image 2.0
AI Judge Analysis
FLUX.2 [pro]
- + Excellent chalk texture with realistic dust and grain
- + Consistency in handwritten style across the entire board
- + Highly detailed slate-like chalkboard surface
- − The board feels more like a small slate plaque than a café chalkboard
- − Very tight cropping on the board makes the café context less visible
Qwen Image 2.0
- + Natural café composition with realistic lighting and background depth
- + Strong adherence to all text elements including the specific date
- + Authentic smudging and wiping marks on the chalkboard surface
- − The pricing for the 'Chocolate Chip Cookies' is oddly formatted with a dash before the nine
- − Slightly less realistic chalk texture compared to Model A
Verdict: Both models followed the complex text instructions perfectly, including the specific date and multiple menu items. FLUX.1 [pro] has a more tactile, realistic chalk-on-slate texture, while Qwen Image 2.0 provides a much better overall composition that truly feels like a sign inside a café. Qwen Image 2.0 is the winner for its superior atmospheric lighting and better use of the scene's space.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
FLUX.2 [pro]
Qwen Image 2.0
AI Judge Analysis
FLUX.2 [pro]
- + Excellent adherence to the 'horse on top' spatial instruction
- + Cinematic lighting with a high level of detail in the astronaut suit and background galaxies
- + Creative interpretation that creates a surreal, dreamlike stack
- − Anatomical glitch where the bottom horse merges awkwardly into the astronaut's back
- − The second horse's position is somewhat ambiguous relative to the astronaut's shoulders
Qwen Image 2.0
- + High visual clarity and sharp rendering
- + Dynamic pose for both the horse and the astronaut
- − Failed the negative constraint; the astronaut is riding the horse instead of vice versa
- − Lacks the surreal quality requested by falling back on a common trope
Verdict: FLUX.2 [pro] followed the complex spatial instruction to put the horse on top of the astronaut, resulting in a truly surreal and creative image. Qwen Image 2.0 ignored the specific instruction 'horse on top, not vice versa' and produced a standard, though well-rendered, image of an astronaut riding a horse.
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]
Qwen Image 2.0
AI Judge Analysis
FLUX.2 [pro]
- + Excellent realism with sophisticated lighting and textures in the taxi interior.
- + Superior prompt adherence regarding the capybara's anatomy, blending the animal head naturally with the body.
- + Precise lighting on the subject's fur that matches the cinematic night environment.
- − The capybara's hands are rendered as human-like fingers covered in fur rather than true front paws.
- − The businesswoman in the background is slightly out of focus, making it harder to read her expression.
Qwen Image 2.0
- + Captured the bored, normal expression of the businesswoman very effectively.
- + Realistic representation of capybara front paws on the steering wheel.
- + High contrast and vibrant colors that evoke a busy city atmosphere.
- − The capybara's head looks 'copy-pasted' onto the body without a neck or natural transition.
- − Lower overall resolution and more 'AI smooth' textures compared to the competing model.
- − The camera angle makes the capybara look disproportionately large for the vehicle cabin.
Verdict: FLUX.2 [pro] is the winner due to its significantly higher level of photorealism and seamless integration of the capybara into the human clothing and environment. While Qwen Image 2.0 did a better job with the businesswoman's expression and the capybara's actual paws, it suffered from poor anatomical blending and a less convincing lighting setup.
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]
Qwen Image 2.0
AI Judge Analysis
FLUX.2 [pro]
- + Excellent photographic realism in the jack-o-lantern and volumetric lighting.
- + Perfect text rendering with high readability and correct spelling.
- + Elegant dark parchment texture with subtle tattered edges.
- − The transition from the 3D jack-o-lantern to the 2D scroll banner feels a bit disconnected.
Qwen Image 2.0
- + Beautiful gothic border that integrates webs and thorns consistently.
- + Strong vintage illustration style that matches the 'parchment poster' request.
- + Accurate text spelling and well-designed scroll banner.
- − The lighting is less cinematic and more flat compared to model A.
- − The jack-o-lantern's carving is slightly less refined.
Verdict: Both models followed the prompt perfectly, including the specific date and location text. FLUX.2 [pro] is more cinematic and polished with superior lighting, while Qwen Image 2.0 leans more into the vintage illustration aesthetic with a better border design. FLUX.2 [pro] is the likely winner due to the higher quality of the central jack-o-lantern and more sophisticated atmospheric depth.
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]
Qwen Image 2.0
AI Judge Analysis
FLUX.2 [pro]
- + Excellent adherence to the '3D cartoon' and 'miniature' style requests.
- + Clean and professional typography layout with the flag indicator.
- + Perfect isometric viewpoint and centered composition.
Qwen Image 2.0
- + High-quality realistic PBR textures on the fish and rice.
- + Clear and legible text that follows the prompt instructions.
- + Accurate representation of various sushi types.
- − Failed to capture the requested '3D cartoon' and 'miniature' aesthetic, opting for realism instead.
- − Texture of the wooden base is slightly grainy compared to the background.
- − Placement of the flag is off-center relative to the text.
Verdict: FLUX.2 [pro] followed the stylistic instructions much more closely, delivering a cohesive 3D cartoon diorama that felt like a deliberate miniature. While Qwen Image 2.0 produced very appetizing and realistic food textures, it ignored the 'cartoon' aspect of the prompt and lacked the polished graphic design aesthetic of FLUX.2 [pro].
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]
Qwen Image 2.0
AI Judge Analysis
FLUX.2 [pro]
- + Excellent fur texture rendering and soft lighting continuity.
- + Superior animal anatomy and facial coherence.
- + Pleasant, balanced botanical environment with soft bokeh.
- − The 'tumbling together' action is more of a static huddle.
- − The puppies tongue appears to be oddly licking the bunny's ear.
Qwen Image 2.0
- + Successfully captured the 'tumbling' and 'playfully chasing' aspect of the prompt.
- + Strong implementation of god rays and sunrise lighting.
- + Better interaction between the different animals in the scene.
- − Anatomical issues with the fox kit, which has two ears on one side of its head and a distorted face.
- − The kitten's tail is missing/blended into the dog's leg.
- − Visible AI artifacts on the kitten's paws.
Verdict: While Qwen Image 2.0 did a better job at capturing the dynamic 'tumbling' action requested in the prompt, it suffered from significant anatomical errors, particularly regarding the fox kit. FLUX.2 [pro] produced a much higher quality image with superior fur detail and cleaner subjects, making it the more aesthetically pleasing 'masterpiece' despite the more static pose.
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]
Qwen Image 2.0
AI Judge Analysis
FLUX.2 [pro]
- + Excellent typography and precise letter rendering including the accent in 'Caffè'.
- + Sophisticated vector emblem style with clean, professional composition.
- + Authentic subtle texture on a light background that enhances the vintage aesthetic.
- − The steam is a bit abstract and looks more like hair or flames.
Qwen Image 2.0
- + Creative use of negative space to incorporate the steam and branding inside the cloche.
- + Strong color palette with good shading on the dome.
- − The banner at the bottom is physically nonsensical with awkward, messy line work and curls.
- − Lack of a vector emblem 'feel', looking more like a clip-art illustration.
- − Typography is less refined compared to the competitor.
Verdict: FLUX.2 [pro] produced a professional-grade logo that perfectly adheres to the 'vector emblem' and 'minimalist' requirements, with superior typography and layout. Qwen Image 2.0 has an interesting concept but fails on the execution of technical details, particularly the distorted banner and the less professional font choice.
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]
Qwen Image 2.0
AI Judge Analysis
FLUX.2 [pro]
- + Excellent vector art style with professional layout and clean borders
- + Accurate representation of the requested NASA color palette
- + Includes creative details like the landing site 'Tranquility' marker and crew silhouettes
- − The placeholder text for the descriptions is gibberish
- − The Saturn V icon looks more like a generic space shuttle or stylized rocket
Qwen Image 2.0
- + Successfully includes all 6 numbered steps in the correct sequence
- + Features a more accurate Saturn V rocket silhouette
- + Clean vertical composition that is easy to follow
- − Contains a spelling error ('Translunjar')
- − Layout feels a bit more cluttered with elements overlapping the text
Verdict: FLUX.2 [pro] produced a more visually polished and 'design-ready' infographic with superior vector aesthetics, whereas Qwen Image 2.0 followed the specific step-by-step instructions slightly better by including all six requested phases. FLUX.2 [pro] is preferred overall because its composition and iconography feel like a professional poster, despite the nonsensical body text.
Next steps
Explore each model
Alibaba's Qwen Image 2.0 model with enhanced text rendering, supporting both Chinese and English prompts with up to 6 images per request