Black Forest Labs' distilled 9 billion parameter image generation model with sub-second inference and multi-reference support
Settled by community votes across 9 shared challenges, with an AI judge weighing in on each.
FLUX.2 [klein] 9B
#13 of 32 in Image Editing
Qwen Image 2.0 Pro
#32 of 62 in Text-to-Image
Where the votes landed
FLUX.2 [klein] 9B
0.0%
win rate
Ties
0.0%
Qwen Image 2.0 Pro
100.0%
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 [klein] 9B
- + Excellent depiction of realistic glass materials including refractions and caustics.
- + Perfect adherence to lighting instructions with soft light from the left.
- + The blue sphere has a beautiful marble-like texture.
- − The glass object is more of a hollow vase/cuboid than a perfect geometric glass cube.
- − The perspective of the book on top of the glass edge is slightly awkward.
Qwen Image 2.0 Pro
- + Geometric accuracy of the glass cube is very high.
- + Strong composition with a clear, matte blue sphere.
- + Accurate representation of the green plant visible through the glass.
- − The glass looks like thin panes rather than a solid or thick cube.
- − The blue sphere appears to be floating mid-air without a physical base inside the cube.
- − The reflections on the left side of the cube are slightly inconsistent with the window placement.
Verdict: Both models followed the complex spatial instructions perfectly. FLUX.2 [klein] 9B stands out for its superior rendering of light, caustics, and material textures, creating a more photographic image, while Qwen Image 2.0 Pro provided a more geometrically precise 'cube' but with less realistic physical interactions between objects.
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 [klein] 9B
- + Excellent typography integration with high-quality fire textures.
- + Dynamic composition with a strong sense of motion through angled perspective.
- + High photorealistic detail in the meat texture and sauce droplets.
- − The burger is not truly 'exploded' as much as it is a double-stacked burger with some separation.
- − Secondary text lacks the requested fiery/glowing effect compared to the main title.
Qwen Image 2.0 Pro
- + Perfect adherence to the 'exploded' request with clear separation of every component.
- + The starburst design and text placement are well-defined and legible.
- + The fiery background and smoke effects create a strong atmosphere.
- − Lighting on the burger feels a bit flat compared to the intensity of the background.
- − The starburst graphic looks like a 2D overlay and doesn't blend as well with the 3D scene as Model A.
Verdict: FLUX.2 [klein] 9B produces a more visually stunning and professionally balanced advertisement with superior texture work, but it fails to fully separate the burger layers. Qwen Image 2.0 Pro followed the specific 'exploded burger' instruction more accurately and maintained high text legibility, though the overall composition feels slightly more static. FLUX.2 remains the better choice for a commercial-quality aesthetic.
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 [klein] 9B
- + Natural chalk smudge and eraser marks increase realism.
- + Consistent, believable handwriting style across the entire board.
- + Includes the wooden frame and background cafe setting for better context.
- − Several spelling errors including 'Riott', 'Risoto', 'Octoopus', and 'fress'.
- − Repetitive pricing text and cluttered layout in the middle section.
Qwen Image 2.0 Pro
- + Perfect spelling for all complex menu items like 'Risotto' and 'Octopus'.
- + Excellent chalk texture with realistic dusty fallout underneath the words.
- + Clear, legible layout with balanced spacing between items.
- − The board lacks a wooden frame, appearing slightly less like a physical café object.
- − Handwriting is almost too perfect, leaning slightly toward a digital brush effect.
Verdict: While FLUX.2 [klein] 9B captures the atmosphere of a smudged, real-world chalkboard effectively, it severely fails on spelling and text legibility. Qwen Image 2.0 Pro provides perfect spelling and high-quality chalk textures while maintaining a consistent handwritten aesthetic, making it the superior choice for a text-heavy menu task.
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 [klein] 9B
- + Excellent photorealism in the capybara's fur and the woman's face.
- + Accurately places the passenger in the back seat as requested.
- + Realistic indoor taxi lighting and bokeh in the background.
- − The passenger appears to be sitting in the front passenger seat due to the perspective, rather than the back.
- − Text on the driver's cap is nonsensical ('NEW TALA').
Qwen Image 2.0 Pro
- + Dynamic composition with a wide-angle feel that captures more of the taxi environment.
- + Highly detailed texture on the steering wheel and jacket.
- + Includes a 'TLC Licensed' sticker which adds to the New York taxi theme.
- − The passenger is clearly sitting in the front seat, directly next to the driver, failing the 'back seat' prompt instruction.
- − The capybara's paws look somewhat human-like and distorted.
- − The scale of the capybara relative to the car interior feels slightly off.
Verdict: Both models failed to clearly place the businesswoman in the back seat, instead placing her in the front passenger area. FLUX.2 [klein] 9B is the winner due to superior photorealism, more natural skin tones, and a more believable capybara rendering, whereas Qwen Image 2.0 Pro suffers from slightly distorted anatomy in the paws.
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 [klein] 9B
- + Excellent typography with a cohesive gothic font choice
- + Sophisticated composition with a central glowing jack-o-lantern and symmetrical trees
- + Perfect crispness and legibility of all requested text elements
- − The thorns in the border appear somewhat repetitive and patterned
- − The moon is cut off by the border
Qwen Image 2.0 Pro
- + Creative use of green internal lighting for the jack-o-lantern
- + Detailed bat illustrations with visible fur and character
- + Strong border design with variety in the thorn shapes
- − The title text uses two different clashing gothic fonts that look messy
- − Text rendering is slightly blurry compared to the other model
- − The scroll banner looks less naturally integrated into the scene
Verdict: FLUX.2 [klein] 9B is the superior choice for this task due to its exceptional text rendering and balanced layout, creating a professional-looking invitation. While Qwen Image 2.0 Pro offered creative touches like green lighting and detailed bats, its typographic choices were inconsistent and less legible.
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 [klein] 9B
- + Excellent wood grain texture on the diorama base.
- + Bold and clear typography for both words.
- + Detailed rendering of the sushi ingredients like fish eggs.
- − The flag icon is incorrect (resembles the Yemen flag instead of Japan).
- − The sushi nigiri piece has an unusual seaweed wrap around the middle.
Qwen Image 2.0 Pro
- + Accurately depicts the Japanese flag icon.
- + Very clean, rounded aesthetic consistent with the 'miniature 3D cartoon' style.
- + Excellent lighting and soft shadows on the base.
- − The word 'SUSHI' is smaller and less prominent than specified.
- − The placement of the flag between the words deviates slightly from the 'SUSHI below it' instruction.
Verdict: While FLUX.2 [klein] 9B has superior texture work on the wooden base, it failed completely on the flag icon. Qwen Image 2.0 Pro followed the stylistic request for a soft, 3D cartoon look much more effectively and correctly identified the cultural symbols required by the prompt.
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 [klein] 9B
- + Strong artistic composition with vibrant colors and clear god rays
- + Extremely sharp focus on the animals' faces and fur textures
- + Whimsical, storybook-like interpretation of the butterflies and lighting
- − Failed to include the baby bunny requested in the prompt
- − The kitten has an anatomically odd, overly wide-eyed expression
- − Visual style leans more towards 3D concept art than 'hyper-photorealistic'
Qwen Image 2.0 Pro
- + Included all four requested animals (dog, cat, fox, bunny)
- + Achieved a more grounded, photorealistic appearance with natural lighting
- + Better adherence to the 'tumbling together' request with animal interaction
- − The fox kit's tail appears unnaturally long and thick for its body size
- − The background landscape is a bit hazy and less detailed compared to the foreground
Verdict: Qwen Image 2.0 Pro is the clear winner as it included all the requested subjects (dog, cat, fox, and bunny), whereas FLUX.2 [klein] 9B missed the bunny entirely. Furthermore, Qwen Image 2.0 Pro captured the 'hyper-photorealistic' instruction more accurately, while FLUX produced an image that looks like a high-end digital illustration.
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 [klein] 9B
- + Excellent typography with perfect spelling and correct accent marks
- + Superior vector aesthetic with clean, balanced line work
- + Authentic retro feel with a subtle paper texture background
- − Steam looks slightly detached from the cloche
Qwen Image 2.0 Pro
- + Creative integration of steam onto the surface of the cloche
- + Warm and inviting color palette
- − Spelling error in 'Floriian' with a double letter 'i'
- − Cluttered banner arrangement with overlapping elements
- − The steam effect looks more like a graphic printed on the dome than actual steam rising
Verdict: FLUX.2 [klein] 9B followed every instruction perfectly, including specific spelling and typography details that are essential for a logo. Qwen Image 2.0 Pro failed on basic text accuracy by misspelling the primary brand name and lacked the professional vector finish present in the competitor's image.
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 [klein] 9B
- + Strong iconography and clean vector shapes.
- + Bold layout with good use of negative space.
- − Numerous spelling errors including 'AOILLO', 'EARDHT', and 'TRANSLURAL'.
- − Nonsensical flow of steps that does not follow the requested chronological order.
Qwen Image 2.0 Pro
- + Perfect adherence to the 6-step chronological structure.
- + Excellent text rendering with no spelling mistakes in the primary steps.
- + Clean, professional vertical infographic composition.
- − Icons are slightly less 'flat' than requested (contains more detail/shading).
- − Small character icons at the bottom are inconsistent in style.
Verdict: Qwen Image 2.0 Pro is the clear winner as it accurately followed the 6-step narrative requested by the prompt with perfect spelling. FLUX.2 [klein] 9B failed significantly on prompt adherence and text accuracy, despite having a nice aesthetic style.
Explore each model
Alibaba's Qwen Image 2.0 Pro model offering higher quality image generation with enhanced detail and accuracy