Black Forest Labs' distilled 9 billion parameter image generation model with sub-second inference and multi-reference support
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
FLUX.2 [klein] 9B
#13 of 32 in Image Editing
Qwen Image 2.0
#34 of 62 in Text-to-Image
Where the votes landed
FLUX.2 [klein] 9B
0%
win rate
Ties
0%
Qwen Image 2.0
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 photorealistic rendering of the glass material with realistic optical distortions.
- + Very natural lighting and depth of field, with soft window light correctly falling across the wooden table.
- + Clean, logical composition with a high-quality wood grain texture.
- − The glass container looks more like a hollow vase than a solid 'cube' due to the rounded edges and thick bottom.
- − The blue sphere appears to be floating mid-air without an obvious physical support.
Qwen Image 2.0
- + Better representation of a sharp-edged 'cube' geometry.
- + Captures all prompt elements including the red book, blue sphere, and plant placement correctly.
- + Clearer visibility of the green plant through the glass panes.
- − The reflections and refractions are physically inconsistent; the blue sphere's reflection on the side panel is confusing and looks like a second object.
- − The lighting is flatter and lacks the atmospheric quality of Image A.
Verdict: FLUX.2 [klein] 9B produces a far more realistic and aesthetically pleasing photograph with superior lighting and texture, although the cube's shape is slightly rounded. Qwen Image 2.0 follows the geometric request of a 'cube' more strictly but fails significantly on optical realism, creating confusing reflections that look like multiple spheres inside the glass.
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 [klein] 9B
- + Excellent skin texture and realistic age-related details on the man's face and hands.
- + Highly effective use of depth of field and bokeh from passing car lights.
- + Captures the atmosphere of light rain and wet pavement reflections perfectly.
- − The bike anatomy is slightly awkward where the man's hand meets the frame.
- − The car in the background lacks the requested motion blur, appearing relatively static.
Qwen Image 2.0
- + Strong 'imperfect framing' that feels like a genuine candid street photograph.
- + Good interaction between the subject's hands and the bicycle mechanics.
- + Realistic reflections on the wet pavement.
- − The image quality appears slightly lower with more digital noise.
- − Missed the motion blur requirement for passing cars.
- − Secondary figure on the right is cut off in a way that feels unintentional rather than cinematic.
Verdict: FLUX.2 [klein] 9B delivers a superior cinematic image with much better lighting and skin textures, making it feel like a professional 50mm lens shot. While Qwen Image 2.0 captures the 'candid' and 'imperfect framing' prompts well, it suffers from lower visual fidelity and a less convincing atmosphere of rain.
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 [klein] 9B
- + Superb texture on the engraved armor and weathered leather straps
- + Highly realistic facial features and skin texture
- + Excellent capture of the shallow depth of field and bokeh sparks
- − The braids are quite simple and some beads are missing from specific strands
Qwen Image 2.0
- + Strong prompt adherence for the 'beaded' hair with colorful ornaments
- + Good representation of worn cloth and leather materials
- + Character design feels distinct and rugged
- − The hand and sword hilt area shows significant anatomical distortion
- − The lighting on the face is less nuanced than the competitor
- − Metal textures look slightly flatter and less metallic than Model A
Verdict: FLUX.2 [klein] 9B is the winner due to its superior technical execution, particularly in the rendering of metal textures and facial realism. While Qwen Image 2.0 did a better job including the small beads in the hair as requested, it suffered from noticeable anatomical artifacts in the hand area and generally lower texture clarity.
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 [klein] 9B
- + Stronger adherence to the 'restaurant menu' layout including text-heavy sections and pricing.
- + Professional typography with clear hierarchical bold headers.
- + Clean, minimalist white space usage that feels like a real printable menu.
- − The food photos are repetitive, showing four different pizzas for four different categories.
- − Significant text artifacts and overlapping characters in the main title.
- − The 'grid' layout for photos is limited to one row.
Qwen Image 2.0
- + Excellent grid layout with a diverse range of food photos including salads, pizza, and mains.
- + High-quality, vibrant food photography that enhances the visual appeal.
- + Strong use of colorful accents in the pricing and labels.
- − The text is largely unreadable gibberish with severe artifacts.
- − The layout feels more like a photo gallery or a digital kiosk screen than a traditional paper menu.
- − Lacks the descriptive text blocks or subsections requested for a functional menu.
Verdict: FLUX.2 [klein] 9B followed the prompt's structural requirements better, creating a realistic menu layout with distinct sections for text and prices. However, Qwen Image 2.0 produced far superior food photography and a more effective grid layout, though it failed to create a functional-looking menu. FLUX.2 is the winner for better capturing the 'professional menu' intent despite the repetitive pizza imagery.
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 integration of the starburst with the overall color scheme
- + Superior typography with clean, consistent glowing effects
- + Highly professional commercial composition with dynamic ingredient spacing
- − The 'exploded' effect is slightly more subtle, looking like a tall stack rather than fully separated components
Qwen Image 2.0
- + Strong 'fiery' effect on the main title text
- + Good sense of vertical separation between the top bun and the patty
- + Nice use of smoke and drips to enhance the food texture
- − The pricing starburst looks lower quality and less integrated compared to the rest of the image
- − Secondary text is cramped and less legible against the background
- − The layout feels more cluttered and less like a polished advertisement
Verdict: FLUX.2 [klein] 9B produces a much more professional advertisement with superior typography and a cohesive design that perfectly integrates the pricing starburst. While Qwen Image 2.0 captures the fire effect on the text well, it struggles with layout and the quality of secondary graphic elements.
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
- + Excellent chalk texture within the letters themselves
- + Accurate spelling on all menu items including the date
- + Centered composition with highly realistic chalk smear backgrounds
- − Has a small spelling error in the footer text ('fress' instead of 'fresh')
Qwen Image 2.0
- + Natural café setting provides better context for the prompt
- + Good adherence to the handwriting style requested
- + Clean and legible text layout
- − Incorrect year rendered as '2026' in the image (it says '2026' which is correct, but 'Today's Specials' is slightly less elegant than A)
- − Light and shadow on the board slightly obscure some of the chalk texture details
Verdict: FLUX.2 [klein] 9B followed the prompt with exceptional detail regarding the chalk texture and elegant cursive script, providing a very clean and professional-looking board. Qwen Image 2.0 offered a more realistic environmental shot of a café, though the text rendering lacks the fine-grained chalky 'grain' that FLUX.2 achieved. FLUX.2 is the winner for superior text fidelity and texture, despite a minor typo in the footnote.
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 [klein] 9B
- + Excellent cosmic background with varied planets and nebulae
- + High levels of detail on the astronaut's suit and helmet faceplate
- + Dynamic lighting and cinematic composition
- − Included unwanted hallucinated text at the bottom of the image
- − Failed the specific spatial instruction 'horse on top, not vice versa'
Qwen Image 2.0
- + Strong surreal elements such as the metallic/scaly texture on the horse
- + Clean, high-quality rendering without garbled text
- + Good sense of movement and depth against the Earth horizon
- − Failed the specific spatial instruction 'horse on top, not vice versa'
- − Background is relatively simple compared to Model A
Verdict: Both models failed the negative/spatial constraint to have the horse on top of the astronaut, instead defaulting to the common trope of an astronaut riding a horse. FLUX.2 [klein] 9B provides a more complex and visually interesting background, but Qwen Image 2.0 is preferred as it produces a cleaner image without the nonsensical text found in the first generated output.
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 photorealistic lighting and interior textures
- + Precise placement of the woman in the back seat as requested
- + Detailed capybara fur and human hand rendering
- − Text on the cap is slightly malformed
- − The capybara's hands look a bit too humanoid/dark
Qwen Image 2.0
- + Higher dynamic range and vibrant night colors
- + Very realistic capybara paws on the steering wheel
- + Strong cinematic perspective
- − Failed the positioning prompt as the passenger is in the front seat instead of the back seat
- − The capybara's proportions were slightly compromised by the angle
Verdict: FLUX.2 [klein] 9B is the clear winner because it correctly followed the spatial instruction to place the woman in the back seat, creating a more convincing narrative scene. While Qwen Image 2.0 offered vibrant colors and excellent paw details, it placed the passenger in the front seat, which contradicts the prompt's taxi-ride logic.
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 perfect spelling in all fields
- + Highly cohesive composition including a beautiful thorn and web border
- + Strong cinematic lighting with an atmospheric moody background
- − The parchment texture is slightly less pronounced in the center compared to model B
Qwen Image 2.0
- + Good scroll banner design and vintage parchment texture
- + Clear and legible text
- + Adheres well to the thorn and web border request
- − The main title has a slight typo ('Invitation' is missing the 'i')
- − The lighting on the pumpkin feels a bit flatter and less integrated into the environment than Model A
Verdict: FLUX.2 [klein] 9B followed the prompt perfectly, delivering an image with zero spelling errors and a very polished, professional layout. Qwen Image 2.0 produced a high-quality vintage aesthetic but suffered from a minor typo in the word 'Invitation' and had slightly less impactful lighting. FLUX.2 is the clear winner for its superior text rendering and cinematic atmosphere.
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 3D miniature/cartoon aesthetic that matches the 'soft refined textures' prompt.
- + Perfect isometric viewpoint and diorama base construction.
- + Very clean typography and layout.
- − The flag icon is incorrect, showing a horizontal tricolor instead of the Japanese flag.
- − One sushi piece features a wrap on top of fish which is somewhat unconventional.
Qwen Image 2.0
- + Correct representation of the Japanese flag.
- + High-quality PBR material rendering on the fish textures.
- + Good text placement and clarity.
- − The perspective is more of a standard 3/4 view rather than the requested 45° isometric.
- − Misses the specific 'miniature 3D cartoon' style, leaning more toward a photorealistic product shot.
Verdict: FLUX.2 [klein] 9B followed the stylistic 'cartoon miniature' and isometric requirements much better than Qwen Image 2.0, creating a more cohesive diorama. While Qwen correctly rendered the flag and had more 'realistic' food textures, FLUX.2 captured the requested artistic intent and layout despite the flag error.
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
- + Excellent dramatic lighting with clear 'god rays' and backlighting on fur.
- + Vibrant color palette and balanced composition.
- + High-quality rendering of various butterflies.
- − Failed to include the 'baby bunny' requested in the prompt.
- − The kitten's pose and expression appear slightly distorted/uncanny.
Qwen Image 2.0
- + Successfully included all four animals: puppy, kitten, bunny, and fox kit.
- + Better portrayal of the 'tumbling' interaction requested in the prompt.
- + Texture on the kitten and bunny is very realistic.
- − The fox kit has a slightly awkward facial structure and blue eyes that look unnatural.
- − The butterflies are less integrated into the lighting of the scene.
Verdict: While FLUX.2 [klein] 9B produces a more aesthetically pleasing image with superior lighting effects, it failed the instruction to include a bunny. Qwen Image 2.0 followed the prompt more accurately by including all four specific animals and better capturing the playful tumbling action.
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 accent marks
- + Superior vector emblem style with clean, professional lines
- + Subtle paper-like texture perfectly matches the background prompt
- − The steam element is a bit thick, resembling a leaf or hair more than vapor
Qwen Image 2.0
- + Creative use of negative space for the steam effect
- + Good metallic shading on the cloche dome
- − Banner is poorly attached and lopsided
- − Text rendering is slightly inconsistent in weight and spacing
- − The cloche handle is slightly off-center
Verdict: FLUX.2 [klein] 9B is the winner because it provides a much more cohesive and professional vector logo that adheres strictly to the 'emblem style' requested. While Qwen Image 2.0 has interesting shading, it suffers from compositional issues such as a lopsided banner and less refined typography.
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 flat-vector aesthetic with clean iconography
- + Follows the NASA-inspired color palette effectively
- + Good use of negative space for the profile silhouettes
- − Significant spelling errors throughout the text (e.g., 'AOILLO', 'EARDHT', 'LANDINING')
- − The flow of the infographic is confusing and does not clearly follow the 1-6 logical sequence
Qwen Image 2.0
- + Excellent adherence to the requested 6-step sequence
- + Significantly better text rendering with mostly correct spelling
- + Clear vertical composition that accurately reflects the mission progression
- − The 'Descent' icon is a bit messy with overlapping vector lines
- − Smaller text in the bottom left 'Armstrong Aldrin Collins' is slightly cramped
Verdict: Qwen Image 2.0 is the clear winner as it successfully followed the complex 6-step prompt while maintaining high text legibility and a logical vertical flow. FLUX.2 [klein] 9B captured the requested art style well, but failed significantly on spelling and the logical ordering of the infographic 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