Black Forest Labs' distilled 9 billion parameter image generation model with sub-second inference and multi-reference support
Settled by community votes across 8 shared challenges, with an AI judge weighing in on each.
FLUX.2 [klein] 9B
#13 of 32 in Image Editing
Qwen Image Max
#35 of 62 in Text-to-Image
Where the votes landed
FLUX.2 [klein] 9B
0.0%
win rate
Ties
0.0%
Qwen Image Max
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 photorealistic textures, particularly on the wooden table and red book cover.
- + Accurate glass refraction and distortion of the plant behind.
- + Perfect lighting and caustic effects on the table surface.
- − The glass object is more of a hollow vase/container than a solid cube.
- − The blue sphere appears small and somewhat marble-like rather than a clean geometric sphere.
Qwen Image Max
- + Perfect adherence to the 'cube' geometry with clean, sharp edges.
- + Large, clear blue sphere centered perfectly.
- + Strong adherence to all spatial instructions.
- − The sphere appears to be levitating unnaturally without the support logic shown in Image A.
- − The glass lacks significant refractive distortion of the background plant.
- − Noticeable digital artifacts/patterns on the book cover.
Verdict: FLUX.2 [klein] 9B produces a more photorealistic image with superior light handling and textures, though the cube is shaped more like a vessel. Qwen Image Max follows the geometric prompt more literally with a perfect cube and sphere, but feels less grounded in reality due to the levitating sphere and flatter glass rendering. FLUX.2 is the winner for its convincing material quality and realistic environmental interaction.
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
- + Excellent rendering of ornate engraved textures on the plate armor.
- + Very high skin and hair detail with clear, lifelike eyes.
- + Clear presence of small beads in the hair braids as requested.
- − Scars look slightly superficial, like red paint rather than deep tissue.
- − Torchlight is present but feels a bit static and less integrated into the environment.
Qwen Image Max
- + Masterful depiction of battle-worn skin with realistic deep scars and grime.
- + Superior lighting and atmosphere with dynamic sparks and believable warm reflections.
- + Highly detailed leather straps with convincing wear, tear, and texture.
- − Engravings on the armor are slightly less crisp than Model A.
- − Face is slightly asymmetric in a way that looks like a generation artifact rather than a wound.
Verdict: Both models followed the prompt exceptionally well, but Qwen Image Max creates a more atmospheric and convincing 'battle-worn' appearance through superior skin textures and lighting integration. While FLUX.2 [klein] 9B has sharper armor engravings, Qwen Image Max feels more like a cohesive cinematic still with better depth and material realism.
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
- + Precise text rendering with clean, professional font styles.
- + Excellent photorealistic textures on the patties and bun.
- + Dynamic 'exploded' composition with components clearly separated.
- − The 'magic burger' text is slightly less fiery than the prompt requested.
- − The sauce droplets look slightly stylized rather than fully photorealistic.
Qwen Image Max
- + Strong fiery effects on the main title text.
- + Atmospheric lighting with realistic smoke and char on the meat.
- + Good sense of motion with flying embers and debris.
- − The burger components are mostly touching, failing the 'exploded' instruction.
- − The top bun texture is a bit inconsistent with real food photography.
Verdict: FLUX.2 [klein] 9B provides a superior technical layout for an advertisement, accurately separating the burger components in mid-air as requested. While Qwen Image Max captures the fiery atmosphere well, it fails to deliver the 'exploded' view of the ingredients. FLUX.2 [klein] 9B is the preferred choice for its clear composition and high-quality text integration.
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 composition with a POV from the dashboard that clearly shows both the driver and the passenger.
- + The capybara's head is perfectly oriented to be looking ahead through the windshield.
- + High level of photorealism and clean lighting, especially on the passenger's face and phone.
- − The character in the passenger seat is physically positioned in the front passenger seat rather than the back seat as requested.
- − The capybara's paws look somewhat like human hands with gloves rather than natural paws.
Qwen Image Max
- + Correctly places the businesswoman in the back seat at a distance from the driver.
- + The texture of the capybara's fur and the leather of the seats is highly detailed.
- + The capybara's paws look more anatomically distinctive, even if slightly elongated.
- − The perspective is awkward, looking into the driver's side window which makes the steering wheel position look cramped.
- − The capybara is looking out the side window rather than at the road while driving.
- − There are visible artifacts on the car ceiling and the passenger's face is somewhat blurry.
Verdict: FLUX.2 [klein] 9B produces a much cleaner, more professional-looking image with better lighting and a more logical direct composition, although it failed the spatial requirement of placing the passenger in the back seat. Qwen Image Max followed the 'back seat' instruction correctly but suffered from an awkward camera angle and lower overall visual clarity. FLUX.2 is preferred for its superior photorealism and more endearing character depiction.
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 font choice that perfectly matches the gothic aesthetic.
- + Superior cinematic lighting and atmosphere within the central illustration.
- + Perfect text rendering with no spelling errors.
- − The thorn border is a bit repetitive and looks slightly digital.
Qwen Image Max
- + Highly detailed hand-drawn style for the thorns and webs.
- + Includes more variety in bats and spider details within the border.
- + Successful adherence to all prompt elements.
- − The transition between the central dark illustration and the light parchment background is a bit harsh.
- − The scroll banner looks slightly more warped compared to Model A.
Verdict: Both models followed the prompt exceptionally well, producing clear and accurate text. FLUX.2 [klein] 9B wins by a narrow margin because its atmospheric lighting and typography feel more cohesive as a single professional poster, whereas Qwen Image Max has a slightly disjointed 'collage' feel between the central image and the background parchment.
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 toy-like aesthetic
- + Very clean and accurate typography
- + Pleasant wood texture on the diorama base
- − The flag icon is incorrect (appears to be Yemen or Egypt style rather than Japan)
- − The sushi design is a bit overly simplified
Qwen Image Max
- + Perfectly accurate Japanese flag icon
- + High-quality PBR material rendering on the fish and glass base
- + More detailed and recognizable sushi varieties
- − Text is slightly less clean than Model A with more drop shadow than requested
- − The glass base creates more complex reflections than the 'minimal' request implied
Verdict: Qwen Image Max is the superior choice because it correctly identifies and renders the Japanese flag, whereas FLUX.2 [klein] 9B provides an incorrect flag for the country requested. While both models followed the isometric 3D styling well, Qwen Image Max also provided more realistic textures for the food itself.
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 fur texture and lighting on the animals
- + Clean, high-quality rendering of the kitten and fox
- + Clear 'god rays' effect consistent with the prompt
- − Completely missed the 'baby bunny' requirement
- − The kitten's eye orientation is slightly uncanny
Qwen Image Max
- + Successfully captured the 'tumbling together' aspect of the prompt
- + Captures the golden sunrise and dew sparkles more effectively
- + Includes multiple animals in a dynamic interaction
- − Failed to include the 'baby bunny' despite having more animals
- − Included a second dog instead of the requested rabbit
- − The fox's front leg and anatomy are slightly distorted
Verdict: Both models failed to include the baby bunny, meaning they are equal in prompt adherence. FLUX.2 provides a cleaner, sharper aesthetic with more realistic animal features, whereas Qwen Image Max creates a more dynamic and playful composition that better fits the 'tumbling together' description. FLUX.2 is the winner due to superior anatomical accuracy and higher visual clarity.
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 including the correct grave accent on 'Caffè'
- + Superior vector emblem style with clean lines
- + Well-balanced circular composition
- − The steam element is a bit thick and stylized compared to the rest of the logo
Qwen Image Max
- + Beautifully detailed steam and hatching on the cloche
- + Nice parchment-style background texture
- + Accurate handling of requested text and dates
- − Incorrect accent mark on 'CAFFÉ' (acute instead of grave)
- − The cloche is slightly off-center relative to the text
Verdict: FLUX.2 [klein] 9B followed the prompt more effectively by producing a clean, vector-style emblem with perfect spelling and grammar, including the Italian grave accent. Qwen Image Max had excellent artistic detailing on the cloche and steam but failed on the specific typography of the name, using the wrong accent mark.
Explore each model
The Max series of Tongyi Qwen’s image generation model excels across a wide range of generation tasks. Compared with the Plus series, it significantly reduces the “AI-like” feel in generated images, enhancing their realism. It delivers more lifelike material textures for human subjects, finer and more detailed natural textures, and more visually appealing text rendering.