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 8 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 Max
21.3
arena score
#35 of 62 in Text-to-Image
Vote tally
Where the votes landed
FLUX.2 [pro]
0%
win rate
Ties
0%
Qwen Image Max
0%
win rate
Shared challenges
8
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 Max
AI Judge Analysis
FLUX.2 [pro]
- + Excellent adherence to lighting instructions with realistic soft window light.
- + Highly realistic glass textures and refractions.
- + Natural and balanced composition with accurate plant placement.
- − The sphere appears more matte than expected for a glossy scene.
- − The plant is very blurred in the background, making it less distinct.
Qwen Image Max
- + Bold, vibrant colors with a very glossy blue sphere.
- + Shows the plant clearly through the glass walls of the cube.
- + Strong focus on the central objects.
- − The sphere is levitating, which defies natural physics without support.
- − The reflection on the bottom glass panel is physically inconsistent with the objects above.
- − The book has a strange black pattern not requested in the prompt.
Verdict: FLUX.2 [pro] is the superior model because it adheres to the prompt while maintaining physical realism, correctly placing the sphere on the base of the cube and providing authentic soft window light. Qwen Image Max has more vibrant colors but suffers from logical errors, such as a levitating sphere and distorted reflections that don't match the scene structure.
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 Max
AI Judge Analysis
FLUX.2 [pro]
- + Excellent depiction of warm torchlight reflecting off the polished engraving
- + Highly lifelike eyes and skin texture including realistic scars
- + Very shallow depth of field with effective bokeh
- − The 'battle-worn' aspect is slightly undermined by the very clean, shiny highlights on the armor
Qwen Image Max
- + Superb attention to fine texture on the worn leather and torn cloth underlayer
- + Great characterization showing age and battle fatigue through facial lines
- + Complex hair braiding with ornate beads
- − Torchlight reflects less naturally on the metal compared to Model A
- − Composition is a bit more centered and rigid
Verdict: Both models followed the prompt excellently, with FLUX.2 [pro] delivering a more cinematic lighting effect and realistic skin Rendering. However, Qwen Image Max captured the gritty details of the 'battle-worn' prompt better, especially in the tattered leather and cloth textures. FLUX.2 [pro] wins slightly on overall visual polish and the quality of the 'lifelike eyes'.
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 Max
AI Judge Analysis
FLUX.2 [pro]
- + Excellent typography with a cohesive 'fiery' glow effect across all text elements.
- + Superior representation of an 'exploded' burger with clear separation between every ingredient.
- + Clean, professional composition that looks like a high-end finished advertisement.
Qwen Image Max
- + High visual energy with dynamic motion blur and flying debris.
- + Textural detail on the patty and bun is very appetizing and sharp.
- + The starburst effect for the price is very impactful and fits the prompt well.
- − Failed to fully 'explode' the burger; the top bun and patty are still touching, which misses the 'suspended in mid-air' instruction for all components.
- − The text 'LIMITED TIME ONLY' is slightly messy and less legible compared to Model A.
Verdict: FLUX.2 [pro] followed the prompt more accurately by fully separating every burger component, creating a true 'exploded' view. While Qwen Image Max had excellent textural detail and dynamic energy, it failed to suspend all ingredients individually, and its text integration was less polished than the clean, professional execution of FLUX.2 [pro].
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 Max
AI Judge Analysis
FLUX.2 [pro]
- + Superior photorealism and lighting, particularly the cinematic bokeh and dashboard details.
- + Excellent character posing, showing a clear interaction between the capybara's paws and the steering wheel.
- + The capybara's hat is more accurate to a traditional taxi driver cap.
- − The capybara paws look a bit more like dark gloves or primate hands than natural capybara feet.
Qwen Image Max
- + Clear visibility of the businesswoman in the back seat matching the 'bored' prompt description.
- + Realistic textures on the capybara's fur and the worn interior of the taxi.
- − The capybara paws are poorly rendered, appearing with too many fingers and a human-like wrist structure.
- − The framing is slightly cramped compared to Model A.
Verdict: FLUX.2 [pro] is the winner due to its superior lighting, cinematic composition, and more realistic integration of the animal into the scene. While Qwen Image Max follows the prompt well, it suffers from anatomical errors in the paws and a less convincing 'taxi driver' hat compared to the professional look in the first image.
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 Max
AI Judge Analysis
FLUX.2 [pro]
- + Excellent photographic rendering of the jack-o-lantern and volumetric lighting.
- + Clean, highly legible text with perfect spelling.
- + Strong cinematic atmosphere with realistic fog and moonlit clouds.
- − The border is very dark and some of the thorns/webs are lost in the shadows.
- − The scroll banner is a bit simple compared to the rest of the illustration.
Qwen Image Max
- + Beautifully detailed gothic border that clearly incorporates webs and thorns.
- + More stylized, artistic scroll banner that feels vintage.
- + Excellent use of the 'parchment' texture throughout the background.
- − The text 'Invitation' has a slight kerning/rendering artifact on the 'v'.
- − The transitions between the central illustration and the parchment background are a bit soft/blurry.
Verdict: Both models followed the prompt perfectly, including all requested text and stylistic elements. FLUX.2 [pro] is preferred for its superior lighting effects and clean typography, whereas Qwen Image Max has a better thematic border and parchment texture that feels more consistent with a vintage poster.
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 Max
AI Judge Analysis
FLUX.2 [pro]
- + Excellent adherence to the 'cartoon' and 'soft texture' style description.
- + Clean typography that is perfectly centered and integrated.
- + Logical diorama base design with a professional 3D render look.
Qwen Image Max
- + High textural detail on the fish and rice that leans into the 'realistic PBR' instruction.
- + Good use of transparency for the glass diorama base.
- + Clear and legible text rendering.
- − Missed the 'cartoon' aesthetic requested, appearing more like a photorealistic miniature.
- − Text placement is slightly crowded compared to the clean layout of Image A.
- − The flag icon is placed to the side rather than following the 'below it' instruction for the layout hierarchy.
Verdict: FLUX.2 [pro] followed the stylistic instructions much better, capturing the '3D cartoon' and 'soft refined texture' vibe perfectly while maintaining clean, centered typography. Qwen Image Max focused more on the PBR realism, resulting in a less cohesive look that missed the specified cartoon aesthetic and diorama layout guidelines.
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 Max
AI Judge Analysis
FLUX.2 [pro]
- + Excellent anatomical accuracy of all four specified animals.
- + Beautiful soft lighting and highly realistic fur textures.
- + Strong composition with a focused interaction between the animals.
- − The animals are sitting relatively still rather than 'tumbling' as requested.
Qwen Image Max
- + Captures the 'tumbling' and 'chasing' aspect of the prompt more dynamically.
- + Features distinct and visible god rays as requested.
- + Vibrant colors in the flowers and butterflies.
- − Failed to include the bunny, instead generating two golden retrievers.
- − The fox's front leg has anatomical issues where it connects to the body.
- − The image has a slightly more saturated, 'AI-processed' look compared to the photorealism of the other.
Verdict: FLUX.2 [pro] followed the subject requirements perfectly, including all four specific animals with high photorealism and beautiful textures. Qwen Image Max failed to include the bunny and had some anatomical glitches, although it did a better job of capturing the active 'tumbling' motion and the 'god rays' mentioned in the prompt. FLUX.2 [pro] is the preferred image due to its superior realism and adherence to the requested animal list.
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 Max
AI Judge Analysis
FLUX.2 [pro]
- + Excellent vector emblem style with clean lines
- + Accurate spelling and elegant typography
- + Highly professional composition with a subtle paper texture
- − The 'Est. 1720' text is slightly small relative to the banner
Qwen Image Max
- + Classic vintage aesthetic with great shading on the cloche
- + Correct spelling and clear hierarchy
- + Stylized steam adds a nice flourish to the icon
- − Background texture is a bit heavy-handed and looks like digital stains
- − Typography is slightly less 'classic' and feels a bit bulky for a minimalist logo
Verdict: FLUX.2 [pro] followed the 'vector emblem' and 'minimalist' instructions perfectly, creating a clean, balanced logo that feels authentically high-end. Qwen Image Max also performed well with the prompt details and spelling, but the overall design is heavier and the background texture is more distracting compared to the professional finish of FLUX.2 [pro].
Next steps
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.