Black Forest Labs' 12-billion parameter flow transformer for high-quality text-to-image generation, suitable for personal and commercial use with streaming support
Settled by community votes across 8 shared challenges, with an AI judge weighing in on each.
FLUX.1 [dev]
24.6
arena score
#16 of 62 in Text-to-Image
Skill signature
· Text-to-Image
Qwen Image Max
21.5
arena score
#35 of 62 in Text-to-Image
Vote tally
Where the votes landed
FLUX.1 [dev]
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.1 [dev]
Qwen Image Max
AI Judge Analysis
FLUX.1 [dev]
- + Excellent adherence to lighting instructions with a clear window source on the left
- + High visual quality with realistic reflections on the glass and spheres
- + Beautiful composition with a cinematic shallow depth of field
- − The 'cube' structure is somewhat ambiguous, appearing more like a glass frame or overlapping panes
Qwen Image Max
- + Perfect geometric representation of a glass cube
- + Strict adherence to all prompt elements including the green plant visible through the glass
- + Good texture on the wooden table and red book
- − The sphere appears to be floating unnaturally without a shadow or resting point on the bottom of the cube
- − Lighting is a bit flat compared to Model A
Verdict: Both models followed the prompt instructions perfectly, including the specific spatial relationships between the book, cube, sphere, and plant. FLUX.1 [dev] produced a more aesthetically pleasing image with superior lighting and materials, while Qwen Image Max produced a more accurate geometric cube. FLUX.1 [dev] is the winner for its more realistic rendering of light and glass.
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.1 [dev]
Qwen Image Max
AI Judge Analysis
FLUX.1 [dev]
- + Excellent skin texture and realistic eye detail
- + Great shallow depth of field effect with soft bokeh
- − Missed the request for beads in the hair
- − Character looks more like a fashion model than a 'battle-worn' warrior, with very few scars or dirt
Qwen Image Max
- + Captures the 'battle-worn' aesthetic perfectly with deep scars and grime
- + Includes all prompt details including beads in hair and ornate engraving
- + Superior leather and fabric texture rendering
- − Slightly aggressive sharpening makes some textures look gritty
- − The torch in the background is a bit distracting compared to the soft bokeh of the other model
Verdict: Qwen Image Max followed the prompt much more accurately, successfully incorporating specific details like the hair beads, ornate engravings, and a truly battle-worn appearance. FLUX.1 [dev] produced a high-quality portrait, but the character was too clean and missed several key descriptors from the 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.1 [dev]
Qwen Image Max
AI Judge Analysis
FLUX.1 [dev]
- + Successfully separates the burger into several suspended layers.
- + Clean professional lighting on the food items.
- − Completely failed to include the 'MAGIC BURGER' title text.
- − Ignored the requirement for the price to be in a starburst.
- − The background is static and lacks the fiery energy requested.
Qwen Image Max
- + Excellent adherence to all text requirements, including font effects and starburst.
- + Captures a high sense of motion with embers, smoke, and flying ingredients.
- + Strong photorealistic textures on the patty and bun.
- − The 'exploded' effect is less pronounced than Model A, as the main components are still largely touching.
Verdict: Qwen Image Max is the clear winner as it followed every part of the complex prompt, including all three specific text elements with the requested fiery effects. While FLUX.1 [dev] produced a clean 'deconstructed' look, it failed to include the main title and specific layout elements like the starburst.
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.1 [dev]
Qwen Image Max
AI Judge Analysis
FLUX.1 [dev]
- + Excellent photorealism in the capybara's fur and the woman's face.
- + Accurate rendering of the requested taxi sign and cap text.
- + Captures the 'bored' expression of the passenger perfectly.
- − Internal composition is confusing; it looks like both are in the front seat or the car is very short.
- − The steering wheel appears to be on the wrong side or duplicated with the passenger.
Qwen Image Max
- + Strong composition showing a clear front-to-back spatial relationship within the vehicle.
- + Very realistic taxi interior details including scuffs on the ceiling and dashboard instruments.
- + Highly detailed texture on the capybara's jacket.
- − The hands on the steering wheel look more like human/primate hands than capybara paws.
- − The human passenger is slightly out of focus and has some facial distortion.
- − The cap is floating slightly off of the capybara's head.
Verdict: FLUX.1 [dev] produced a much higher quality image in terms of texture and lighting, but struggled with the spatial layout of the car interior, making it look like the woman was sitting next to the capybara. Qwen Image Max handled the complex perspective of a taxi cab interior much better, placing the woman clearly in the back seat, even though it failed on the anatomy of the animal's 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.”
FLUX.1 [dev]
Qwen Image Max
AI Judge Analysis
FLUX.1 [dev]
- + Strong cinematic lighting with a vibrant color palette.
- + Clean, thorn-based border framing.
- − Several text errors including 'Falloween Rancy' and typos in the details.
- − Missing the web element in the border.
- − Composition feels more like a modern poster than a vintage invitation.
Qwen Image Max
- + Near-perfect adherence to all text requirements with elegant gothic fonts.
- + Accurately represents the 'vintage parchment' look with cobwebs and thorns.
- + Excellent layout that balances the invitation elements naturally.
- − The jack-o-lantern is slightly less 'glowing' compared to model A.
Verdict: Qwen Image Max is the clear winner as it followed every detail of the prompt, including complex text and specific design elements like the parchment texture and spider webs. In contrast, FLUX.1 [dev] struggled significantly with the text rendering, producing several spelling errors and failing to include the requested 'Halloween Party Invitation' title correctly.
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.1 [dev]
Qwen Image Max
AI Judge Analysis
FLUX.1 [dev]
- + Excellent miniature/diorama aesthetic with a clear 'toy' feel
- + Subtle and sophisticated lighting with soft shadows
- + Cleanly rendered Japanese flag icon and small raised base
- − Text rendering is poor with 'SUSHI' misspelled as 'SUSH CATON' and random characters at the top
- − Very shallow depth of field causes excessive blurring on the subject
Qwen Image Max
- + Perfect text rendering for both 'JAPAN' and 'SUSHI'
- + High-quality PBR materials with realistic textures on the rice and fish
- + Strict adherence to the 45-degree isometric perspective and composition
- − The glass base has some minor geometry clipping at the corners
- − Visual style is slightly more 'realistic product render' than 'miniature 3D cartoon'
Verdict: Qwen Image Max is the clear winner as it followed every instruction, specifically nailing the text rendering which FLUX.1 [dev] failed to spell correctly. Qwen Image Max also provided a more diverse and high-detail sushi selection with excellent lighting and material properties, whereas FLUX.1 [dev] suffered from a heavy blur and poor typographic execution.
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.1 [dev]
Qwen Image Max
AI Judge Analysis
FLUX.1 [dev]
- + Warm, consistent lighting that creates a bright and joyful atmosphere.
- + Clean composition with distinct, expressive characters.
- − Failed to follow the prompt's mascot list, omitting the kitten and adding two of the same puppy.
- − Highly stylized/cartoony look that ignores the 'hyper-photorealistic' requirement.
- − Animals have an artificial, 3D-render toy aesthetic.
Qwen Image Max
- + Successfully includes all requested elements: puppy, kitten, and fox kit in a realistic style.
- + Excellent lighting with visible god rays and detailed dew sparkles as requested.
- + Captures the 'tumbling' and 'playful' action much better than the static lineup in Model A.
- − The 'bunny' is missing or merged into one of the other creatures' forms.
- − Anatomy on the fox's paws is slightly awkward near the puppy.
Verdict: Qwen Image Max is the clear winner as it adheres to the 'hyper-photorealistic' style and correctly includes the specific mix of animals (kitten, fox, puppy), whereas FLUX.1 [dev] produced a cartoony image and failed to include the kitten entirely. Qwen Image Max also better captured the requested environmental effects like god rays and dew sparkles.
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.1 [dev]
Qwen Image Max
AI Judge Analysis
FLUX.1 [dev]
- + Features a very clean vector style suitable for a logo.
- + Follows the color palette closely with a light, warm cream background.
- − Several spelling errors including 'Flariláan' and 'Reseaurant'.
- − Includes extraneous numbers like '11011' and '1941' not requested.
Qwen Image Max
- + Perfect text rendering of 'Caffé Florian' and 'Est. 1720'.
- + Excellent vintage texture on the background and high-quality illustration details on the cloche.
- + Great balance and composition for a vintage brand identity.
- − The cloche is a bit large relative to the text for a standard logo format.
Verdict: Qwen Image Max is the clear winner as it flawlessly rendered the requested text and date, whereas FLUX.1 [dev] suffered from multiple spelling hallucinations and unnecessary extra text. Qwen Image Max also delivered a more cohesive vintage aesthetic with superior texture and illustrative depth.
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.