Head to head
Esc

Models · slot A

to navigate to pick

FLUX.1 [schnell] FP8 Black Forest Labs Qwen Image 2512 Alibaba

Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.

FLUX.1 [schnell] FP8

19.0 arena score

#46 of 62 in Text-to-Image

Skill signature · Text-to-Image

Qwen Image 2512

22.9 arena score

#30 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.1 [schnell] FP8

0.0%

win rate

Ties

0.0%

Qwen Image 2512

100.0%

win rate

0.0% 0.0% ties 100.0%
Shared challenges 13

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 [schnell] FP8
Qwen Image 2512

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent handling of glass transparency and light refraction.
  • + The cube structure has sharp, realistic edges.
  • + Strong adherence to the 'soft light from the left' instruction.
  • The glass object is a rectangular prism rather than a cube.
  • The sphere appears to be floating on an internal shelf rather than sitting on the bottom.

Qwen Image 2512

  • + Correctly generates a cube-shaped glass container.
  • + The plant is clearly visible through the glass panels as requested.
  • + The sphere is naturally placed on the bottom surface.
  • The glass has an overly green tint that looks less like clear glass.
  • The physics of the reflection of the blue sphere on the right panel seems inconsistent.

Verdict: Qwen Image 2512 followed the spatial and geometric prompts more accurately by providing a true cube with the sphere on the bottom and the plant visible through multiple panes. FLUX.1 [schnell] FP8 produced a more aesthetically pleasing image with better lighting, but it failed on the specific geometry by creating a rectangular prism instead of a cube.

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.”

FLUX.1 [schnell] FP8
Qwen Image 2512

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent handling of wet pavement reflections and light quality
  • + Technically accurate bike frame geometry
  • + Realistic skin textures on the man
  • Cars in the background are sharp, missing the requested motion blur
  • The man looks significantly more Caucasian than Japanese
  • Lack of visible rain droplets despite the wet ground

Qwen Image 2512

  • + Successfully captures the requested motion blur in the background traffic
  • + Subject's ethnicity and facial features are much more accurate to the prompt
  • + Captures the appearance of falling rain and a more convincing 'candid' street photography style
  • Major anatomical errors with the hands (multiple fingers blending/missing)
  • Bicycle frame geometry is disjointed and nonsensical at the joints
  • The man is posing for the camera rather than being 'candid' while repairing

Verdict: FLUX.1 [schnell] FP8 produces a much cleaner image with better technical quality and bike detail, but it fails the specific ethnic request and ignores the motion blur requirement. Qwen Image 2512 much better captures the look of Japanese street photography and the requested motion blur, though it suffers from significant anatomical errors in the hands and bicycle structure. FLUX.1 [schnell] FP8 is the preferred winner as its flaws are stylistic rather than structural failures.

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 [schnell] FP8
Qwen Image 2512

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Intense, high-contrast lighting that creates a dramatic atmosphere
  • + Extremely sharp focus on the iris and skin texture of the face
  • + Clean, cinematic composition with effective bokeh
  • Misses several prompt requirements including the braids and beads in the hair
  • The 'battle-worn' aspects like scars and dirt are very subtle to non-existent
  • Armor is dark and lacks the requested 'ornate engraved' visibility

Qwen Image 2512

  • + Excellent adherence to all prompt details including braids, beads, and scars
  • + Highly detailed engraving on the plate armor and visible leather straps
  • + Accurate depiction of a battle-worn character with realistic dirt and wounds
  • The torch in the background is a bit distracting compared to the requested bokeh focus
  • Overall image sharpness is slightly softer than Model A in the hair area

Verdict: While FLUX.1 [schnell] FP8 produced a striking, high-quality portrait, it failed to include several key descriptive elements from the prompt such as the braids and beads. Qwen Image 2512 followed every instruction meticulously, providing the specific armor details, hair styling, and battle-worn features that were requested.

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.”

FLUX.1 [schnell] FP8
Qwen Image 2512

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Stronger adherence to the white background request
  • + Better organization of sections for appetizers, pizza, and mains
  • + Clean and highly legible layout
  • Several spelling errors in headings like APPTIZERS and SECCER
  • Text body is mostly illegible gibberish

Qwen Image 2512

  • + Excellent grid layout for food photography
  • + High-quality food images with vibrant colors
  • + Creative use of color accents in the categorization
  • Nonsense text for headers and menu items
  • Failed to include a specific section for Pizza/Pies correctly in the header logic

Verdict: FLUX.1 [schnell] FP8 offers a layout that feels more like a physical menu with clear sections and a white minimalist background, though it suffers from spelling errors in the headers. Qwen Image 2512 produces superior food photography and a more modern graphic design feel, but the text is entirely nonsensical and it missed some of the specific section categories. FLUX is slightly better for a functional layout, while Qwen is better for visual impact.

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 [schnell] FP8
Qwen Image 2512

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Clean imagery for the central burger.
  • + Follows the request for a dark background with embers.
  • Major text errors including 'LIIMITED' and 'LIIMIED TIME NEEY'.
  • Incorrect price rendering, showing €69 as the primary focus instead of €6.99.
  • The burger is largely intact rather than 'exploded' as requested.

Qwen Image 2512

  • + Perfect text adherence with the requested 'fiery, glowing effect'.
  • + Accurately represents an 'exploded' burger with separated components.
  • + Successfully integrates the stardust/starburst for the price with the correct amount.
  • The 'LIMITED ONLY' text is missing the word 'TIME' from the specific requested phrase.

Verdict: Qwen Image 2512 followed the prompt much more effectively, particularly regarding the 'exploded' burger layout and the fire-themed typography. FLUX.1 [schnell] FP8 suffered from significant spelling errors and failed to correctly render the price or the exploded composition.

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.”

FLUX.1 [schnell] FP8
Qwen Image 2512
0% wins 0% ties 100% wins

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Natural chalk texture on the board surface
  • + Accurate date following the prompt
  • Numerous spelling errors including 'Traffle Mushnroom', 'Octopuss', and 'Llemens'
  • Inconsistent layout with overlapping text and repeated words
  • Failed to use elegant cursive for the title

Qwen Image 2512

  • + Excellent adherence to the 'elegant cursive' style for the title and menu items
  • + High text accuracy with minimal spelling errors beyond a slight typo in 'Risito'
  • + Beautiful composition with realistic chalk dust and eraser smudges
  • Slightly gold/yellow tint to the chalk which wasn't specifically requested but looks aesthetically pleasing

Verdict: Qwen Image 2512 is the clear winner as it followed all stylistic instructions, including the requirement for elegant cursive handwriting and high text legibility. In contrast, FLUX.1 [schnell] FP8 suffered from significant spelling hallucinations and a messy, repetitive layout that looked less professional.

The Reversed Rodeo

Text-to-Image

“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”

FLUX.1 [schnell] FP8
Qwen Image 2512

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent adherence to the 'horse on top' spatial instruction.
  • + Cinematic lighting and high level of detail in the machinery.
  • + Creative interpretation of the surreal prompt.
  • The 'astronaut' is represented as a boxy machine rather than a traditional suited person.
  • Anatomical oddity with a second horse head appearing behind the first.

Qwen Image 2512

  • + High visual quality with realistic textures on the horse and suit.
  • + Clear cinematic background showing the Earth's curve.
  • Failed the primary spatial instruction of the prompt ('horse on top, not vice versa').
  • Very traditional interpretation that ignores the 'surreal' request.

Verdict: FLUX.1 [schnell] FP8 correctly followed the difficult spatial instruction to place the horse on top, creating a surreal and cinematic image. Qwen Image 2512 ignored the specific 'not vice versa' instruction and produced a standard astronaut riding a horse, which failed the core prompt challenge.

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 [schnell] FP8
Qwen Image 2512

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent text rendering on the hat
  • + Warm, Cinematic lighting used for the interior
  • The passenger appears to be holding two phones which is illogical
  • The capybara's paw placement is clumsy with one front paw reaching too high

Qwen Image 2512

  • + Highly accurate interpretation of the capybara's expression and anatomy
  • + Superior passenger expression that perfectly matches the 'bored' prompt
  • + Better overall composition looking through the windshield
  • The hands on the steering wheel have slightly odd texture
  • Missing explicit 'TAXI' text on the driver hat

Verdict: Qwen Image 2512 is the winner because it captured the specific nuances of the prompt much better, particularly the 'completely normal, bored expression' of the passenger. While FLUX.1 [schnell] FP8 has great lighting, it failed on the passenger's logic (giving her two phones) and produced a less convincing capybara posture.

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 [schnell] FP8
Qwen Image 2512

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Atmospheric cinematic lighting with a good sense of depth in the background
  • + Strong jack-o-lantern design that glows effectively
  • Numerous spelling errors in both the banner and the footer text
  • The layout of the bottom text is messy and nonsensical
  • Lack of requested webs and thorns in the border

Qwen Image 2512

  • + Excellent adherence to all prompt elements including webs and thorns
  • + Almost perfect text rendering for the event details
  • + Highly legible and stylish gothic typography
  • Slight spelling error in the main title ('Hallowern' instead of 'Halloween')
  • The lighting is less 'vintage parchment' and more clean digital art

Verdict: While FLUX.1 [schnell] FP8 captures a moodier atmosphere, it fails significantly on text legibility and detail accuracy. Qwen Image 2512 followed the complex instructions for the border and the scroll banner much better, and despite a minor typo in the title, provided a much more usable invitation layout.

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 [schnell] FP8
Qwen Image 2512

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent 3D shader work with soft, jelly-like textures
  • + Clean, minimalist aesthetic that matches the 'cartoon' request
  • Failed the text prompt, repeating 'JAPAN' with errors instead of 'SUSHI'
  • The flag icon is integrated into the text incorrectly

Qwen Image 2512

  • + Perfect text rendering of both 'JAPAN' and 'SUSHI'
  • + Includes all requested elements: text, flag, diorama base, and garnish
  • + Beautiful interpretation of a miniature diorama with varied sushi types
  • Background is slightly more saturated than requested but still blue

Verdict: While FLUX.1 [schnell] FP8 has very appealing soft-3D textures, it completely failed the text requirement by omitting the word 'SUSHI' and misspelling the bottom line. Qwen Image 2512 followed every instruction perfectly, including complex text, the flag icon, and a more creative diorama base while maintaining the isometric 3D cartoon style.

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 [schnell] FP8
Qwen Image 2512

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent vibrant color palette and warm lighting
  • + Dynamic and playful composition
  • + Successful rendering of multiple orange-toned baby animals
  • Failed to include a bunny, replacing it with a third feline-like creature
  • Anatomical errors such as a five-legged appearance in the center
  • Butterflies have a simplified, sticker-like appearance

Qwen Image 2512

  • + Successfully included all four requested animals: puppy, kitten, bunny, and fox
  • + Highly detailed fur textures and realistic anatomy
  • + Clearly defined god rays and dew sparkles on the grass
  • The composition is a bit static with the animals posing rather than 'tumbling'
  • The kitten's tail is missing or obscured by the puppy's paw

Verdict: While FLUX.1 [schnell] FP8 captured a more whimsical atmosphere with beautiful lighting, it failed the prompt's core requirement by omitting the bunny and including a strange fifth animal cluster. Qwen Image 2512 followed the prompt perfectly, rendering each specific animal with high anatomical accuracy and superior fur textures.

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 [schnell] FP8
Qwen Image 2512

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Strong minimalist vector aesthetic
  • + Clean color palette adherence
  • Significant spelling errors in the brand name
  • Misinterpreted cloche as a building dome
  • Awkward typography placement

Qwen Image 2512

  • + Perfect text rendering of the brand name and date
  • + Excellent illustration of the cloche and steam
  • + High-quality vintage texture and shading
  • Slightly less 'minimalist' than a standard flat vector logo

Verdict: Qwen Image 2512 is the clear winner as it followed every part of the prompt, including perfect spelling and a correct representation of a restaurant cloche. FLUX.1 [schnell] FP8 failed to spell the name correctly and provided a confusing architectural dome rather than a food dome.

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.”

FLUX.1 [schnell] FP8
Qwen Image 2512

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Successfully captures a minimalist, clean vector aesthetic
  • + Follows the NASA color palette precisely with navy, white, and muted red
  • + Displays structured typography for the main title
  • Text is largely gibberish and poorly rendered
  • Iconography is inconsistent and does not accurately represent the mission stages
  • Layout feels cluttered and illogical toward the bottom

Qwen Image 2512

  • + Successfully illustrates all 6 requested stages with specific icons like the Saturn V and Lunar Module
  • + Text is legible and mostly accurate with recognizable names like Armstrong and Aldrin
  • + Excellent composition that flows logically from launch to landing
  • Includes an unprompted orange/gold color that deviates from the requested palette
  • Contains some repeated labels (e.g., '2. Earth Orbit' appears twice)
  • The style is more illustrative than the requested minimalist 'flat-vector' style

Verdict: Qwen Image 2512 is the clear winner as it successfully interprets all 6 stages of the mission with relevant, high-quality illustrations and legible text. While FLUX.1 [schnell] FP8 captures the 'minimalist' aesthetic more accurately, its failure to generate readable text or distinct, recognizable mission icons makes it much less effective as an infographic.

Next steps

Explore each model