Head to head
Esc

Models · slot A

to navigate to pick

FLUX.1 [schnell] 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]

18.7 arena score

#48 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]

0%

win rate

Ties

0%

Qwen Image 2512

0%

win rate

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]
Qwen Image 2512

AI Judge Analysis

FLUX.1 [schnell]

  • + Excellent visual clarity and high-resolution textures
  • + Beautiful handling of soft window light and reflections
  • + Includes all prompt elements including the plant behind the cube
  • Added an extra blue sphere on top of the book that was not requested
  • Functional physics of the sphere 'floating' inside the cube is a bit surreal

Qwen Image 2512

  • + Perfect spatial adherence to the prompt's layout
  • + Realistic placement of the sphere resting on the bottom of the cube
  • + Captures the green tint often seen in glass edges well
  • The glass cube has a mirror-like floor which wasn't requested
  • Slightly less vibrant color palette compared to image A

Verdict: Both models followed the complex spatial instructions remarkably well. FLUX.1 [schnell] produced a more visually stunning and 'clean' image with better lighting, but it hallucinated an extra blue sphere on top of the book. Qwen Image 2512 followed the prompt more literally without adding extra elements, making it the more accurate tool for this specific set of instructions.

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]
Qwen Image 2512

AI Judge Analysis

FLUX.1 [schnell]

  • + Excellent depiction of wet textures and pavement reflections
  • + Follows the 50mm shallow depth of field requirement well
  • + The bicycle design is relatively coherent and modern
  • Missed the 'motion blur from passing cars' instruction as the traffic appears static
  • The man's hands are anatomically confused and merge with the handlebars
  • Lacks the 'candid' feel, appearing more staged

Qwen Image 2512

  • + Successfully captured motion blur in the passing cars as requested
  • + Strong sense of realism in the subject's face and natural skin texture
  • + Excellent 'candid' composition with imperfect framing that feels authentic
  • The man is crouching next to the bike rather than actively 'repairing' it
  • Some minor artifacting on the bicycle spokes
  • The hand resting on the seat has slightly distorted fingers

Verdict: Qwen Image 2.5-12 is the superior image as it followed nearly all technical prompt instructions, including the difficult 'motion blur' and 'candid' feel. While FLUX.1 [schnell] produced a clean image, it failed to incorporate motion blur and suffered from significant anatomical issues with the subject's hands.

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]
Qwen Image 2512

AI Judge Analysis

FLUX.1 [schnell]

  • + Extremely high-resolution skin texture and pore detail
  • + Intense, lifelike eye rendering
  • + Strong cinematic lighting and bokeh
  • Missed the beads in the hair braids and the bokeh sparks
  • Armor is cut off and lacks the 'ornate engraved plate' detail requested
  • Facial proportions are slightly stylized/exaggerated

Qwen Image 2512

  • + Excellent adherence to all prompt elements, including beads and sparks
  • + Beautifully detailed engraved plate armor and leather straps
  • + Well-balanced composition with a convincing 'battle-worn' appearance
  • Eyes lack the crystalline sharpness of the other model
  • Braids merge slightly awkwardly with facial hair in the crop

Verdict: Qwen Image 2512 is the clear winner for its superior prompt adherence, successfully including the beads, sparks, and detailed armor that FLUX.1 [schnell] largely ignored. While FLUX.1 [schnell] offers more intense facial detail, Qwen Image 2512 provides a much better realization of the paladin concept and specific lighting requests.

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]
Qwen Image 2512

AI Judge Analysis

FLUX.1 [schnell]

  • + Excellent white space utilization for a minimalist aesthetic.
  • + Clean, professional typography that is highly legible.
  • + Strictly followed the requested sections: Appetizers, Pizza, and Mains.
  • The food images in the grid look repetitive and low-quality compared to the layout.
  • The 'ORFEFUS' heading is a hallucination that makes little sense in the context.

Qwen Image 2512

  • + High-quality food photography with vibrant colors.
  • + Creative use of colorful accents through colored icons next to menu items.
  • + Balanced grid layout for the photography section.
  • Included significant spelling errors in all major headings (e.g., 'RESSAGRENT', 'APPETIIZIZERS', '/MEANS').
  • The layout feels slightly cramped, losing the 'minimalist' feel requested in the prompt.

Verdict: FLUX.1 [schnell] captures the minimalist, professional aesthetic of a modern menu much better than Qwen Image 2512, despite the odd gibberish word. While Qwen Image 2512 has superior image quality for the food items, the glaring spelling errors in large bold text make it less successful for a design-focused 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 [schnell]
Qwen Image 2512

AI Judge Analysis

FLUX.1 [schnell]

  • + Excellent photorealistic texture on the meat patty and melting cheese
  • + The lighting on the burger feels very natural and integrated with the fiery theme
  • Spelling error in the main title ('AGIC BURGER') and repeated/incorrect price text
  • Failed the 'exploded' portion of the prompt as the burger is largely assembled
  • Floating crouton-like debris feels disconnected from the burger components

Qwen Image 2512

  • + Perfect text adherence with correct spelling and fiery glowing effects
  • + Successfully interpreted the 'exploded' burger layout with separated components
  • + Dynamic composition with great use of the starburst for the price
  • Slightly less 'gritty' photorealism compared to Model A, with a more polished commercial look
  • The tomato slices and lettuce look a bit more like stock assets than organic components

Verdict: Qwen Image 2512 is the clear winner as it followed every instruction in the prompt, including the complex text requirements and the 'exploded' structural layout. In contrast, FLUX.1 [schnell] failed to spell the product name correctly and kept the burger mostly intact, missing the core concept of the ad.

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]
Qwen Image 2512

AI Judge Analysis

FLUX.1 [schnell]

  • + Natural chalk board texture and lighting.
  • + Clean layout with a legible handwriting style.
  • Numerous spelling errors including 'Pril', 'Taffle', 'Mushmnctiom', and 'Octtoopus'.
  • Fails to follow the request for elegant cursive handwriting for the title.
  • Truncated and repetitive nonsense text at the bottom.

Qwen Image 2512

  • + Excellent spelling accuracy for nearly all requested items.
  • + Successfully renders elegant cursive chalk handwriting as requested.
  • + Authentic chalk details including smudges, dust, and varied stroke pressure.
  • Small typo in 'Risotto' (spelled 'Risitto').
  • The cursive style stays very consistent, looking slightly more like a digital font than natural handwriting in some strokes.

Verdict: Qwen Image 2512 is the clear winner for its superior ability to handle complex text prompts and specific stylistic requests. While FLUX.1 [schnell] creates a nice chalkboard aesthetic, it suffers from significant spelling failures and ignores the cursive requirement, whereas Qwen Image 2512 followed almost all instructions with high fidelity.

The Reversed Rodeo

Text-to-Image

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

FLUX.1 [schnell]
Qwen Image 2512

AI Judge Analysis

FLUX.1 [schnell]

  • + Excellent adherence to the 'horse on top' spatial instruction
  • + Surreal and artistic composition with cinematic lighting
  • + Creative interpretation where the astronaut serves as the mount
  • The horse appears to have two heads or a conjoined body
  • The astronaut's anatomy is a bit jumbled and unclear

Qwen Image 2512

  • + High clarity and realistic lighting on the horse and astronaut
  • + Great face detail inside the helmet
  • + Dynamic and clean composition
  • Failed the negative constraint to have the horse on top
  • A very literal and common interpretation of the prompt

Verdict: While Qwen Image 2512 produces a much cleaner and more realistic image, it completely fails to follow the specific spatial instruction for the horse to be on top. FLUX.1 [schnell] captures the surreal inversion requested by the prompt, despite having some anatomical artifacts with the horse's heads.

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]
Qwen Image 2512

AI Judge Analysis

FLUX.1 [schnell]

  • + Excellent texture on the capybara's fur
  • + Clean composition with a cinematic shallow depth of field
  • + Accurate rendering of the woman's hands and the smartphone
  • Failed to place both paws on the steering wheel as requested
  • The cap is a beanie rather than a traditional taxi driver cap

Qwen Image 2512

  • + Perfect adherence to the 'both front paws on the steering wheel' instruction
  • + Very authentic 'professional' taxi driver cap and dark jacket
  • + Strong storytelling with the woman's bored expression in the background
  • The capybara's paws look more like human hands/fingers
  • The lighting on the capybara's face is a bit flat compared to the background

Verdict: Qwen Image 2512 followed the complex technical instructions much better, correctly placing both paws on the steering wheel and utilizing a more traditional driver's cap. While FLUX.1 [schnell] has slightly more realistic fur and lighting, it failed on the specific pose of the paws and generated a simple beanie instead of a professional cap.

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]
Qwen Image 2512

AI Judge Analysis

FLUX.1 [schnell]

  • + Strong composition with a clear central focus.
  • + Great use of color contrast between the dark elements and the glowing orange jack-o-lantern.
  • Multiple spelling errors and repeated text fields ("Time: 17.2026", "Tive: 7pm").
  • The scroll banner is not used for the required text, and the background banner has grammar issues.

Qwen Image 2512

  • + Excellent adherence to the border requirement featuring both thorns and spider webs.
  • + Text rendering is significantly more accurate for the event details and the scroll banner.
  • + Includes all requested artistic elements like twisted trees and cinematic lighting.
  • Minor spelling error in the word "Hallowern" in the main title.
  • The 'E' in 'Invitation' is slightly malformed.

Verdict: While FLUX.1 [schnell] has a nice aesthetic, it fails significantly on text accuracy, creating redundant and misspelled lines of event information. Qwen Image 2512 much more effectively executes the prompt's layout and border requirements, and despite one letter typo in the title, it provides a functional and polished invitation.

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]
Qwen Image 2512

AI Judge Analysis

FLUX.1 [schnell]

  • + Excellent minimal and clean aesthetic
  • + High-quality realistic PBR textures on the salmon
  • + Precisely adheres to the 45-degree isometric perspective
  • Failed to include the word 'SUSHI' in the text
  • The sushi piece is a strange hybrid of a roll and nigiri

Qwen Image 2512

  • + Perfectly followed all text instructions including 'JAPAN' and 'SUSHI'
  • + Includes a more comprehensive and appealing sushi set
  • + Great use of soft cartoon textures and dioramas
  • Text is slightly off-center to the left
  • More complex scene than the 'minimal' request

Verdict: Qwen Image 2512 is the winner as it strictly followed all prompt instructions, including the specific text requirements and the flag icon. While FLUX.1 [schnell] has a very clean and professional render quality, it failed to include the word 'SUSHI' and produced a slightly confused sushi model.

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]
Qwen Image 2512

AI Judge Analysis

FLUX.1 [schnell]

  • + Warm, cinematic lighting with a soft dreamy atmosphere.
  • + Beautifully rendered butterflies and flower field.
  • Failed to include the baby bunny as a distinct animal, merging its features into a cat-like creature.
  • The animals look more like digital illustrations than hyper-photorealistic.

Qwen Image 2512

  • + Successfully included all four requested animals: golden retriever, tabby kitten, bunny, and fox kit.
  • + Excellent fur texture and realistic animal anatomy.
  • + Captures the 'god rays' and 'dew sparkles' mention in the prompt effectively.
  • The composition is a bit static and posed rather than 'tumbling and chasing'.
  • Slightly less 'warmth' in the overall color grade compared to image A.

Verdict: Qwen Image 2512 is the clear winner because it correctly depicted all four specific baby animals requested in the prompt, whereas FLUX.1 [schnell] missed the bunny entirely, merging it into a strange cat-hybrid. Qwen also achieved a higher level of photorealism in the fur and facial features of the animals.

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]
Qwen Image 2512

AI Judge Analysis

FLUX.1 [schnell]

  • + Clean vector aesthetic with symmetrical layout
  • + Follows the requested color palette accurately
  • Major spelling errors in the brand name ('Cafeé Framilan')
  • Incorrect date ('7720' instead of '1720')
  • Missing the steam element requested in the prompt

Qwen Image 2512

  • + Perfect text rendering for both the brand name and the date
  • + Includes all requested elements including the steam and banner
  • + Beautiful vintage illustration style with high-quality cross-hatching
  • Slightly less 'minimalist' than requested due to the detailed shading

Verdict: Qwen Image 2512 followed every part of the prompt, including the specific name and date, and correctly incorporated the 'steam' element which FLUX.1 [schnell] missed. FLUX.1 [schnell] failed significantly on the text, misspelling the name and providing a futuristic year, making it unusable as a logo for the requested brand.

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]
Qwen Image 2512

AI Judge Analysis

FLUX.1 [schnell]

  • + Clean vector aesthetic with consistent line weights
  • + Effective use of the requested color palette
  • + Minimalist layout that feels like a modern infographic
  • Nonsense text throughout the image
  • Failed to follow the logical sequence of the mission steps
  • The icons are abstract and do not clearly represent the specific entities requested (like the Saturn V)

Qwen Image 2512

  • + Successfully rendered readable English text for most steps
  • + Accurate iconography including the Saturn V and Lunar Module
  • + Logical layout that follows a sequence from top to bottom
  • Numbered list is confused with repeated numbers (two '2's, two '3's)
  • Minor spelling errors in smaller text like 'Desceeint'
  • Included a shuttle-like fin on the Saturn V which is historically inaccurate

Verdict: Qwen is the clear winner as it produced an actual infographic with readable text and recognizable icons (Saturn V, Lunar Module) according to the prompt's requested steps. While FLUX.1 [schnell] captured the 'modern vector' style well, it failed completely on typography and logical content, resulting in a beautiful but meaningless image.

Next steps

Explore each model