Head to head
Esc

Models · slot A

to navigate to pick

FLUX.1 Krea [dev] 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 Krea [dev]

18.8 arena score

#47 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 Krea [dev]

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 Krea [dev]
Qwen Image 2512

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent photographic realism with natural lens blur and lighting.
  • + Accurate material representation with high-quality glass reflections and a textured book cover.
  • + Precise adherence to the 'soft window light from the left' instruction.
  • The thick glass base of the cube looks more like a tray than a simple hollow cube.

Qwen Image 2512

  • + Clear representation of all requested objects with vibrant colors.
  • + Good spatial arrangement of the plant behind the cube.
  • + Accurate rendering of the wooden table texture.
  • The glass has an unnatural teal tint and lacks the realistic refractive indices seen in Image A.
  • The perspective on the back corner of the cube is slightly warped.

Verdict: FLUX.1 Krea [dev] produced a superior image with convincing photographic quality and sophisticated lighting that perfectly matches the 'window light' prompt. While Qwen Image 2512 followed all instructions correctly, its execution lacks the realistic textures and lighting depth found in FLUX.1 Krea [dev], resulting in a more 'digital' and less physical appearance.

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 Krea [dev]
Qwen Image 2512

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent depiction of raining conditions with visible rain droplets.
  • + Captures motion blur from passing cars effectively as requested.
  • + Realistic bike frame geometry and textures.
  • The man is standing and holding the bike rather than actively repairing it.
  • The framing feels a bit too centered for an 'imperfect framing' request.

Qwen Image 2512

  • + Successfully captures a more candid, imperfect street photography composition.
  • + Highly detailed facial texture and natural skin tones.
  • + Excellent reflections on the wet pavement.
  • The man is looking directly at the camera, which feels less 'candid' and more like a portrait.
  • Lacks the requested motion blur from the background traffic.
  • The bike's proportions and mechanical details are slightly warped.

Verdict: FLUX.1 Krea (dev) followed the technical camera prompts better, specifically inclusion of motion blur and the sensation of rain, although the subject is static. Qwen Image 2512 provides a more emotive and realistic human subject with excellent skin texture, but fails to include the motion blur and makes the subject look at the camera, breaking the 'candid' street photography style.

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 Krea [dev]
Qwen Image 2512
0% wins 0% ties 100% wins

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Exquisite engraving detail on the plate armor
  • + Clean and dramatic lighting that focuses on the character
  • + Realistic hair texture and braid structure
  • The blood/dirt on the face looks more like digital splatters than integrated scars
  • Bokeh sparks feel a bit generic and flat

Qwen Image 2512

  • + Excellent integration of scars and dirt into the skin texture
  • + More complex and colorful bead details in the hair
  • + Stronger sense of environmental depth with the visible torch light
  • Lower clarity on the engraved armor patterns compared to the other model
  • The bokeh sparks are a bit messy and touch the character's hair unnaturally

Verdict: Both models followed the prompt exceptionally well, but Qwen Image 2512 captures the 'battle-worn' aspect more effectively through the natural-looking scars and skin texture. While FLUX.1 Krea (dev) has more impressive technical detail on the metal engravings, Qwen's warmer lighting and more intricate character details make for a more compelling portrait.

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 Krea [dev]
Qwen Image 2512

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent typography and realistic menu structure.
  • + High-quality, appetizing food photography that looks professional.
  • + Clean adherence to the 'Mains' and 'Appetizers' section request.
  • Repeats the 'Appetizers' section twice.
  • Text is largely gibberish despite the realistic layout.

Qwen Image 2512

  • + Includes colorful icons and accents that match the 'vibrant accents' prompt.
  • + Effective use of the grid layout for multiple food photos.
  • + Better attempt at creating distinct categories like 'Pies/Mains'.
  • The main header text is nonsensical.
  • The food photos have a slightly more artificial, 'AI-look' compared to Image A.
  • Resolution on smaller text is quite muddy and difficult to read.

Verdict: FLUX.1 Krea [dev] produces a much more realistic and professional-looking menu with superior photography quality and cleaner typography layout. While Qwen Image 2512 does a better job incorporating colorful accents and icons, its overall visual fidelity is lower, and the text rendering is less clean than FLUX.1 Krea.

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 Krea [dev]
Qwen Image 2512

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Clean, professional typographic layout
  • + Realistic food textures and high clarity on the main burger
  • Failed to render the price inside a starburst
  • Text is plain white instead of having the requested 'fiery, glowing effect'
  • The 'LIMITED TIME ONLY' text is repeated unnecessarily

Qwen Image 2512

  • + Perfect adherence to all text instructions, including the fiery effect and starburst price
  • + More dynamic 'exploded' composition with better sense of motion
  • + Excellent integration of embers and atmospheric lighting
  • None notable; follows all prompt constraints effectively

Verdict: Qwen Image 2512 followed every instruction in the prompt, including the specific fiery text effects and the starburst for the price, which FLUX.1 Krea [dev] missed. Qwen also captured a more dynamic sense of motion with the ingredients, creating a more convincing 'exploded' burger advertisement.

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 Krea [dev]
Qwen Image 2512

AI Judge Analysis

FLUX.1 Krea [dev]

  • + The text layout is clean and fits the board well.
  • + Good chalk dust texture and smudging on the background.
  • Numerous spelling errors including 'Gruffle' and 'Chrcuations'.
  • The text style looks more like a digital marker than realistic chalk on a board.

Qwen Image 2512

  • + Excellent adherence to the request for realistic, elegant cursive chalk handwriting.
  • + High text accuracy with almost zero spelling errors.
  • + Visual texture of the chalk and the chalkboard environment is very realistic.
  • One minor typo in 'Risitto' (instead of Risotto).

Verdict: Qwen Image 2512 is the clear winner as it captures the 'elegant cursive' and 'chalk texture' requested in the prompt with much higher fidelity. FLUX.1 Krea [dev] struggles significantly with text accuracy, introducing several nonsensical words and a flatter, more digital font style.

The Reversed Rodeo

Text-to-Image

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

FLUX.1 Krea [dev]
Qwen Image 2512

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Successfully followed the difficult positional prompt showing the horse on top of the astronaut
  • + Creative mechanical integration of the astronaut into the horse's saddle area
  • + Cinematic lighting with a clear view of Earth in the background
  • The astronaut's posture is somewhat awkward and mashed into the horse's underbelly
  • Minor blurriness in the horse's mane and tail

Qwen Image 2512

  • + High resolution and realistic textures on the horse's coat and astronaut's suit
  • + Good composition with a clear, heroic pose
  • Failed the primary prompt instruction to have the horse on top
  • Anatomical issues with the horse's front legs appearing detached or incorrectly jointed

Verdict: This was a trick prompt designed to test spatial reasoning. FLUX.1 Krea [dev] followed the difficult instruction to place the horse on top, creating a surreal image where the astronaut is the mount, whereas Qwen Image 2512 failed this instruction and produced a standard astronaut-riding-horse image.

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 Krea [dev]
Qwen Image 2512

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent fur texture on the capybara
  • + Includes two passengers for a more crowded, realistic taxi feel
  • + Good lighting and atmospheric bokeh in the background
  • The passenger looking at the phone has anatomical issues with her face/eyes
  • Capybara paws look a bit more like bear paws than capybara paws
  • The capybara is positioned very high in the seat

Qwen Image 2512

  • + Perfectly captures the 'bored' expression requested for the passenger
  • + Composition from the front dashboard provides a clear view of the scene
  • + Accurate capybara facial anatomy and driver's hat
  • The capybara's hands look slightly more human/primate than rodent
  • Less variety in the background compared to Model A

Verdict: While both models followed the prompt well, Qwen Image 2512 is the winner due to the superior execution of the passenger's expression and a better overall composition that clearly shows both the driver and the backseat activities. FLUX.1 Krea [dev] suffered from significant artifacts on the secondary characters' faces.

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 Krea [dev]
Qwen Image 2512

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Strong vintage aesthetic with a dark, moody parchment color palette.
  • + Excellent composition with the jack-o-lantern centered between silhouetted trees.
  • + Included the spider webs and thorns border as requested.
  • Major spelling errors in the main title ('Pasty Halloween') and small banner.
  • The text structure is cluttered and contains repetitive words like 'are are'.

Qwen Image 2512

  • + Almost perfect text rendering for the event details and banner.
  • + Cinematic lighting with a cool atmospheric blue sky that contrasts well with the orange glow.
  • + Highly detailed twisted trees and thorn border that fits the gothic theme.
  • One minor typo in the main header ('Hallowern').
  • The scroll banner is slightly less integrated into the bottom layout compared to the top.

Verdict: While FLUX.1 Krea [dev] captures the vintage parchment aesthetic very well, it struggles significantly with text accuracy and legibility. Qwen Image 2512 provides a much more professional and polished result with superior lighting and nearly perfect text adherence, making it the more functional 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 Krea [dev]
Qwen Image 2512

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent adherence to the 'minimal' requirement with a clean, singular focus
  • + High-quality PBR materials giving the salmon a realistic glossy sheen
  • + Very accurate 45° isometric perspective and lighting
  • The text is a bit too soft and puffy compared to the 'bold' request
  • The flag icon is represented as a physical objects rather than a graphic element next to text

Qwen Image 2512

  • + Captures a diverse platter of sushi with good cartoon-style modeling
  • + Excellent graphic design for the text layout including the flag icon placeholder
  • + Rich, vibrant colors and clay-like textures
  • Ignored the 'minimal' garnish instruction by adding grass and flowers
  • The composition feels a bit crowded compared to the 'ultra-clean' requirement

Verdict: FLUX.1 Krea (dev) followed the aesthetic constraints much better, delivering a truly minimal, high-clarity isometric scene that looks like a professional 3D render. Qwen Image 2512 created a more complex and visually interesting scene, but it failed to respect the 'minimal' and 'solid background' prompts as strictly as FLUX.

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 Krea [dev]
Qwen Image 2512

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent sense of motion and playfulness
  • + Superior lighting with soft, natural-looking god rays
  • + Coherent meadow environment with beautiful depth of field
  • Failed to include the baby bunny
  • Includes a second kitten instead of following the species list exactly

Qwen Image 2512

  • + Successfully included all four requested species
  • + High detail in the fur texture and 'expressive eyes'
  • + Strong adherence to the 'dew sparkles' requirement in the grass
  • Static, posed composition lacks the requested 'chasing' and 'tumbling' action
  • The scale between animals is slightly inconsistent, making the rabbit look tiny compared to the kitten

Verdict: FLUX.1 Krea [dev] captures the 'joyful' and 'tumbling' energy of the prompt much better with a dynamic composition, though it fails on the specific prompt requirement of a baby bunny. Qwen Image 2512 followed the subject list perfectly by including all four animals but produced a more generic portrait-style shot rather than an action scene.

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 Krea [dev]
Qwen Image 2512

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Strong vintage woodcut aesthetic
  • + Excellent use of negative space for the cloche handle
  • + Subtle weathered texture on the background
  • Text spelling is incorrect (FLANOR'IN)
  • Steam resembles a wick or single flame more than food steam

Qwen Image 2512

  • + Perfect text rendering of 'Caffè Florian'
  • + Dynamic and detailed steam illustration
  • + Accurate placement of 'Est. 1720' on the banner
  • Slightly less 'minimalist' than requested due to high shading detail
  • Banner ends are a bit cramped at the bottom

Verdict: Qwen Image 2512 is the clear winner because it correctly spelled the restaurant name and followed the banner instructions perfectly. While FLUX.1 Krea [dev] captured a more authentic minimalist vector style, the significant spelling error ('FLANOR'IN') makes it unusable as a logo.

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 Krea [dev]
Qwen Image 2512

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Strong 'Apollo 11' title typography.
  • + High-contrast, clean vector color palette.
  • Failed to follow the numbered step instructions, replacing them with random icons like Saturn and four human silhouettes.
  • Text within the infographic is largely gibberish.
  • The flow of the information is chaotic and non-linear.

Qwen Image 2512

  • + Successfully followed the specific sequence of steps including Launch, Earth Orbit, and Landing.
  • + Captured the icons requested, such as the Saturn V and Lunar Module.
  • + Includes clever details like the names of the three astronauts at the bottom.
  • Some text labels are redundant or misspelled ('TranslauraJ', 'Desceeint').
  • The numbers assigned to labels are inconsistent (two step 2s, two step 3s).

Verdict: Qwen Image 2512 is the clear winner as it attempted each requested step of the infographic and successfully rendered complex subjects like the Saturn V and the Lunar Module. FLUX.1 Krea [dev] failed the prompt's instructions significantly, providing a nonsensical collection of icons that do not relate to the specific mission phases requested.

Next steps

Explore each model