Head to head
Esc

Models · slot A

to navigate to pick

FLUX.1 [dev] Black Forest Labs FLUX1.1 [pro] Black Forest Labs

Settled by community votes across 13 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

FLUX1.1 [pro]

18.4 arena score

#50 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.1 [dev]

0%

win rate

Ties

0%

FLUX1.1 [pro]

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 [dev]
FLUX1.1 [pro]

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent photorealistic texture on the book's leather cover.
  • + High-quality glass refractions and realistic soft lighting from the window.
  • + Very clean and sharp rendering of the wooden table.
  • The glass structure has an extra internal vertical pane that makes it look more like a display stand than a simple cube.

FLUX1.1 [pro]

  • + Perfect adherence to the 'glass cube' geometry.
  • + The blue sphere is more vibrant and centrally positioned.
  • + The plant is clearly visible through the glass as requested.
  • The sphere appears to be floating without a clear physical resting point inside the cube.
  • The book's texture is slightly less realistic compared to Model A.

Verdict: Both models followed the prompt instructions perfectly, including the placement of the sphere, book, and plant. FLUX.1 [dev] produced a more sophisticated texture for the book and table, but FLUX1.1 [pro] better captured the simple geometry of a 'cube' and provided a clearer view of the plant through the glass.

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 [dev]
FLUX1.1 [pro]

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent realism in skin texture and clothing materials.
  • + Clean, logical bicycle architecture that looks physically possible.
  • + Perfectly executed shallow depth of field and bokeh.
  • Fails to include the 'motion blur' from passing cars as requested.
  • The lighting on the pavement is a bit flat compared to the pro version.

FLUX1.1 [pro]

  • + Captures the 'candid' and 'imperfect framing' feel more authentically.
  • + Better environmental reflections and wet pavement textures.
  • + Stronger cinematic color grading and atmosphere.
  • The bicycle frame is physically nonsensical and broken.
  • The subject's hands are mangled and blending into the handlebars.
  • Anatomical issues with the legs and a floating object behind the subject.

Verdict: FLUX.1 [dev] is the clear winner because it maintains high structural integrity in the bicycle and human anatomy, while FLUX1.1 [pro] suffers from severe AI hallucinations, including a mangled bike frame and distorted hands. Although FLUX1.1 [pro] captures the requested 'imperfect' street photography aesthetic better, the technical glitches make it a significantly weaker image.

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]
FLUX1.1 [pro]

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent depiction of clean, braided hair
  • + Highly symmetrical and aesthetically pleasing face
  • + Clear representation of polished, ornate metal texture
  • Fails to realistically depict the 'battle-worn' or 'scars and dirt' aspect of the prompt
  • Model appears more like a clean fashion model than a grueling paladin

FLUX1.1 [pro]

  • + Strong adherence to the 'battle-worn' and 'dirt/scars' descriptive prompts
  • + Dynamic lighting with sparks and excellent skin texture detail
  • + Realistic, gritty interpretation of a paladin
  • The braids are less distinct and partially obscured compared to image A
  • Composition is very tight, slightly cutting off some of the ornate armor details

Verdict: FLUX1.1 [pro] followed the prompt more accurately by incorporating the grit, dirt, and battle-worn appearance requested, whereas FLUX.1 [dev] produced a very clean and pristine image that ignored the 'worn' descriptors. FLUX1.1 [pro] also featured more realistic skin textures and lifelike eyes, making it the superior interpretation of the character's status.

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 [dev]
FLUX1.1 [pro]

AI Judge Analysis

FLUX.1 [dev]

  • + Clean, professional typographic layout that mimics a real menu
  • + High-quality, realistic food photography and lighting
  • + Clear, legible sans-serif font choices
  • Failed to include a photo grid as requested
  • Missing a dedicated pizza category section

FLUX1.1 [pro]

  • + Followed the grid layout instruction for food photos effectively
  • + Includes all requested categories including pizza
  • + Creative use of icons and vibrant accents
  • Text consists largely of illegible gibberish compared to Model A
  • Layout feels a bit cluttered and less 'minimalist' than the other
  • Low resolution or slightly blurred appearance on small text and icons

Verdict: FLUX.1 [dev] produced a much more realistic and professionally designed menu with clean lines and high-quality photography, though it failed to incorporate the requested grid layout. FLUX1.1 [pro] adhered better to the prompt's structural requirements (grid and pizza section) but the actual quality of the text and overall design coherence is significantly lower than its competitor. FLUX.1 [dev] is preferred for its superior aesthetic and professional finish despite the minor prompt omissions.

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]
FLUX1.1 [pro]

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent depiction of a deconstructed/exploded burger layout.
  • + Clean rendering of the currency symbol and price.
  • + Captures the 'magic' theme with subtle sparkles and floating elements.
  • Completely missed the 'MAGIC BURGER' title text.
  • Failed to include the starburst element for the price.
  • Lacks the fiery, glowing effect on the text requested in the prompt.

FLUX1.1 [pro]

  • + Successfully included all requested text phrases with accurate spelling.
  • + Strong sense of motion with debris and dynamic lighting.
  • + Impressive photorealistic textures on the lettuce and meat patties.
  • The burger is not 'exploded' or deconstructed as requested; it is mostly assembled.
  • The price is at the bottom without the starburst graphic.
  • The 'Magic Burger' title is repeated twice, once in a neon style not explicitly requested.

Verdict: FLUX.1 [dev] followed the 'exploded' burger instruction much better but failed significantly on the text requirements, missing the main title entirely. FLUX1.1 [pro] produced a high-quality advertisement with all text included correctly, though it failed to properly separate the burger components into a mid-air deconstruction. FLUX1.1 [pro] is the preferred choice for a usable ad due to its superior text integration and visual punch.

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 [dev]
FLUX1.1 [pro]

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent text accuracy with no spelling errors or repeated items.
  • + Strong adherence to the chalkboard texture and realistic handwriting style.
  • + Perfect layouts for all three requested menu items including pricing.
  • The cursive handwriting at the bottom has some slight legibility issues like 'drish' instead of 'fresh'.
  • The title is in print-block letters rather than the 'elegant cursive' specifically requested.

FLUX1.1 [pro]

  • + The title uses a cursive style that more closely matches the 'elegant cursive' prompt requirement.
  • + Atmospheric lighting and background composition give a cozy café feel.
  • Significant text hallucinations and errors, including a $228 octopus and repeated menu lines.
  • Spelling mistakes such as 'Chipkies' and 'Herbss'.
  • Poor layout with items condensed and price tags overlapping or incorrect.

Verdict: FLUX.1 [dev] is the clear winner because it accurately rendered all specific menu items and prices while maintaining a consistent chalkboard aesthetic. FLUX1.1 [pro] failed significantly on text integrity, producing repetitive lines, astronomical prices, and several misspelt words.

The Reversed Rodeo

Text-to-Image

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

FLUX.1 [dev]
FLUX1.1 [pro]

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent anatomical rendering of the horse's musculature.
  • + Clean, cinematic lighting with high contrast.
  • + Good spatial positioning showing the Earth in the background.
  • Failed the negative constraint: the astronaut is on top of the horse, not vice versa.
  • The horse's back legs lack hooves, appearing pointed and unfinished.

FLUX1.1 [pro]

  • + Highly detailed textures on the spacesuit and horse's mane.
  • + Dynamic and dramatic composition with a beautiful nebular sky.
  • + Atmospheric lighting and rich color palette.
  • Failed the negative constraint: the astronaut is on top of the horse, not vice versa.
  • The horse's chest and belly anatomy appears fused or distorted with the saddle.

Verdict: Both FLUX.1 [dev] and FLUX1.1 [pro] failed to follow the specific negative constraint 'horse on top, not vice versa,' instead generating standard images of astronauts riding horses. FLUX1.1 [pro] is slightly preferred for its superior artistic detail and more complex environment, whereas FLUX.1 [dev] produced a cleaner but more anatomical flawed horse.

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]
FLUX1.1 [pro]

AI Judge Analysis

FLUX.1 [dev]

  • + Successfully places the character in the front seat and the passenger in the back seat as requested.
  • + The capybara's paws are clearly on the steering wheel.
  • + High level of detail in the capybara's fur and the passenger's expression.
  • The perspective is slightly awkward with the TAXI sign appearing inside the car roofline.
  • The passenger's hands and phone interaction look slightly less natural than Model B.

FLUX1.1 [pro]

  • + Excellent bokeh and lighting realism in the background city lights.
  • + Strong textures on the clothing and car upholstery.
  • + Cinematic lighting on the capybara's face.
  • Failed the spatial positioning requirement; both subjects appear to be in the front seat or mid-cabin.
  • The capybara does not have its paws on the steering wheel.
  • The passenger is looking at the capybara rather than looking bored at her phone.

Verdict: FLUX.1 [dev] followed the complex spatial instructions much better than FLUX1.1 [pro], correctly placing the woman in the back seat and the capybara's paws on the wheel. While FLUX1.1 [pro] produced a more aesthetically pleasing image with better lighting and textures, it failed nearly all the specific character positioning and action prompts.

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]
FLUX1.1 [pro]

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent illustration of the thorns and twisted trees with a strong gothic feel.
  • + Bold and clear central jack-o-lantern with effective cinematic lighting.
  • Significant text errors including 'Falloween Ranty' and 'You Tre invited'.
  • Redundant time listing ('7pm, 7pm') and poor character rendering in 'Arches'.

FLUX1.1 [pro]

  • + Successfully captured the 'dark parchment' texture with ragged paper edges.
  • + Better arrangement of the graveyard atmosphere with depth and a realistic moon.
  • Repeated text blocks for time and location clutter the bottom of the poster.
  • Minor spelling errors in the secondary banner like 'You inivted to a n night of frights'.

Verdict: While both models struggled with perfect text accuracy, FLUX1.1 [pro] is the superior choice for its parchment-like design and much higher legibility for the main 'Halloween Party' title. FLUX.1 [dev] produced a more vibrant illustration but failed significantly on the primary typography and name of the event.

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]
FLUX1.1 [pro]

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent adherence to the small raised diorama base requirement.
  • + Superior PBR material quality with realistic light scattering on the fish textures.
  • + Includes the requested flag icon.
  • Includes extraneous text 'SUSH CATON' and a random kanji character.
  • The sushi variety is limited to just one type.

FLUX1.1 [pro]

  • + Correctly renders both 'JAPAN' and 'SUSHI' text in a bold, clean style.
  • + Offers a more diverse and visually appealing variety of sushi types.
  • + Very clean, bright 'cartoon' aesthetic that matches the 3D miniature prompt.
  • Failed to include the requested flag icon.
  • The text 'SUSHI' is significantly smaller and less bold than the 'JAPAN' text.

Verdict: FLUX.1 [dev] produced a more sophisticated rendering of materials with a realistic miniature feel, but its text rendering was cluttered with hallucinated characters. FLUX1.1 [pro] followed the text instructions more accurately and provided a more interesting variety of sushi, though it missed the flag icon.

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]
FLUX1.1 [pro]

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent handling of the lighting request with distinct 'god rays' and backlighting.
  • + Includes all four requested animals (dog, cat, bunny, fox).
  • + Vibrant colors and high-quality rendering of the meadow environment.
  • The style leans into 'Pixar-like' 3D animation rather than the requested 'photorealistic' scene.
  • The animals look like stylized toys with oversized, glassy eyes.

FLUX1.1 [pro]

  • + Features more realistic fur textures and anatomically believable eyes.
  • + Better captured the 'chasing butterflies' action through the gaze and posture of the animals.
  • + Superior bokeh and depth of field in the foreground.
  • Failed to include all four requested animals, missing the fox kit.
  • The butterflies are less defined and look more like floating sparks of light.

Verdict: FLUX.1 [dev] followed the complex prompt more accurately by including all four specific animals, whereas FLUX1.1 [pro] missed the fox. However, FLUX1.1 [pro] significantly outperformed on the 'photorealistic' requirement, producing natural fur and realistic expressions compared to the cartoonish, doll-like aesthetic of FLUX.1 [dev].

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]
FLUX1.1 [pro]

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent color palette adherence with warm brown and cream tones.
  • + Clean vector emblem style that feels truly minimalist.
  • + Correct spelling of 'Est. 1720'.
  • Significant spelling errors in the brand name ('Flariláan') and secondary text ('Reseaurant').
  • Extraneous numbers ('11011', '1941') that were not in the prompt.

FLUX1.1 [pro]

  • + Ornate and high-quality vintage line work and shading.
  • + Includes a decorative border that enhances the vintage aesthetic.
  • + Closer to the requested 'Caffè Florian' spelling, though still slightly off.
  • Text rendering errors ('Caifeé FRATILIAN') despite high visual quality.
  • The layout is a bit more crowded than a 'minimalist' prompt usually dictates.

Verdict: While both models failed to perfectly spell 'Caffè Florian', FLUX1.1 [pro] produced a much more professional and aesthetically pleasing design with sophisticated vintage textures and line work. FLUX.1 [dev] followed the minimalist instruction better but suffered from severe typos and added nonsensical numbers that cluttered the 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 [dev]
FLUX1.1 [pro]

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent adherence to the NASA-inspired color palette.
  • + Superior typography and overall layout composition.
  • + Very clean, professional vector aesthetic with crisp lines.
  • The text content is largely gibberish despite good font choices.
  • The trajectory diagram is visually appealing but logicially confusing regarding the specific mission steps.

FLUX1.1 [pro]

  • + Stronger visual storytelling with clear icon labeling for steps 1-5.
  • + Bold 'Apollo 11' heading is legible and well-integrated into the design.
  • + Better attempt at including the requested iconography like the Saturn V.
  • The color palette is less sophisticated than requested, relying on heavy contrast.
  • The moon illustration is overwhelming and occupies too much of the screen space compared to the data.
  • Graphic elements like icons overlap awkwardly in some places.

Verdict: FLUX.1 [dev] produced a far more professional and aesthetically pleasing infographic that perfectly matches the requested NASA style, despite the nonsensical text. While FLUX1.1 [pro] followed the numbered instructions for different steps more literally, its composition is cluttered and lacks the polished vector feel of the other model.

Next steps

Explore each model