Head to head
Esc

Models · slot A

to navigate to pick

FLUX1.1 [pro] Black Forest Labs FLUX1.1 [pro] Ultra Black Forest Labs

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

FLUX1.1 [pro]

18.4 arena score

#50 of 62 in Text-to-Image

Skill signature · Text-to-Image

FLUX1.1 [pro] Ultra

18.5 arena score

#49 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX1.1 [pro]

0%

win rate

Ties

0%

FLUX1.1 [pro] Ultra

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.”

FLUX1.1 [pro]
FLUX1.1 [pro] Ultra

AI Judge Analysis

FLUX1.1 [pro]

  • + Excellent refraction and internal reflections within the glass structure
  • + Vibrant colors with a high-contrast aesthetic
  • + Strong adherence to all spatial and object requirements
  • The glass container is more of a rectangular prism than a cube
  • The sphere appears to be floating without a visible support, which feels slightly less grounded

FLUX1.1 [pro] Ultra

  • + Perfectly adheres to the 'cube' geometry
  • + Highly realistic textures on the red book cover and spine text
  • + Subtle, realistic dust and reflections on the glass surfaces
  • The light source feels more diffused and less directed from the left compared to model A

Verdict: Both models followed the prompt perfectly, but FLUX1.1 [pro] Ultra is the winner due to more accurate geometry (a true cube) and incredible attention to detail in textures like the book's spine and the micro-particles on the glass. FLUX1.1 [pro] produced a beautiful image, but its glass container was elongated into a rectangular prism rather than the requested 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.”

FLUX1.1 [pro]
FLUX1.1 [pro] Ultra

AI Judge Analysis

FLUX1.1 [pro]

  • + Excellent depiction of heavy rain and evocative street reflections
  • + Face and skin texture feel very natural and realistic
  • + Captures an 'imperfect' street photography aesthetic well
  • Serious anatomical and structural issues with the bicycle frame which appears broken or warped
  • The man is standing on a small, nonsensical wheel-like object

FLUX1.1 [pro] Ultra

  • + Successfully incorporates the requested motion blur from passing cars
  • + The bicycle is structurally more coherent and realistic
  • + Better clarity and higher resolution overall
  • The lighting on the man feels a bit too clean/studio-like for a candid street shot
  • The man's pose looks more like he is leaning on the bike than repairing it

Verdict: While FLUX1.1 [pro] captures a more authentic 'candid' mood and superior skin textures, it fails significantly on the physical logic of the bicycle. FLUX1.1 [pro] Ultra follows the motion blur prompt much better and provides a clean, coherent image, though it loses some of that raw street photography grit.

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.”

FLUX1.1 [pro]
FLUX1.1 [pro] Ultra

AI Judge Analysis

FLUX1.1 [pro]

  • + Exceptional skin texture with realistic dirt and faint scarring.
  • + Intense, lifelike eye rendering with clear reflections.
  • + Accurate adherence to 'bokeh sparks' and 'ornate engraved plate armor' descriptions.
  • The hair braids and beads are a bit messy and indistinct.
  • The level of 'battle-worn' blood spatter might be slightly more intense than 'faint dirt' implied.

FLUX1.1 [pro] Ultra

  • The image failed to load or is a completely black canvas.

Verdict: FLUX1.1 [pro] produced a high-quality, professional-grade portrait that captured almost every specific detail of the prompt, including complex textures and lighting. FLUX1.1 [pro] Ultra failed to generate or display an image, resulting in a black output. Therefore, FLUX1.1 [pro] is the default winner for providing a highly relevant and visually stunning result.

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.”

FLUX1.1 [pro]
FLUX1.1 [pro] Ultra

AI Judge Analysis

FLUX1.1 [pro]

  • + Excellent typography and header layout.
  • + Clear, logical sectioning and pricing structure.
  • + Clean professional presentation with the inclusion of realistic cutlery.
  • The food photos in the grid are somewhat small and slightly repetitive.
  • The text in the body becomes unreadable gibberish.

FLUX1.1 [pro] Ultra

  • + Beautiful, high-vibrancy food photography in a dynamic grid.
  • + Excellent use of white space for a modern minimalist feel.
  • + Good use of bold sans-serif fonts according to the prompt.
  • The text has several typos and nonsensical headers like 'For Pizzzans'.
  • The layout of the menu items is sparse and less functional as a real menu.

Verdict: FLUX1.1 [pro] provides a more realistic and complete menu layout with logical sections, whereas FLUX1.1 [pro] Ultra excels in the aesthetic quality and vibrancy of the food photos. FLUX1.1 [pro] is a better representation of a professional design, despite the superior visual pop of the photography in the Ultra version.

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.”

FLUX1.1 [pro]
FLUX1.1 [pro] Ultra

AI Judge Analysis

FLUX1.1 [pro]

  • + Excellent photorealistic texture on the meat and buns
  • + Dynamic sense of motion with flying debris
  • + Accurate neon-style glowing text effect
  • Failed the 'exploded burger' requirement, keeping the main stack mostly intact
  • Duplicate 'MAGIC BURGER' text creates visual clutter
  • Missing the starburst for the price

FLUX1.1 [pro] Ultra

  • + Successfully rendered the 'exploded' view with separated layers
  • + Superior adherence to the fiery, glowing text style requested
  • + Better composition with the embers and fire at the base
  • The 'starburst' for the price is very subtle/missing
  • Text at the bottom corners is incoherent gibberish
  • The 'exploded' effect is slightly messy with overlapping patty layers

Verdict: FLUX1.1 [pro] Ultra followed the complex layout instructions much better than FLUX1.1 [pro], capturing the 'exploded' burger concept and the fiery text styles accurately. While FLUX1.1 [pro] has slightly more realistic food textures, its failure to separate the burger components and the repetitive text makes it a less effective 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.”

FLUX1.1 [pro]
FLUX1.1 [pro] Ultra

AI Judge Analysis

FLUX1.1 [pro]

  • + The text has a convincing chalk texture and consistent cursive style for the title.
  • + The overall layout is clean and resembles a professional cafe chalkboard.
  • + The color palette and lighting in the background are aesthetically pleasing.
  • It hallucinated additional lines of text and wildly incorrect prices like $228 and $98.
  • It failed to include the full name of the specific menu items requested in the prompt.

FLUX1.1 [pro] Ultra

  • + The handwriting style is very realistic with natural variations in letter size and slant.
  • + The chalk smudges on the sides of the board add to the realism of the medium.
  • + The prompt adherence for the specific menu items and date is better than the competitor.
  • It suffered from severe text repetition and 'stroke' artifacts, leading to gibberish like 'mushroomm ris'.
  • The title is in print style rather than the 'elegant cursive' requested in the prompt.

Verdict: While FLUX1.1 [pro] produced a cleaner and more visually appealing image, it failed significantly on pricing accuracy and content relevance. FLUX1.1 [pro] Ultra followed the prompt's content more closely but suffered from technical text-rendering issues, including repetitive words and missing the cursive requirement for the title. FLUX1.1 [pro] is slightly preferred for a believable output, despite the price hallucinations, as the text in the Ultra version feels cluttered and poorly edited.

The Reversed Rodeo

Text-to-Image

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

FLUX1.1 [pro]
FLUX1.1 [pro] Ultra

AI Judge Analysis

FLUX1.1 [pro]

  • + Excellent cinematic lighting and atmosphere
  • + High level of detail in the horse's fur and the clouds
  • + Strong artistic rendering with a surreal, painterly feel
  • Fails the spatial reasoning requirement; the astronaut is on top of the horse
  • The anatomy of the horse merging with clouds is slightly messy
  • Lacks a clear 'in space' feel compared to physical orbital views

FLUX1.1 [pro] Ultra

  • + Crystal clear image quality and high resolution
  • + Great sense of scale with the Earth in the background
  • + Dynamic posing of the horse
  • Fails the primary prompt instruction; the astronaut is riding the horse, not vice versa
  • Includes a strange orange anatomical artifact on top of the astronaut's backpack
  • Less surreal and more like a standard stock composite

Verdict: Both FLUX1.1 [pro] and FLUX1.1 [pro] Ultra failed the negative constraint/spatial instruction to place the horse on top of the astronaut. FLUX1.1 [pro] produces a more 'cinematic' and 'surreal' aesthetic as requested, while Ultra is sharper and more literal but contains odd artifacts like the orange object on the backpack. Model A is slightly preferred for adhering better to the stylistic keywords of the prompt.

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.”

FLUX1.1 [pro]
FLUX1.1 [pro] Ultra

AI Judge Analysis

FLUX1.1 [pro]

  • + Excellent photographic lighting and interior atmosphere
  • + Accurately places the passenger in the back seat as requested
  • + Texture of the capybara fur and the jacket is highly realistic
  • The capybara's paws are not clearly on the steering wheel as requested
  • The passenger's posture is a bit cramped due to the perspective

FLUX1.1 [pro] Ultra

  • + Sharp focus on the capybara and clear street background
  • + High resolution and clean text on the cap
  • + Composition is dynamic and follows a clear rule of thirds
  • Failed the spatial prompt by putting the passenger in the front seat instead of the back
  • The passenger's hands are mangled and fused with the phone and steering wheel
  • The capybara's paws are not visible on the steering wheel

Verdict: FLUX1.1 [pro] followed the complex spatial instructions much better by placing the passenger in the back seat, whereas FLUX1.1 [pro] Ultra placed her in the front, resulting in anatomical errors where her hands merge with the steering wheel. FLUX1.1 [pro] also managed a more atmospheric, photorealistic interior that fits the 'night taxi' theme more convincingly.

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.”

FLUX1.1 [pro]
FLUX1.1 [pro] Ultra

AI Judge Analysis

FLUX1.1 [pro]

  • + Atmospheric cinematic lighting with a strong glow effect
  • + Beautifully rendered twisted trees and moonlit sky
  • Poor typography with repetitive lines and spelling errors
  • The text layout is messy and overlaps awkwardly at the bottom

FLUX1.1 [pro] Ultra

  • + Excellent layout following the parchment scroll concept perfectly
  • + High-quality gothic typography that is legible and elegant
  • + Strong adherence to all prompt elements including the specific border details
  • Includes one line of redundant, slightly misspelled text below the scroll
  • The jack-o-lantern is placed higher than 'central' but fits the scroll design well

Verdict: While FLUX1.1 [pro] has slightly more atmospheric lighting, it fails significantly on text legibility and composition, repeating the date, time, and location multiple times. FLUX1.1 [pro] Ultra provides a much more polished and professional invitation layout with a clear scroll motif and superior gothic font rendering, making it the clear winner for a graphic design task.

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.”

FLUX1.1 [pro]
FLUX1.1 [pro] Ultra

AI Judge Analysis

FLUX1.1 [pro]

  • + Excellent typography rendering with clean, bold characters.
  • + Perfectly follows the 45-degree isometric perspective request.
  • + Highly consistent miniature 3D cartoon style with soft, pleasing textures.
  • Missed the small flag icon requirement.
  • The garnish includes odd small tomatoes/onions that aren't typical for sushi.

FLUX1.1 [pro] Ultra

  • + Successfully included the Japanese flag icon as requested.
  • + Very high attention to detail in material textures, especially on the salmon nigiri.
  • + Achieves a sophisticated diorama look with more complex lighting.
  • Perspective is slightly flatter than the requested 45-degree isometric angle.
  • Includes unnecessary elements like a bug and a large plant that detract from the 'minimal garnish' request.

Verdict: FLUX1.1 [pro] adheres more strictly to the requested isometric perspective and typography layout, creating a very clean and simple diorama. However, FLUX1.1 [pro] Ultra is the only model that followed the instruction for a flag icon and displays higher fidelity in its 3D material rendering, though it added unwanted elements like a ladybug.

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.”

FLUX1.1 [pro]
FLUX1.1 [pro] Ultra

AI Judge Analysis

FLUX1.1 [pro]

  • + Excellent use of backlighting and rim light on the fur
  • + High level of detail in the eyes and whiskers
  • + Warm, inviting color palette that matches the 'golden sunrise' request
  • Failed to include the red fox kit in the group
  • The animals are sitting still rather than 'tumbling together' as requested

FLUX1.1 [pro] Ultra

  • + Successfully included all four requested animals (dog, cat, bunny, fox)
  • + Deeper composition with better use of foreground and background flowers
  • + Clearer representation of 'god rays' in the upper right corner
  • The fox kit's anatomy looks slightly more stylized/illustrative than 'hyper-photorealistic'
  • The animals are sitting relatively static instead of 'playfully chasing' or 'tumbling'

Verdict: While both models failed to capture the dynamic action of 'tumbling together,' FLUX1.1 [pro] Ultra is the superior choice because it followed the complex prompt requirements by including all four specific animals, whereas FLUX1.1 [pro] missed the fox. FLUX1.1 [pro] Ultra also features a more sophisticated depth of field and clearer lighting effects, even if the animals lean slightly more toward a 'cute' aesthetic than pure photorealism.

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.”

FLUX1.1 [pro]
FLUX1.1 [pro] Ultra

AI Judge Analysis

FLUX1.1 [pro]

  • + Excellent typography style that matches the vintage aesthetic well.
  • + Good use of ornamental flourishes to create a balanced emblem.
  • + Accurate cream and warm brown color palette.
  • Misspelled name as 'FRANILIAN' instead of 'Florian'.
  • The cloche dome looks more like a building cupola than a food cloche.

FLUX1.1 [pro] Ultra

  • + Strong vector emblem style with a clean circular composition.
  • + Includes the 'Est. 1720' text clearly in the bottom banner area.
  • + The cloche dome is clearly recognizable as food service equipment.
  • Misspelled name as 'Framilian' instead of 'Florian'.
  • Typography is a bit bulky compared to the requested 'classic' style.

Verdict: Both models failed to correctly spell the specific name 'Caffè Florian', with FLUX1.1 [pro] outputting 'Franilian' and FLUX1.1 [pro] Ultra outputting 'Framilian'. FLUX1.1 [pro] Ultra is the preferred choice because its central icon actually looks like a restaurant cloche, whereas FLUX1.1 [pro] created a dome that looks more like a cathedral or building roof.

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.”

FLUX1.1 [pro]
FLUX1.1 [pro] Ultra

AI Judge Analysis

FLUX1.1 [pro]

  • + Successfully uses the requested NASA color palette.
  • + Adheres to the flat-vector style with a clean aesthetic.
  • + Logical, even if abstract, layout with central focal point.
  • Failed to provide all 6 specific steps in sequence.
  • Text is mostly gibberish or contains significant typos.
  • Step numbering is repetitive and confusing.

FLUX1.1 [pro] Ultra

  • + Attempts to include all 6 specific steps from the prompt.
  • + Superior typography and layout for an infographic style.
  • + Excellent use of icons and text blocks to simulate a real poster.
  • Step numbering and headers are slightly scrambled or redundant.
  • Text contains many misspellings and 'lorem ipsum' style filler.
  • The layout becomes a bit cluttered at the bottom.

Verdict: FLUX1.1 [pro] Ultra (Image B) is the clear winner as it more accurately follows the instructional steps of the prompt, including a sequential flow of 6 specific mission stages. While FLUX1.1 [pro] (Image A) has a very high aesthetic quality, it fails the infographic mission by neglecting the specific content requested in the prompt.

Next steps

Explore each model