Head to head
Esc

Models · slot A

to navigate to pick

FLUX.1 [dev] 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.

FLUX.1 [dev]

24.6 arena score

#16 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

FLUX.1 [dev]

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.”

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

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent photorealism in the textures of the book and sphere
  • + Strong lighting and reflection work on the glass surfaces
  • + Creative framing with a more artistic, shallow depth of field
  • The glass 'cube' actually looks more like a rectangular prism or a complex assembly rather than a simple cube

FLUX1.1 [pro] Ultra

  • + Perfect adherence to the geometry of a cube
  • + Highly detailed book spine with realistic texturing and gold leaf effects
  • + Accurately represents the transparency and thinness of glass
  • The blue sphere is levitating without any physical support, which looks slightly less grounded than Model A's interpretation

Verdict: Both models followed the prompt perfectly, including the specific spatial relationships of the objects and the soft window lighting. FLUX1.1 [pro] Ultra is the winner as it correctly rendered a cube shape, whereas FLUX.1 [dev] produced a more elongated rectangular object.

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] Ultra

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent handling of shallow depth of field and rain atmosphere
  • + Skin texture and facial details are highly realistic
  • + Perfectly captures the request for a 50mm lens aesthetic with organic blur
  • The motion blur of the passing car is quite subtle compared to the prompt request
  • The man is holding the bicycle rather than clearly repairing it

FLUX1.1 [pro] Ultra

  • + Dynamic motion blur on the passing vehicle aligns well with the prompt
  • + Captures an 'imperfect framing' look by placing the subject off-center
  • + Clear rain reflections on the wet pavement
  • The man's leg is clipping through the rear wheel of the bicycle
  • The depth of field is deeper than requested, losing the 50mm portrait feel
  • The facial features look slightly smoother and less natural than Model A

Verdict: FLUX.1 [dev] produces a much more realistic and aesthetically pleasing portrait with superior skin textures and convincing depth of field. While FLUX1.1 [pro] Ultra captures the requested motion blur of the passing car more effectively, it suffers from a significant anatomical/mechanical clipping error where the man's leg merges with the bicycle wheel.

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] Ultra

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent skin texture with realistic freckles and pores.
  • + Great attention to detail on the metal armor and bokeh background.
  • + Faithful representation of lifelike eyes and braided hair.
  • Missed the request for beads in the hair.
  • The character looks a bit too clean and youthful for a 'battle-worn' paladin.
  • Leather straps and cloth underlayers are mostly obscured.

FLUX1.1 [pro] Ultra

  • The image failed to load or is a solid black square.

Verdict: FLUX.1 [dev] produced a high-quality, detailed portrait that followed most of the stylistic prompts, although it failed to include the specific detail of beads in the hair. FLUX1.1 [pro] Ultra failed to generate a visible image, resulting in a black output.

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] Ultra

AI Judge Analysis

FLUX.1 [dev]

  • + Extremely clean and professional typography
  • + Highly readable layout typical of a real-world modern menu
  • + Excellent use of white space and minimalist design
  • Does not follow the grid photo requirement as well as the competitor
  • Text is mostly gibberish despite looking visually structured
  • Only includes two food photos instead of a grid

FLUX1.1 [pro] Ultra

  • + Adheres better to the 'grid' instruction with multiple food photos
  • + Includes sections for all requested categories (Appetizers, Pizza, Mains)
  • + Dynamic and vibrant presentation with clear section headers
  • Text rendering is poor with several typos (e.g., 'For Pipzzans', 'Appet Love')
  • Composition feels a bit cluttered compared to Model A
  • Perspective distortion from the angled mock-up view makes it harder to read

Verdict: FLUX1.1 [pro] Ultra followed the prompt much more closely by including a grid of food photos and specifying a distinct 'Pizza' section, which FLUX.1 [dev] omitted. However, FLUX.1 [dev] produced a much more sophisticated and professional-looking graphic design with superior typography and spacing. FLUX1.1 [pro] Ultra is the likely winner for better prompt adherence regarding the visual elements and layout structure.

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] Ultra

AI Judge Analysis

FLUX.1 [dev]

  • + Successfully rendered most of the requested text including the price.
  • + Clean, vertical stacking of ingredients creates a clear 'exploded' look.
  • Completely failed to include the primary title 'MAGIC BURGER'.
  • The starburst for the price is missing.
  • The composition feels a bit static compared to the 'dynamic' request.

FLUX1.1 [pro] Ultra

  • + Excellent adherence to all text requirements including the 'MAGIC BURGER' title.
  • + Features a much higher sense of motion and dynamic energy with floating embers and debris.
  • + High-quality, photorealistic texture on the meat, cheese, and vegetables.
  • The price is not inside a starburst as requested.
  • The bottom of the frame has some small, illegible AI-generated legal text artifacts.

Verdict: FLUX1.1 [pro] Ultra is the clear winner as it successfully included all three requested text elements, whereas FLUX.1 [dev] omitted the main title entirely. FLUX1.1 [pro] Ultra also captured the 'dynamic' and 'fiery' atmosphere much more effectively with vibrant lighting and floating particulate matter.

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] Ultra

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent text accuracy with no spelling errors in the menu items.
  • + Very clean and legible chalk handwriting that adheres to the elegant style requested.
  • + Well-balanced composition with consistent spacing between items.
  • The text looks slightly digital/vectorized, lacking some of the raw chalk grain and smudging requested in the prompt.

FLUX1.1 [pro] Ultra

  • + Features a more authentic chalk texture with visible dust and natural stroke variations.
  • + The lighting and wood texture of the frame look highly realistic.
  • Significant text hallucinations and repetition, including 'fresh fresh daily' and doubled lines.
  • Incorrect spelling and abbreviations, such as 'mushroomm ris.' and 'fiiistratnisnios'.
  • The layout is cluttered and messy compared to the request.

Verdict: FLUX.1 [dev] is the clear winner as it successfully rendered all complex text items with perfect spelling and a consistent aesthetic, whereas FLUX1.1 [pro] Ultra suffered from severe text repetition and gibberish. While FLUX1.1 [pro] Ultra had a more realistic 'chalk' texture, its failure to adhere to the legibility and content requirements of the prompt makes it much less useful.

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] Ultra

AI Judge Analysis

FLUX.1 [dev]

  • + Strong cinematic lighting with atmospheric glow
  • + Smooth, high-quality textures on the spacesuit and horse
  • + Clean composition with a focused subject
  • Failed the negative constraint; the astronaut is riding the horse instead of vice versa
  • Lower level of background detail compared to Model B

FLUX1.1 [pro] Ultra

  • + Higher overall complexity with detailed Earth background and satellites
  • + More realistic rendering of the horse's musculature and mane
  • + Better depth and scale in the composition
  • Failed the negative constraint; the astronaut is riding the horse instead of vice versa
  • Slightly messy proportions on the horse's rear leg

Verdict: Both FLUX.1 [dev] and FLUX1.1 [pro] Ultra failed the specific negative constraint to have the 'horse on top' of the astronaut, both resorting to the common trope of an astronaut riding a horse. FLUX1.1 [pro] Ultra is the superior image due to its more detailed background, realistic textures, and complex lighting, whereas FLUX.1 [dev] is a bit simpler and more stylized.

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] Ultra

AI Judge Analysis

FLUX.1 [dev]

  • + Successfully places the passenger in the back seat as requested.
  • + The capybara has both paws on the steering wheel.
  • + The composition feels like a view through the windshield, which is engaging.
  • The passenger looks slightly too close to the front for a backseat, though still spatially behind.
  • The capybara's paws look somewhat small and oddly articulated.

FLUX1.1 [pro] Ultra

  • + High visual clarity and sharp detail on the capybara's fur and clothing.
  • + Excellent rendering of Manhattan street lights in the background.
  • Failed the spatial prompt by putting the passenger in the front passenger seat.
  • The passenger is holding a steering wheel, which does not make sense for a passenger seat.
  • The capybara only has one arm visible and reaching towards the wheel.

Verdict: FLUX.1 [dev] followed the complex spatial instructions much better by placing the passenger in the back seat and ensuring the capybara had two paws on the wheel. While FLUX1.1 [pro] Ultra has slightly higher texture quality, it failed significantly on the prompt adherence by putting the woman in the front and giving her a second steering wheel.

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] Ultra

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent vibrant lighting on the jack-o-lantern and moon.
  • + Clean, thorned border frame that contains the composition well.
  • + Bold and legible event details at the bottom.
  • Significant spelling errors in the title text: 'Falloween Rantcy'.
  • The text 'You Tre' and duplicate '7pm, 7pm' are clear quality issues.
  • Composition feels slightly clustered in the center.

FLUX1.1 [pro] Ultra

  • + Almost perfect text spelling across the entire invitation.
  • + Superior adherence to the 'parchment scroll' and 'webs and thorns' prompt elements.
  • + Stronger gothic aesthetic with more detailed background elements like the castle.
  • Redundant text line 'You are invited to a noickt or a night of frights' below the banner.
  • The glow of the jack-o-lantern is less integrated with the moon compared to Model A.

Verdict: FLUX1.1 [pro] Ultra followed the complex layout and content instructions much better than FLUX.1 [dev], successfully rendering a parchment scroll with nearly perfect spelling. While FLUX.1 [dev] had more striking cinematic lighting, its failure to correctly spell 'Halloween' or 'Invitation' makes it unusable as a party invite. FLUX1.1 [pro] Ultra is the clear winner for its detail and text accuracy.

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] Ultra

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent 3D miniature textures that look like soft clay or stylized plastic.
  • + Contains the small raised diorama base as requested.
  • Included misspelled text 'SUSH CATON' and random characters.
  • The text is very small and lacks the 'large bold' impact requested.

FLUX1.1 [pro] Ultra

  • + Perfect text rendering for 'JAPAN' and 'SUSHI' in a bold, clean style.
  • + High-quality isometric composition with very clean PBR materials.
  • + Accurate flag icon integration.
  • Includes some unnecessary elements like a small ladybug and steam on cold food.
  • Slightly busier scene than the 'minimal garnish' requested.

Verdict: FLUX1.1 [pro] Ultra followed the text instructions perfectly, producing clean, legible, and aesthetically pleasing typography paired with a high-clarity isometric scene. FLUX.1 [dev] captured the miniature material look well but failed significantly on the text requirements, including spelling errors and extraneous symbols.

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] Ultra

AI Judge Analysis

FLUX.1 [dev]

  • + Features all four requested animals plus an extra dog for a total of four subjects.
  • + Strong backlight create a warm, glowing atmosphere.
  • Missed the tabby kitten requirement entirely.
  • The animals look more like animated illustrations or plush toys than the requested 'hyper-photorealistic' scene.
  • The fox and bunny characters are morphologically very similar and lack distinct species traits.

FLUX1.1 [pro] Ultra

  • + Successfully includes the specific animals requested: golden retriever, tabby kitten, bunny, and fox kit.
  • + Significantly higher detail in the fur texture and 'dew sparkles' in the grass.
  • + Better adherence to the 'hyper-photorealistic' style while maintaining the cute aesthetic.
  • One of the butterflies in the top center has a slightly glitched wing shape.
  • The animals are more passive (watching) rather than 'playfully chasing and tumbling' as requested.

Verdict: FLUX1.1 [pro] Ultra is the clear winner as it correctly followed the prompt to include a tabby kitten, which FLUX.1 [dev] omitted. Furthermore, FLUX1.1 [pro] Ultra achieved a much higher level of realism in the fur and environment, whereas FLUX.1 [dev] produced a flatter, more 3D-animation style output.

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] Ultra

AI Judge Analysis

FLUX.1 [dev]

  • + Clean vector aesthetic that matches the minimalist request.
  • + Great balance of negative space and typography.
  • + Includes a clear cloche and steam icon.
  • Spelling errors in both the restaurant name and the word 'Restaurant'.
  • Contains irrelevant numbers above the logo.

FLUX1.1 [pro] Ultra

  • + Excellent color palette and vintage circular emblem composition.
  • + Typography is very clean and readable, despite a slight misspelling.
  • + Subtle texture on the background matches the prompt perfectly.
  • Misspelled name as 'Framilian' instead of 'Florian'.
  • Slightly less 'minimalist' than Model A due to the complex badge design.

Verdict: Both models failed to spell 'Caffè Florian' correctly, but FLUX1.1 [pro] Ultra produced a much more professional and aesthetically pleasing vintage emblem. While FLUX.1 [dev] captured the minimalist vector style well, it was hampered by multiple spelling errors and strange extraneous numbers.

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] Ultra

AI Judge Analysis

FLUX.1 [dev]

  • + Strong aesthetic adherence to the muted NASA-inspired palette.
  • + Elegant composition with a central rocket and circular diagram.
  • + Clean flat-vector style with professional-looking icons.
  • Text is largely gibberish and does not follow the specific step labels.
  • Iconography sequence is confusing and includes irrelevant planets like Saturn.
  • Failed to provide the specific 6-step linear sequence requested.

FLUX1.1 [pro] Ultra

  • + Successfully incorporated almost all specific step labels (Launch, Earth Orbit, Translunar, etc.).
  • + Bold, readable typography for the main headings.
  • + Logical layout where icons represent stages of the mission descending toward the moon.
  • Supporting text contains significant typos and nonsensical phrases.
  • The composition is a bit cluttered with redundant labels.
  • The Saturn V rocket is stylistically inconsistent with some of the more abstract icons.

Verdict: FLUX1.1 [pro] Ultra is the clear winner for prompt adherence, as it accurately captured the requested 6-step sequence and labels, whereas FLUX.1 [dev] produced a generic space graphic with gibberish text. While FLUX.1 [dev] had a more cohesive artistic style, FLUX1.1 [pro] Ultra followed the complex instructional requirements of the infographic far more effectively.

Next steps

Explore each model