Head to head
Esc

Models · slot A

to navigate to pick

FLUX.2 [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.2 [dev]

24.5 arena score

#17 of 62 in Text-to-Image

Skill signature · Text-to-Image

FLUX1.1 [pro] Ultra

17.9 arena score

#51 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.2 [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.2 [dev]
FLUX1.1 [pro] Ultra

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent depiction of physical realism and lighting
  • + Natural-looking dust and reflections on the glass
  • + Perfect adherence to all prompt elements
  • The glass cube has a very thick, almost vase-like base compared to its walls

FLUX1.1 [pro] Ultra

  • + Realistic book texture and spine details
  • + Precise glass edges and transparency
  • + Consistent lighting from the left
  • The blue sphere is levitating inside the cube, which feels less natural
  • The plant's scale feels slightly flattened against the glass

Verdict: Both models followed the complex spatial instructions perfectly. FLUX.2 [dev] is preferred for its more grounded physical realism, with the sphere sitting naturally on the bottom of the cube, whereas FLUX1.1 [pro] Ultra shows the sphere floating in mid-air.

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

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent skin texture and hyper-realistic facial details
  • + More convincing 'imperfect framing' that feels like a candid street photo
  • + Great attention to detail with raindrops on the jacket and wet hans
  • The handlebars and cables of the bicycle become a bit tangled/nonsensical in the center

FLUX1.1 [pro] Ultra

  • + Strong implementation of motion blur from passing cars
  • + Clean composition with a clear red bicycle
  • + Accurate depiction of wet pavement reflections
  • Skin texture is slightly too smooth and looks 'AI-generated'
  • The man's posture and interaction with the bike look staged rather than a repair
  • The bicycle wheels look distorted where they meet the ground

Verdict: FLUX.2 [dev] wins this round by leaning into the 'no stylization' and 'candid' aspects of the prompt, providing grit and hyper-realistic skin textures that FLUX1.1 [pro] Ultra lacks. While FLUX1.1 [pro] Ultra captures the motion blur and environmental reflections well, its subject looks too clean and artificial to pass as a real street photo.

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

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent adherence to details like the small beads in the braids and the ornate engraving on the plate armor.
  • + Strong bokeh effect with sparks and warm torchlight reflecting realistically off the metallic surfaces.
  • + Highly detailed skin texture showing both fresh scars and dirt as requested.
  • The torch itself is partially cut off at the edge of the frame, which slightly disrupts the composition.

FLUX1.1 [pro] Ultra

  • The image failed to render, resulting in a completely black canvas.
  • Zero adherence to the prompt criteria due to technical failure.

Verdict: FLUX.2 [dev] successfully followed all instructions, producing a high-quality portrait with intricate armor details and accurate lighting. FLUX1.1 [pro] Ultra failed to generate a visible image, making FLUX.2 [dev] the winner by default.

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

AI Judge Analysis

FLUX.2 [dev]

  • + Includes specific sections for Appetizers, Pizza, and Mains as requested
  • + Features high-quality food photography with professional lighting
  • + Uses bold vibrant accents that align with the casual dining prompt
  • The text is mostly gibberish or garbled characters
  • The layout feels a bit cramped due to the tight grid

FLUX1.1 [pro] Ultra

  • + The text is much more legible and follows real English spelling in header sections
  • + Excellent use of white space that fits the 'modern minimalist' aesthetic
  • + Realistic mock-up presentation with a perspective shadow
  • The 'grid' of photos is somewhat chaotic and overlaps the text sections
  • Missing a distinct, well-defined 'Pizza' section header compared to Model A

Verdict: FLUX1.1 [pro] Ultra produces a superior minimalist design with much cleaner typography, though its grid layout for images is less organized than requested. FLUX.2 [dev] followed the grid and structural requirements more precisely, but failed significantly on text rendering and legibility.

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

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent text integration with a fiery glowing effect as requested.
  • + Realistic food rendering with believable textures on the patty and bun.
  • + Strong composition with the price in a flaming starburst as specified.
  • The 'exploded' effect is a bit static compared to the sense of motion in Model B.

FLUX1.1 [pro] Ultra

  • + Very dynamic exploded view with many flying ingredients creating a sense of scale.
  • + High-resolution details on the embers and background elements.
  • + Clean typography for the main title.
  • Failed to place the price inside a starburst.
  • Includes messy hallucinated text at the bottom left and right of the frame.
  • The burger stack looks like several burgers merged rather than one 'exploded' unit.

Verdict: FLUX.2 [dev] significantly outperformed the competitor by adhering to every specific prompt requirement, including the starburst element and the fiery text effect. FLUX1.1 [pro] Ultra created a more visually complex explosion, but failed on key prompt details and included unsightly artifact text at the bottom of the image.

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

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent chalk texture and realistic handwritten variations.
  • + Flawless text spelling for all requested menu items.
  • + Consistent artistic style across the entire board.
  • The layout is slightly crowded at the top.

FLUX1.1 [pro] Ultra

  • + Natural wood framing adds to the cafe aesthetic.
  • + Clear differentiation between title and menu items.
  • Significant spelling errors and repetitive text (e.g., 'mushroomm', 'friesstratnisnios').
  • The chalk texture looks more like a digital pen than actual chalk.
  • Failed to correctly render the 'Grilled Octopus' line, cutting off 'Herbs'.

Verdict: FLUX.2 [dev] followed the prompt almost perfectly, delivering highly realistic chalk textures and accurate spelling for the complex menu items. FLUX1.1 [pro] Ultra suffered from significant text hallucinations and repetition, resulting in nonsensical words and a less convincing chalk effect.

The Reversed Rodeo

Text-to-Image

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

FLUX.2 [dev]
FLUX1.1 [pro] Ultra

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent anatomical details on the horse's fur and the astronaut's suit.
  • + High-quality cinematic lighting with a realistic nebula background.
  • + Strong sense of depth and atmospheric perspective.
  • The shadow on the clouds below is a 'ghost horse' shape that doesn't align with the subject's pose.

FLUX1.1 [pro] Ultra

  • + Dynamic, energetic composition with the horse rearing.
  • + Striking color palette with clean blue and white tones.
  • + Intricate background details including satellites and a ringed planet.
  • The astronaut's left leg is missing or incorrectly merged into the horse's back.
  • There is a nonsensical orange T-shaped object floating above the astronaut's backpack.

Verdict: Both models successfully interpreted the prompt, but FLUX.2 [dev] produces a more coherent and physically grounded image with superior anatomical accuracy. While FLUX1.1 [pro] Ultra has a more exciting composition, it suffers from several logical errors and missing limbs.

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

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent adherence to the scene layout with the capybara in front and businesswoman in the back.
  • + The capybara's hands are correctly placed on the steering wheel.
  • + The businesswoman has a naturally bored, candid expression as requested.
  • The capybara's paws look slightly uncanny/human-like in texture.
  • The lighting on the capybara's face is a bit flat compared to the background.

FLUX1.1 [pro] Ultra

  • + High cinematic visual quality and Sharpness.
  • + Good texture on the capybara's fur and the leather jacket.
  • Failed to place the businesswoman in the back seat; she is sitting in the front passenger seat.
  • The capybara appears to be looking out the side window rather than driving forward.
  • The capybara is not wearing a 'taxi driver cap', but rather a generic hat with small text.

Verdict: FLUX.2 [dev] followed the spatial instructions of the prompt much better, correctly placing the passenger in the back seat and the capybara in the driver's seat with its paws on the wheel. FLUX1.1 [pro] Ultra created a more cinematic image but failed several key prompt requirements, including composition and specific character placement.

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

AI Judge Analysis

FLUX.2 [dev]

  • + Follows all text instructions perfectly with no typos or repetitions.
  • + Superior atmosphere with a dark, moody color palette that feels cinematic.
  • + Integrated layout where the Jack-o-lantern and background elements create a cohesive scene.
  • The 'parchment' effect is mostly limited to the outer edges rather than the central background.
  • The gothic title text is slightly less intricate than the style in Model B.

FLUX1.1 [pro] Ultra

  • + Stronger interpretation of the 'dark parchment' and 'small scroll banner' elements.
  • + Excellent thorn border detail that frames the central composition well.
  • + Jack-o-lantern has a high-quality glow and polished appearance.
  • Includes significant text hallucination and repetition below the scroll banner.
  • Fails to include the full title 'Halloween Party Invitation', omitting the word 'Party'.
  • Composition feels a bit more like a digital collage than a unified cinematic scene.

Verdict: FLUX.2 [dev] is the clear winner because it correctly renders all requested text without errors or hallucinations, whereas FLUX1.1 [pro] Ultra repeats phrases with typos and misses parts of the title. FLUX.2 [dev] also produces a more atmospheric and moody image that better captures the 'spooky but polished' request.

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

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent adherence to the 'minimal garnish' and 'square format' constraints
  • + Very clean and bold typography that matches the prompt instructions perfectly
  • + High-clarity textures that look realistic yet stylized as requested
  • The diorama base is a bit plain compared to the potential of the prompt

FLUX1.1 [pro] Ultra

  • + Beautiful soft lighting and steam effects that enhance the 'miniature' feel
  • + More creative and detailed 3D assets such as the chopsticks and small dishes
  • + High-quality rendering of materials and textures
  • Included significant extra elements despite the 'minimal garnish' instruction
  • Typography is stylistically weaker than Image A and slightly overlaps the plant garnish
  • A small unrecognizable red insect-like artifact is present on the base

Verdict: FLUX.2 [dev] is the winner because it followed all layout and text instructions precisely, creating a clean, professional-looking graphic with minimal distractions. While FLUX1.1 [pro] Ultra produced a more visually intricate scene with impressive lighting, it ignored the 'minimal garnish' constraint and included unexpected elements like a plant and an odd red artifact on the base.

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

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent photorealism with convincing fur texture and lighting
  • + Matches all requested animal types including a distinct fox kit and tabby kitten
  • + Beautifully rendered backlighting and dew sparkles
  • Includes two bunnies despite the prompt implying a group of different individuals
  • The animals are sitting rather than 'tumbling and chasing'

FLUX1.1 [pro] Ultra

  • + Enhanced 'big expressive eyes' that Lean into the wholesome/cute aesthetic
  • + Dynamic movement with animals standing on hind legs to interact with butterflies
  • + Soft, dreamlike coloring with excellent depth of field
  • Faces appear more 'Disney-fied' or stylized rather than 'hyper-photorealistic'
  • The animals share a very similar orange color palette, making them less distinct as separate species

Verdict: FLUX.2 [dev] delivers a much more realistic and anatomically accurate representation of the animals with superior fur texture, though it is a bit static. FLUX1.1 [pro] Ultra captures the 'joyful' and 'expressive' parts of the prompt more effectively through character posing, but the visuals lean towards 3D animation rather than photography. FLUX.2 [dev] is the winner for better adhering to the 'photorealistic' requirement and distinct species identification.

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

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent typography with perfect spelling of 'Caffè Florian'.
  • + Balanced minimalist composition that follows the vector emblem style accurately.
  • + Clean execution of the cloche and steam icons.
  • The banner layout is a bit busy with overlapping ribbon layers.

FLUX1.1 [pro] Ultra

  • + Beautiful warm color palette and sophisticated shading.
  • + Effective use of the circular badge format which adds to the vintage feel.
  • + Elegant rendering of the steam and textured background.
  • Failed the primary text prompt by spelling it 'Caffè Framilian'.
  • The design is significantly more complex than the requested 'minimalist' style.

Verdict: FLUX.2 [dev] is the clear winner because it correctly follows the text instructions, whereas FLUX1.1 [pro] Ultra hallucinated the name as 'Framilian'. FLUX.2 [dev] also adhered better to the 'minimalist' portion of the prompt, providing a cleaner vector-style logo suitable for a restaurant 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.2 [dev]
FLUX1.1 [pro] Ultra

AI Judge Analysis

FLUX.2 [dev]

  • + Clean, crisp iconography that aligns well with the flat-vector request.
  • + Higher text legibility for the main labels despite some typos.
  • + Logical flow from top-left to bottom-right that follows the specific 6-step prompt sequence.
  • Includes several redundant or garbled labels (e.g., 'SATURN ICON', 'UALSIST ORDIT').
  • Layout is a basic grid rather than a more creative infographic flow.

FLUX1.1 [pro] Ultra

  • + Superior infographic composition with a central moon horizon and a professional layout.
  • + More sophisticated visual style that better utilizes the 'muted red' and 'light gray' palette requested.
  • + Includes granular sub-text that mimics the look of a real poster.
  • Information flow is confusing, with step 6 appearing at the top right and other steps scattered semi-randomly.
  • Iconography is inconsistent, such as using a generic rocket instead of a Saturn V for the launch.
  • Significant gibberish text in the supporting blocks.

Verdict: FLUX.2 [dev] followed the specific 6-step prompt instructions much more accurately, providing clear icons for each requested stage in a logical order. However, FLUX1.1 [pro] Ultra produced a far more aesthetically pleasing and professional 'poster' composition, despite the fact that its actual information hierarchy was chaotic and the iconography was less specific to the Apollo mission.

Next steps

Explore each model