Head to head
Esc

Models · slot A

to navigate to pick

FLUX.1 Krea [dev] Black Forest Labs FLUX.2 [pro] Black Forest Labs

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

FLUX.1 Krea [dev]

18.8 arena score

#48 of 62 in Text-to-Image

Skill signature · Text-to-Image

FLUX.2 [pro]

26.3 arena score

#8 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.1 Krea [dev]

0.0%

win rate

Ties

0.0%

FLUX.2 [pro]

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]
FLUX.2 [pro]

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent depiction of thick glass with realistic internal reflections and distortions
  • + Accurate photographic lighting and shallow depth of field
  • The sphere appears to have a reflection but is not physically centered well within the cube
  • The cube edges are slightly rounded, looking more like a container than a geometric cube

FLUX.2 [pro]

  • + Perfect geometric cube structure with sharp, clean edges
  • + Excellent spatial arrangement with a matte blue sphere that contrasts well with the glass
  • + True-to-prompt lighting from the left window
  • The glass lacks some of the refractive realism and weight seen in the other image
  • The plant's visibility through the cube is somewhat muted

Verdict: Both models followed the prompt perfectly. FLUX.1 Krea [dev] produced a more tactile, realistic photograph with impressive caustic reflections, but FLUX.2 [pro] achieved a cleaner, more precise geometric composition that felt more like a deliberate still life. FLUX.2 [pro] is slightly preferred for its superior clarity and better representation of the 'cube' and 'sphere' as distinct shapes.

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]
FLUX.2 [pro]

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent depiction of motion blur on the passing vehicles
  • + Captures the 'imperfect framing' requested through a slightly off-center, candid perspective
  • + Realistic reflections on the wet asphalt
  • The man is holding the bicycle rather than repairing it
  • The bicycle anatomy is slightly warped, particularly where the seat meets the frame

FLUX.2 [pro]

  • + Perfectly adheres to the 'repairing' action with a natural kneeling pose
  • + Exceptional detail in the skin texture and clothing materials
  • + Beautiful bokeh and shallow depth of field that feels like a 50mm lens
  • The movement of the car lacks the requested motion blur, appearing more static
  • Composition feels a bit more staged/structured compared to the 'imperfect framing' requested

Verdict: FLUX.2 [pro] is the superior image because it accurately captures the central action of repairing the bicycle with high anatomical and textural fidelity. While FLUX.1 Krea [dev] handled the motion blur and 'imperfect' requested aesthetic slightly better, it failed to show the man actually performing a repair, showing him simply standing with the bike instead.

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]
FLUX.2 [pro]

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent crispness in the engraved plate armor patterns.
  • + Moody and professional lighting that emphasizes the bokeh effect.
  • + Symmetry and framing feel very intentional and cinematic.
  • The dirt/scars look more like surface blood splatter than integrated facial scarring.
  • Beads in the hair are very uniform and lack color variation.

FLUX.2 [pro]

  • + Superior interpretation of 'lifelike eyes' and 'faint scars' with more realistic skin textures.
  • + Exceptional detail on the leather straps and textured linen underlayer.
  • + Dynamic lighting with a visible torch source adds to the realism of the reflections.
  • The bokeh sparks appear a bit more like generic streaks rather than points of light.
  • The composition is slightly more zoomed in, clipping the armor detail.

Verdict: FLUX.2 [pro] wins by a narrow margin due to its superior rendering of textures, specifically the leather straps and the rough fabric of the cowl which were requested in the prompt. While FLUX.1 Krea [dev] produces a very clean and symmetrical image, FLUX.2 [pro] features more realistic skin imperfections and better-integrated hair accessories that enhance the 'battle-worn' aesthetic.

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]
FLUX.2 [pro]

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent food photography quality
  • + Professional use of negative space
  • + Accurate sections for appetizers/mains
  • Text consists of illegible gibberish characters
  • Repeats the header 'APPETIZERS' twice instead of using 'PIZZA'
  • Some food items in the grid look somewhat distorted

FLUX.2 [pro]

  • + Legible English text for item names
  • + Stronger incorporation of vibrant color accents
  • + Modern logo-style icons for categories
  • Repetitive content (Garlic Bread and Pizza listed under all sections)
  • Spelling errors in main headers ('MINS' instead of 'MAINS')
  • Layout is slightly cluttered compared to Model A

Verdict: FLUX.1 Krea [dev] produces a more realistic and professional-looking design layout with superior photography, but its text is entirely nonsensical. FLUX.2 [pro] succeeds in generating legible item names and better color accents, but fails on logical content organization and basic spelling in headers.

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]
FLUX.2 [pro]

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent photographic quality and lighting on the burger ingredients.
  • + Includes a dramatic fire and coal foreground that adds to the 'fiery' theme.
  • + Clear and legible typography.
  • The text is plain white and lacks the 'fiery, glowing effect' specifically requested.
  • The price is not rendered in a starburst as requested.
  • The burger is less 'exploded' and more of a standard stacked exploded view.

FLUX.2 [pro]

  • + Perfect adherence to the 'fiery/glowing' text effect requested for the title.
  • + Better 'exploded' composition with a stronger sense of motion and swirling embers.
  • + Correctly placed the price in a starburst with a glowing aesthetic.
  • The burger ingredients look slightly more illustrative compared to the high realism of Model A.

Verdict: While FLUX.1 Krea [dev] produces a more photorealistic burger, FLUX.2 [pro] followed the stylistic instructions far more accurately, particularly regarding the glowing fire text and the inclusion of the starburst price tag. FLUX.2 [pro] also captured a better sense of motion with the swirling sauce and embers, making it the superior advertisement overall.

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]
FLUX.2 [pro]

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Clean layout with a wooden frame.
  • + Excellent legibility for most of the text.
  • Significant text errors including 'Gruffle', 'Loman', and 'Chrucuations'.
  • The chalk texture feels slightly like a digital brush rather than high-friction chalk.

FLUX.2 [pro]

  • + Perfect text accuracy for all requested items.
  • + Superior realistic chalk texture with authentic dust and varying opacity.
  • + Captures the 'cozy café' atmosphere better with the blurred background.
  • The board choice is a slate slab rather than a traditional framed chalkboard mentioned in some interpretations.

Verdict: FLUX.2 [pro] is the clear winner as it followed the complex menu text perfectly, whereas FLUX.1 Krea made several hallucinations and spelling errors. FLUX.2 [pro] also delivered a significantly more realistic chalk texture and used a more convincing cursive style as requested.

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]
FLUX.2 [pro]
0% wins 0% ties 100% wins

AI Judge Analysis

FLUX.1 Krea [dev]

  • + High cinematic visual quality with realistic lighting and textures.
  • + Detailed render of the astronaut suit.
  • Failed the core prompt instruction: the astronaut is riding the horse, not the other way around.
  • Anatomical issues where the astronaut's leg merges into a mechanical horse part.

FLUX.2 [pro]

  • + Successfully followed the specific instruction of having the horse on top of the astronaut.
  • + Vibrant galactic background with good color contrast.
  • + Interesting surreal composition.
  • The back half of a second horse appears to be growing out of the astronaut's back.
  • The horse's hooves are floating awkwardly rather than standing firmly on the astronaut.

Verdict: Both models struggled with the complex spatial logic of the request. However, FLUX.2 [pro] followed the semantic instruction to place the horse on top, whereas FLUX.1 Krea produced a standard astronaut-riding-horse image, completely ignoring the 'not vice versa' constraint. Despite some anatomical confusion in the middle ground, FLUX.2 [pro] is the winner for prompt adherence.

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]
FLUX.2 [pro]

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent character expressions, especially the bored passenger
  • + Clean composition with a focused view of the capybara's face
  • + Good lighting on the subject's fur
  • Confusing composition with an extra person in the passenger seat
  • The taxi cap on the head looks like a plastic toy rather than a professional uniform
  • Taxi light on top of the car follows strange geometry

FLUX.2 [pro]

  • + Superior environmental realism with detailed dashboard and window reflections
  • + Accurate anatomy and posture for a driver
  • + High-quality textures on the jacket and cap
  • The passenger is slightly out of focus and less prominent in the composition
  • The capybara's paws look somewhat human-like due to the dark fur/lighting

Verdict: FLUX.2 [pro] is the clear winner as it more accurately follows the prompt's request for a realistic taxi interior and professional attire, whereas FLUX.1 Krea [dev] added an extra person and has less realistic lighting. FLUX.2 [pro] creates a much more convincing NYC atmosphere with intricate dashboard details and rain-streaked windows.

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]
FLUX.2 [pro]

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Strong composition with a dedicated scroll banner design
  • + Clean, symmetrical border with intricate spiderweb details
  • Significant text errors including 'Pasty Halloween' and 'nights frights'
  • Repetitive word 'are are' in the bottom banner
  • Date and time details are cluttered and poorly formatted

FLUX.2 [pro]

  • + Excellent text rendering with near-perfect spelling and layout
  • + Cinematic lighting with fog and a moon that adds depth to the background
  • + Superior adherence to the specific event details requested
  • The thorns in the border are slightly less defined compared to A
  • Parchment texture is a bit dark in the bottom corners, making the border less visible

Verdict: While FLUX.1 Krea produced a nice graphic design layout, FLUX.2 [pro] is the clear winner due to its superior text rendering and accuracy. FLUX.2 [pro] followed all layout and content instructions perfectly, whereas FLUX.1 Krea suffered from several spelling errors and typos in the invitation text.

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]
FLUX.2 [pro]

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent typography with a friendly, rounded aesthetic.
  • + Strong PBR materials, especially the translucency and sheen on the salmon.
  • The flag is placed physically in the scene rather than as a graphic icon.
  • Only one piece of sushi, which feels a bit sparse for the prompt.

FLUX.2 [pro]

  • + Perfect adherence to the layout instructions, including the flag icon placement.
  • + High-quality 3D miniature style with great variety in the sushi models.
  • + Sophisticated lighting and clean isometric composition.
  • The text is a bit tighter and less playful than Model A's stylized font.

Verdict: FLUX.2 [pro] followed the layout instructions much more precisely, specifically placing the flag as an icon below the text as implied by the prompt. While FLUX.1 Krea [dev] produced a stunning material render for the salmon, FLUX.2 [pro] created a more complete and better-composed miniature diorama with varied sushi types and cleaner iconography.

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]
FLUX.2 [pro]

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent dynamic motion showing the animals leaping and running
  • + Strong lighting with visible god rays and backlighting
  • + High-quality fur texture
  • Missed the baby bunny entirely
  • Duplicate animal species (two kittens instead of four distinct animals)

FLUX.2 [pro]

  • + Perfect prompt adherence including all four requested species
  • + Very high levels of detail in the fur and eyes
  • + Natural-looking interaction between the animals
  • Static composition compared to the 'chasing and tumbling' description
  • Subtle anatomical issues with the fox's snout

Verdict: While FLUX.1 Krea [dev] captured the energy and light of the prompt more effectively, it failed to include the bunny and instead generated two kittens. FLUX.2 [pro] followed the prompt more accurately by including all four specified animals and maintaining a very professional, polished aesthetic, making it the more reliable interpretation.

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]
FLUX.2 [pro]

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Successfully captures a detailed hand-etched vintage aesthetic.
  • + Correctly implements the 'Est. 1720' text and the cloche dome concept.
  • Severely misspells the primary brand name as 'FLAN OR'IN'.
  • The composition is a bit cluttered with the cloche, banner, and multiple text lines overlapping.

FLUX.2 [pro]

  • + Perfect text rendering for both 'Caffè Florian' and 'Est. 1720'.
  • + Excellent minimalist vector emblem style that follows the prompt instructions precisely.
  • + Clean, balanced composition with professional spacing.
  • The cloche design is very simple, bordering on generic.
  • Subtle texture is present but very minimal compared to the aesthetic in model A.

Verdict: FLUX.2 [pro] is the clear winner because it correctly spells the requested brand name 'Caffè Florian', whereas FLUX.1 Krea [dev] failed significantly on the primary text. FLUX.2 [pro] also better adheres to the 'minimalist' and 'vector emblem' style requested in the prompt, resulting in a cleaner, more professional 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]
FLUX.2 [pro]

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Crisp vector style and clean large typography for the header.
  • + Adheres strictly to the requested NASA color palette.
  • Fails completely on logical iconography, showing Saturn for 'Launch' and generic astronauts for other steps.
  • The numbering and flowchart logic are nonsensical and disconnected from the prompt's 6-step structure.

FLUX.2 [pro]

  • + Excellent adherence to the logical steps and specific iconography requested (Saturn V, lunar module, trajectory arcs).
  • + Superior text rendering and layout that mimics a professional infographic.
  • + Clever inclusion of extra details like the crew names (Armstrong, Aldrin, Collins).
  • Missing explicit step numbers 5 and 6, although the visual flow remains clear.
  • Small sub-text below headers contains gibberish/placeholder characters.

Verdict: FLUX.2 [pro] is the clear winner as it successfully translated the complex multi-step prompt into a logical and visually coherent infographic. While FLUX.1 Krea [dev] followed the artistic style and colors well, it failed to provide the specific required icons for each step, resulting in a nonsensical layout compared to the structured timeline produced by FLUX.2 [pro].

Next steps

Explore each model