Black Forest Labs' aesthetically-tuned 12-billion parameter flow transformer optimized for high-quality images with incredible aesthetics, suitable for personal and commercial use
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 [max]
25.8
arena score
#10 of 62 in Text-to-Image
Vote tally
Where the votes landed
FLUX.1 Krea [dev]
0%
win rate
Ties
0%
FLUX.2 [max]
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 Krea [dev]
FLUX.2 [max]
AI Judge Analysis
FLUX.1 Krea [dev]
- + Excellent photographic realism with natural window light
- + High quality rendering of the blue sphere's internal reflections
- + The red book looks like an authentic vintage cloth-bound book.
- − The glass cube has an open top which contradicts the book sitting 'on top' of it
- − The plant behind the cube is quite dark and lacks clear visibility through the glass.
FLUX.2 [max]
- + The glass cube is correctly depicted as a solid enclosure with a top surface
- + The plant is clearly visible through the glass as requested in the prompt
- + Excellent lighting effects with sunbeams on the table.
- − The blue sphere appears to be floating slightly above the base
- − The texture of the red book is a bit overly uniform and looks slightly digital.
Verdict: Both models followed the prompt instructions perfectly regarding object placement and color. FLUX.2 [max] is the winner because it correctly depicted the plant visible through the glass and rendered the cube as a physical structure that could actually support the book, whereas FLUX.1 Krea [dev] rendered an open-topped box.
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 [max]
AI Judge Analysis
FLUX.1 Krea [dev]
- + Successfully captures motion blur on the passing cars as requested.
- + Realistic pavement reflections and rain atmosphere.
- + Good execution of the imperfect, candid framing.
- − The subject is standing and holding the bike rather than actively repairing it.
- − The bicycle's rear wheel and chain area have significant structural distortions.
- − The face looks slightly more stylized/painterly compared to the realistic skin texture requested.
FLUX.2 [max]
- + Excellent adherence to the 'repairing' action with realistic hand placement and tools on the ground.
- + Superior skin texture and fine detail in the subject's face and hands.
- + Highly realistic bicycle and basket construction.
- − Lacks significant motion blur on the background vehicles requested in the prompt.
- − The 'imperfect framing' is less evident compared to Image A.
Verdict: FLUX.1 Krea (dev) follows the technical camera instructions like motion blur and imperfect framing more closely, but fails on the primary action and mechanical detail. FLUX.2 (max) delivers a much more convincing and high-quality representation of an elderly man repairing a bike with superior textures and anatomical accuracy, though it misses the specific request for motion-blurred cars. FLUX.2 (max) is preferred for its significantly higher visual fidelity and logical consistency.
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 [max]
AI Judge Analysis
FLUX.1 Krea [dev]
- + Excellent symmetrical framing and intense facial expression
- + Superior Bokeh effects with well-defined light circles
- + Ornate engravings on the armor are intricate and well-realized
- − Dirt on the face appears more like blood splatters than grime
- − The leather strap lacks high-resolution surface grain
FLUX.2 [max]
- + Outstanding skin texture including realistic visible pores and scabs
- + Exceptional detail on the frayed cloth underlayer and weathered leather
- + Dynamic three-quarter angle adds depth to the character's gaze
- − The hair braids are somewhat messy and blend awkwardly with the metal beads
- − Lighting is a bit flatter across the face compared to the more dramatic shadowing in Model A
Verdict: Both models captured the prompt with high accuracy, but FLUX.2 [max] takes the lead due to its incredible micro-detail in textures, particularly the skin, frayed cloth, and scratched leather. While FLUX.1 Krea [dev] offers a more cinematic, symmetrical composition with better bokeh, FLUX.2 [max] feels more 'lifelike' and physically grounded in its materials.
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 [max]
AI Judge Analysis
FLUX.1 Krea [dev]
- + Elegant white-space management and clean professional layout.
- + High-quality, appetizing food photography in the grid.
- + Good use of bold sans-serif typography for headings.
- − Repeat 'Appetizers' section instead of following the pizza/mains request.
- − Text legibility for sub-items is poor with significant artifacts.
FLUX.2 [max]
- + Excellent adherence to all prompt sections: Appetizers, Pizza, and Mains.
- + Superior text rendering and legibility for a menu mockup.
- + Vibrant color-coding for sections enhances the user interface.
- − Food photos are somewhat repetitive with mostly pizza and sandwiches.
- − The grid layout feels slightly more cramped than Model A.
Verdict: FLUX.2 [max] is the winner as it correctly implemented all three requested sections (Appetizers, Pizza, and Mains) while maintaining high text legibility. While FLUX.1 Krea [dev] offered a more sophisticated aesthetic, it failed the prompt instruction by repeating the Appetizers category and had messy, unreadable body text.
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 [max]
AI Judge Analysis
FLUX.1 Krea [dev]
- + Excellent photorealistic rendering of the burger textures
- + Strong visual hierarchy with clean, professional typography
- + Dynamic lighting with realistic fire and coal elements
- − Failed to place the price in a starburst as requested
- − Text rendering missed the 'fiery, glowing effect' specified in the prompt
- − The burger explosion is mostly vertical and less 'dynamic' than model B
FLUX.2 [max]
- + Perfect adherence to all text requirements, including the starburst and fiery font effects
- + Superior 'exploded' composition with components spread at dynamic angles
- + Highly effective use of embers and sauce splatters to create a sense of motion
- − Illustrative feel to the sauce and background compared to Model A's realism
- − Slightly crowded composition with the starburst overlapping some elements
Verdict: FLUX.2 [max] is the winner because it followed every specific detail of the prompt, particularly the complex text requirements like the fiery glowing font and the price starburst. While FLUX.1 Krea produced a more traditionally photorealistic food shot, it ignored several stylistic instructions regarding the graphical elements.
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 [max]
AI Judge Analysis
FLUX.1 Krea [dev]
- + Features a realistic wood frame and chalkboard smudge texture
- + Correctly handles the date and partial title prompt
- − Text contains several hallucinations and misspellings like 'Gruffle' and 'Hcoman'
- − The font style looks more like a digital script than authentic handwritten chalk
FLUX.2 [max]
- + Excellent text accuracy with no spelling errors on the requested items
- + Authentic chalk texture with realistic variation in thickness and dustiness
- + Consistent handwriting style that matches the cozy café aesthetic requested
- − Title is in a stylized print rather than the requested 'elegant cursive'
Verdict: FLUX.2 [max] significantly outperforms FLUX.1 Krea [dev] in terms of text rendering and overall prompt adherence. While FLUX.1 Krea [dev] struggles with multiple spelling errors and illogical menu repetitions, FLUX.2 [max] delivers crisp, accurate text and a more convincing 'hand-written' chalk texture.
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 [max]
AI Judge Analysis
FLUX.1 Krea [dev]
- + Excellent adherence to the 'horse on top' instruction
- + Detailed mechanical armor/saddle for the horse
- + Cinematic lighting with a realistic Earth background
- − The horse's legs have slightly unnatural anatomical proportions
- − The astronaut's positioning is somewhat clipped by the horse's neck
FLUX.2 [max]
- + High level of intricate detail in the galaxy background and asteroid
- + Very clean rendering of the horse and astronaut equipment
- + Stable and pleasing composition
- − Failed the negative constraint/specific instruction of 'horse on top'
- − Produces a standard interpretation rather than the requested surreal reversal
Verdict: While FLUX.2 [max] produced a high-quality and visually appealing image, it completely ignored the specific instruction to have the horse riding the astronaut. FLUX.1 Krea [dev] successfully followed this difficult logical constraint, creating a surreal and cinematically lit scene where the horse is the primary rider.
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 [max]
AI Judge Analysis
FLUX.1 Krea [dev]
- + The capybara's paws are correctly rendered as furry animal limbs on the steering wheel.
- + The capybara is looking forward through the windshield with a professional demeanor.
- + The yellow taxi cap is clearly legible and fits the theme well.
- − There is an extra person in the passenger seat not requested by the prompt.
- − The 'taxi' sign on top of the car is facing the wrong direction relative to the car's orientation.
FLUX.2 [max]
- + Successfully rendered a single businesswoman in the back seat as requested.
- + The lighting on the passenger's face from the phone screen is very realistic.
- + The city background through the windows feels more atmospheric and expansive.
- − The capybara has distinctively human hands and arms, which is jarring and inaccurate.
- − The taxi sign on top of the car is oddly placed and partially cut off.
Verdict: FLUX.1 Krea [dev] followed the physical description of the capybara much better by giving it paws, although it failed the negative constraint of having only one passenger by adding an extra woman in the front seat. FLUX.2 [max] captured the boredom and lighting of the passenger perfectly, but the inclusion of human hands on the animal driver is a significant anatomical failure that ruins the prompt's intent. FLUX.1 Krea [dev] is preferred because the capybara's appearance is more coherent even with the extra character.
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 [max]
AI Judge Analysis
FLUX.1 Krea [dev]
- + Strong vintage graphic design aesthetic
- + Elegant gothic border with distinct spiderweb corners
- − Major typos in the central header text ('Pasty Halloween')
- − Repetitive and garbled text on the bottom scroll banner
- − The jack-o-lantern looks more like a 2D illustration than a cinematic object
FLUX.2 [max]
- + Perfect text rendering for all requested details, including date and location
- + Highly realistic cinematic lighting on the central jack-o-lantern
- + Atmospheric background with mist and a spooky castle silhouette
- − The thorns in the border are slightly messy in the corners
- − Small section of the parchment edge at the top left looks like a digital artifact
Verdict: FLUX.2 [max] significantly outperformed FLUX.1 Krea [dev] by accurately rendering all the specific text requested in the prompt, whereas FLUX.1 Krea [dev] failed with multiple typos and garbled phrases. FLUX.2 [max] also provided a more immersive, cinematic atmosphere with realistic lighting and a cohesive composition.
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 [max]
AI Judge Analysis
FLUX.1 Krea [dev]
- + Excellent text rendering with clean, playful typography.
- + Stronger 3D lighting and shadow realism on the diorama base.
- + High-quality salmon texture that feels both cartoonish and appetizing.
- − The Japan flag is placed on a toothpick in the food rather than as a UI icon as requested.
- − The scene feels a bit sparse with only one piece of sushi.
FLUX.2 [max]
- + Perfect adherence to the flag icon request as a graphic element next to the text.
- + Excellent interpretation of the diorama base with layered wooden and stone textures.
- + Great variety of sushi models that fit the miniature aesthetic.
- − The 'JAPAN' text is slightly darker and less balanced in the layout than Model A.
- − The 45-degree angle is slightly flatter compared to a true isometric look.
Verdict: Both models followed the prompt exceptionally well, but FLUX.2 (max) is the winner due to its superior scene composition and precise adherence to the flag icon request. While FLUX.1 Krea (dev) has slightly better lighting, FLUX.2 (max) provides a more complete miniature world with a better variety of assets and a more professional layout.
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 [max]
AI Judge Analysis
FLUX.1 Krea [dev]
- + Excellent fur texture and individual hair detail
- + Vibrant, high-contrast colors and strong god rays
- + Extremely cute and expressive facial features
- − Missed the rabbit completely, substituting it with a second kitten
- − Depth of field is a bit flat with some blurred flowers feeling artificial
FLUX.2 [max]
- + Successfully included all four requested animals (dog, cat, bunny, fox)
- + Beautiful atmospheric lighting with realistic dew sparkles on the grass
- + Action-oriented composition following the 'chasing' and 'tumbling' prompt
- − The fox's anatomy is slightly stiff compared to the other animals
- − Smaller scale for animals makes the individual fur detail less 'ultra-detailed' than Model A
Verdict: While FLUX.1 Krea (dev) has superior fur rendering and a more polished 'masterpiece' glow, it failed the core prompt by leaving out the bunny and including two kittens. FLUX.2 (max) followed the prompt perfectly, including all specific animals in a more complex and atmospheric scene with better adherence to the 'dew sparkles' and 'tumbling' instructions.
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 [max]
AI Judge Analysis
FLUX.1 Krea [dev]
- + Excellent vintage engraving style with rich cross-hatching
- + Dynamic use of typography and banner layout
- − Significant spelling errors in the brand name ('FLANOR'IN')
- − Steam looks more like a chimney or nozzle emission than natural steam
FLUX.2 [max]
- + Perfect text rendering with correct spelling and accents
- + Clean, balanced circular emblem composition
- + Captures the minimalist vector style more accurately
- − Illustration of the cloche is very simple and lacks the 'vintage' character of the other model
- − Banner feels a bit small relative to the circle
Verdict: While FLUX.1 Krea [dev] has a superior artistic and aged aesthetic, its inability to spell the requested name correctly makes it unusable as a logo. FLUX.2 [max] follows the prompt perfectly, delivering correct typography and a professional, balanced layout that adheres to both the 'minimalist' and 'vector' keywords.
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 [max]
AI Judge Analysis
FLUX.1 Krea [dev]
- + Stronger 'navy and red' NASA color palette adherence
- + Includes a clear landing site marker for 'Tranquility'
- − Failed almost all logic and icon requests by showing Saturn (planet) and astronauts instead of mission phases
- − Text rendering is messy and contains gibberish
- − The numbering sequence is illogical and poorly placed
FLUX.2 [max]
- + Excellent prompt adherence for all 6 mission steps including specific icons like the Saturn V and Lunar Module
- + Crisp, legible text and modern vector layout
- + Includes great thematic details like the pilot names and 'Tranquility' marker
- − Repeats the label 'Earth Orbit' for the first two panels
- − Colors are slightly more muted gray than the requested navy
Verdict: FLUX.2 [max] is the clear winner as it successfully follows the complex multi-step infographic structure, providing specific icons for launch, orbit, and landing as requested. FLUX.1 Krea [dev] failed the logic of the prompt, incorrectly depicting the planet Saturn instead of a Saturn V rocket and failing to provide a coherent sequence of events.
Next steps
Explore each model
Black Forest Labs' flagship image generation model delivering state-of-the-art quality with exceptional realism, precision, and consistency for both text-to-image and advanced image editing