Black Forest Labs' premium multimodal flow transformer with greatly improved prompt adherence and typography generation for in-context image generation and editing without compromise on speed
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
FLUX.1 Kontext [max]
23.7
arena score
#23 of 62 in Text-to-Image
Skill signature
· Text-to-Image
FLUX1.1 [pro]
18.4
arena score
#50 of 62 in Text-to-Image
Vote tally
Where the votes landed
FLUX.1 Kontext [max]
0.0%
win rate
Ties
100.0%
FLUX1.1 [pro]
0.0%
win rate
0.0%
100.0% ties
0.0%
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 Kontext [max]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent adherence to lighting instructions with realistic 'soft window light from the left'.
- + Highly realistic reflections and caustics on the wooden table.
- + Accurate glass physics showing the background through the refraction of the cube.
- − The blue sphere has a slightly textured, non-smooth appearance compared to a typical sphere.
FLUX1.1 [pro]
- + Perfectly smooth and vibrant blue sphere.
- + Simple and clean composition that isolates the subject well.
- + Follows all object placement instructions correctly.
- − The glass container is more of a rectangular prism than a cube.
- − The light source is somewhat ambiguous and lacks the directional shadow qualities requested.
Verdict: FLUX.1 Kontext [max] produced a much more photorealistic image with sophisticated lighting and table reflections that perfectly matched the 'light from the left' prompt. FLUX1.1 [pro] followed the placement instructions well but failed to make the object a cube and had flatter lighting overall.
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 Kontext [max]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent adherence to the 'repairing' action with a detailed look at the bicycle chain
- + The rain effects are highly visible and realistic across the entire frame
- + Exceptional skin texture and anatomical detail in the hands
- − The man's heritage appears somewhat ambiguous compared to the specific request
- − The bicycle geometry is slightly warped near the rear wheel
FLUX1.1 [pro]
- + Strong composition with a clear cinematic feel and good use of bokeh
- + Captures the 'candid' and 'street photo' aesthetic very effectively
- + Excellent job capturing a specific Japanese elderly character
- − The 'repairing' action is weakly represented as he appears to just be holding the bike
- − Major anatomical/logical error with a third small wheel or pedal-like structure floating behind his feet
- − The bicycle frame is nonsensical and disconnected in the middle
Verdict: FLUX.1 Kontext [max] is the winner because it successfully depicts the man actually repairing the bicycle with high-quality textures and realistic rain. FLUX1.1 [pro] creates a beautiful atmosphere and a more accurate character model for the location, but it fails on a functional level with severe structural hallucinations in the bicycle and a lack of clear interaction with the mechanics of the bike.
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 Kontext [max]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent depiction of ornate engraved plate armor with high luster
- + Strong warm lighting consistent with torchlight source
- + Clearly visible braids and beard texture
- − The skin has a somewhat artificial, uniform 'leathery' texture
- − Missing the requested dirt and scars on the skin
- − The eye color looks slightly supernatural or flat rather than just lifelike
FLUX1.1 [pro]
- + Superb skin texture including fine dirt, scars, and pores
- + Highly realistic and lifelike eyes with impressive depth
- + Great interpretation of the 'battle-worn' aesthetic with messy hair and grime
- − The armor is slightly more muted and less 'ornate' than requested
- − The beads in the hair are smaller and less distinct than in image A
Verdict: FLUX1.1 [pro] delivers a much more convincing 'battle-worn' appearance with realistic skin imperfections and lifelike eyes that exceed the quality of FLUX.1 Kontext [max]. While FLUX.1 Kontext [max] features more impressive engravings on the armor, its clean skin and slightly stylized look don't match the gritty details of the prompt as effectively.
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 Kontext [max]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent photo quality for the individual food items
- + Clean, professional white space usage
- + Good adherence to the grid layout requirement
- − Text is mostly gibberish with messy scripts
- − Sections for appetizers and mains are not clearly defined as requested
- − Lacks vibrant accents, appearing a bit monochromatic
FLUX1.1 [pro]
- + Successfully includes specific sections like 'APPETIZERS' and 'PIZZA'
- + High-quality presentation with cutlery adds to the professional feel
- + Modern aesthetic with better font hierarchy
- − Food photos in the grid are a bit smaller and more cluttered
- − The grid layout is slightly disjointed compared to Model A
- − Text includes some minor character artifacts
Verdict: FLUX1.1 [pro] is the likely winner because it followed the structural instructions more closely, including specific category headers like appetizers and pizza. While FLUX.1 Kontext [max] had beautiful food photography, it failed to categorize the menu items effectively, resulting in a less functional design.
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 Kontext [max]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent typography rendering with the requested glowing/fiery effect.
- + Perfect adherence to all text requirements including the price and starburst element.
- + Very realistic food rendering with detailed textures on the patty and vegetables.
- − The burger is not fully 'exploded' by component; rather, it is a whole burger with a few extra toppings floating around it.
- − The price is missing the starburst container requested in the prompt.
FLUX1.1 [pro]
- + Strong 'exploded' aesthetic with many small components flying through the air.
- + Great use of lighting and depth of field in the background.
- − Failed to apply the fiery/glowing effect to the price text.
- − Includes redundant and conflicting text (neon blue vs plain white).
- − Missing the starburst element and has garbled text at the bottom.
Verdict: FLUX.1 Kontext [max] is the winner because it successfully integrated all requested text and visual themes with high fidelity and professional layout. While FLUX1.1 [pro] captured the 'exploded' motion well, it struggled with the text styling instructions, producing redundant titles and ignoring the fiery effect on the price.
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 Kontext [max]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent text accuracy including completion of the truncated 'Brown But...' prompt item
- + Highly realistic chalk texture with smudges and natural variations
- + Perfect adherence to price and item details
FLUX1.1 [pro]
- + Elegant cursive title as requested in the prompt
- + Beautifully composed background and lighting in the cafe setting
- + Consistent artistic style across the handwriting
- − Serious text errors including repeating the octopus item and adding 'Herbss'
- − Incorrect pricing ($228 and $98) compared to the prompt
- − Hallucinated 'Chipkies' and spelling errors in the footer text
Verdict: FLUX.1 Kontext [max] followed the prompt instructions perfectly, correctly inferring the truncated text for 'Brown Butter Chocolate Chip Cookies' and maintaining accurate pricing. FLUX1.1 [pro] produced a more atmospheric image with better cursive, but failed significantly on text accuracy by repeating lines and misspelling basic words. FLUX.1 Kontext [max] is the clear winner for its superior logic and adherence to the specific menu requirements.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
FLUX.1 Kontext [max]
FLUX1.1 [pro]
0% wins
100% ties
0% wins
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent high-detail rendering of the spacesuit and horse fur.
- + Clearer cinematic background with lens flare and planetary details.
- + Physically consistent lighting for the space setting.
- − Prompt adherence failure: shows astronaut on top of the horse, ignoring 'horse on top' instruction.
FLUX1.1 [pro]
- + Dynamic composition and more 'surreal' atmospheric lighting.
- + Intricate saddle and gear details that blend astronaut and equestrian themes.
- + Highly expressive horse pose.
- − Prompt adherence failure: shows astronaut on top of the horse, ignoring 'horse on top' instruction.
- − The horse's front legs and hooves have anatomical inconsistencies.
Verdict: Both FLUX.1 Kontext and FLUX1.1 [pro] failed the negative constraint/spatial reasoning challenge, placing the astronaut on top of the horse instead of vice versa. FLUX.1 Kontext is the preferred choice as its anatomical rendering of the horse is superior and the visual quality is crisp and professional.
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 Kontext [max]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent photorealistic texture on the capybara's fur.
- + Accurate high-angle perspective from outside/side window.
- + The capybara's paws are correctly placed on the steering wheel.
- − The passenger is holding the phone to her ear like a call instead of looking at it as requested.
- − The interior scale feels slightly cramped.
FLUX1.1 [pro]
- + Successfully captures both characters clearly in one frame from the back seat.
- + The passenger is looking at her phone as requested with a bored expression.
- + Creative cinematic lighting and bokeh in the background.
- − The capybara is not holding the steering wheel; it appears to be sitting in the passenger side or the center.
- − The scale of the capybara relative to the woman is slightly too large.
Verdict: FLUX.1 Kontext [max] produced a more technically realistic image with superior texture and correct placement of the driver's paws on the wheel. However, FLUX1.1 [pro] followed the behavioral instructions for the passenger better and offered a more balanced composition that showed the interior scene more clearly, even though it failed the specific steering wheel 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.1 Kontext [max]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent typography with a truly gothic aesthetic.
- + Text is perfectly legible and free of major typos.
- + Captures the 'dark parchment' and 'vintage' vibe more effectively through texture.
- − The date format uses commas instead of dots (30,10,2026).
- − The location is repeated twice at the bottom.
- − The banner for the sub-text is integrated behind the pumpkin rather than clear.
FLUX1.1 [pro]
- + Stronger visual composition with a clear focal moon and vertical hierarchy.
- + Includes the requested 'thorns' in the border very clearly with a vibrant orange contrast.
- + Good use of cinematic lighting on the pumpkin and trees.
- − Significant text errors including 'You inivted to a n night of frights'.
- − Repetitive layout of date, time, and location information.
- − Failed the 'square format' requirement, producing a rectangular poster.
Verdict: FLUX.1 Kontext [max] is the winner because it followed the square format constraint and produced high-quality, legible gothic typography that fits a 19th-century invitation style. While FLUX1.1 [pro] has a more striking color palette, its failure to adhere to the requested aspect ratio and the presence of numerous spelling errors in the text make it less usable for a design-heavy prompt.
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 Kontext [max]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent text typography and rendering
- + Clean and simple composition following the 'minimal' requirement
- + High quality textures on the fish and rice
- − Missed the request for a small flag icon
- − The background is slightly more saturated than the 'light blue' requested
FLUX1.1 [pro]
- + Beautiful 3D miniature collection with high variety
- + Softer, more accurate light blue background
- + Captures the diorama feel very effectively
- − Failed to include the flag icon
- − The text 'SUSHI' is significantly smaller than the 'JAPAN' text, relative to Model A's balanced scaling
- − Ignored the 'minimal' garnish instruction by including multiple extra items like tomatoes
Verdict: FLUX.1 Kontext [max] produced a much cleaner and more professional-looking image that strictly followed the 'minimal' instruction, featuring high-quality rendered text. While FLUX1.1 [pro] offered more variety in the sushi types, it ignored the request for minimal garnish and the text hierarchy is less impactful. Both models failed to include the requested flag icon.
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 Kontext [max]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.1 Kontext [max]
- + Includes all four requested animals: puppy, kitten, bunny, and fox kit.
- + Excellent composition with all animals interacting and looking towards the butterflies.
- + Beautiful lighting with clear god rays and a rich wildflower environment.
- − The puppy's front left leg has a slightly awkward anatomical merger with the foliage.
- − The rabbit's face looks a bit more like a plush toy than a real animal compared to the others.
FLUX1.1 [pro]
- + Extremely high-quality fur texture and realistic eye reflections.
- + Very soft, dreamy bokeh that creates a professional photographic look.
- + Whimsical character expressions that capture the 'joyful' vibe perfectly.
- − Failed to include the fourth animal, missing the red fox kit entirely.
- − The animals are mostly sitting still rather than 'tumbling' or 'playfully chasing' as requested.
- − The kitten is orange instead of the requested 'tabby' pattern.
Verdict: FLUX.1 Kontext [max] is the winner because it successfully included all four distinct animals requested in the prompt, whereas FLUX1.1 [pro] missed the fox kit. While FLUX1.1 [pro] offered slightly more refined fur textures and lighting, FLUX.1 Kontext [max] captured the complexity of the scene and the specific animal types much more accurately.
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 Kontext [max]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.1 Kontext [max]
- + Perfect text rendering of the requested brand name including the accent over the letter E.
- + Clean minimalist vector style that adheres closely to the 'emblem' prompt.
- + Excellent balance and composition with a well-defined banner.
- − The steam element is very simple and could be more elegantly integrated.
FLUX1.1 [pro]
- + Intricate woodcut-style illustration on the cloche provides a premium vintage feel.
- + Includes an elegant decorative border that enhances the overall presentation.
- − Significant spelling error in the primary brand name, changing 'Florian' to 'Fratilian'.
- − Incorrect rendering of 'Caffè', using an extra dot and an unusual character shape.
- − Slightly less 'minimalist' than requested due to high amount of ornamental detail.
Verdict: FLUX.1 Kontext [max] is the clear winner as it followed all instructions perfectly, including the specific spelling of 'Caffè Florian'. While FLUX1.1 [pro] produced a more intricate and aesthetically pleasing illustration of the cloche, it failed significantly on prompt adherence by misspelling the core text.
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 Kontext [max]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent flat-vector illustrative style with high visual appeal.
- + Strong color palette consistency matching the NASA-inspired request.
- + Includes recognizable depictions of the Saturn V and Lunar Module.
- − Major labeling errors including labeling Earth as 'MOON'.
- − Instructional steps for a chronological infographic were ignored in favor of a messy diagram.
- − Contains unrelated celestial bodies like a planet with rings.
FLUX1.1 [pro]
- + Successfully follows the requested infographic structure with numbered steps.
- + Very clean, modern vector aesthetic with minimal distractions.
- + Excellent adherence to the 'navy, white, and light gray' color palette.
- − Text rendering is mostly illegible gibberish.
- − The central moon graphic is somewhat abstract and lacks the 'crisp lines' requested for the Earth elements.
- − Missing some specific icons like the Saturn V for the launch step.
Verdict: FLUX1.1 [pro] followed the complex formatting instructions much better, producing a structured, numbered infographic that aligns with the requested steps, despite the illegible text. FLUX.1 Kontext [max] produced a more beautiful illustration but failed fundamentally on accuracy, mislabeling the Earth as the Moon and failing to follow the step-by-step layout requested.
Next steps
Explore each model
Black Forest Labs' enhanced 12-billion parameter flow transformer with 6x faster generation than FLUX.1 [pro], delivering superior composition, detail, and artistic fidelity