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 of 62 in Text-to-Image
FLUX1.1 [pro] Ultra
#51 of 62 in Text-to-Image
Where the votes landed
FLUX.1 Kontext [max]
100.0%
win rate
Ties
0.0%
FLUX1.1 [pro] Ultra
0.0%
win rate
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.”
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent depiction of window light and shadows on the table
- + The sphere displays authentic glass refraction and reflections
- + High-quality photographic texture on the book and sphere
- − The glass cube has a heavy mirrored base that wasn't requested
FLUX1.1 [pro] Ultra
- + Perfect adherence to spatial relationships, including the plant behind the cube
- + Clean, modern aesthetic with very clear glass edges
- + Accurate representation of the blue sphere floating/suspended inside
- − Lighting is somewhat flat compared to the dramatic shadows in the other model
- − Physics of the sphere are slightly ambiguous compared to the weighted feel of Model A
Verdict: Both models followed the prompt instructions perfectly, including the specific placement of the cube, sphere, book, and plant. FLUX1.1 [pro] Ultra produced a cleaner, more balanced composition that feels more accurately like a glass cube, while FLUX.1 Kontext [max] excelled in lighting and shadow realism but added an unprompted mirrored base to the glass structure.
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.”
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent depiction of rain with visible droplets and realistic interaction with surfaces
- + Superior shallow depth of field giving a professional cinematic feel
- + Realistic skin texture and age-appropriate physical details
- − The bike chain and crankset are physically impossible and incorrectly rendered
- − Missed the motion blur requirement for passing cars
FLUX1.1 [pro] Ultra
- + Successfully incorporated motion blur from a passing car
- + Good adherence to the imperfect framing and street photography composition
- + Correctly depicted a Japanese subject in a clear urban context
- − The 'repairing' action is less convincing, looking more like he is just holding the basket
- − The rain effect is very subtle compared to the request for 'light rain'
- − The bicycle geometry, particularly the rear wheel and frame, is anatomically broken
Verdict: FLUX.1 Kontext [max] creates a much more atmospheric and cinematic image with impressive rain effects and textures, though it fails to include the requested motion blur. FLUX1.1 [pro] Ultra captures the motion blur and a more 'candid' feel, but the image quality feels slightly more synthetic and the bicycle's anatomy is significantly flawed. Overall, FLUX.1 Kontext [max] is preferred for its superior artistic execution and lighting, despite the technical bike errors.
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.”
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent adherence to the prompt including braided hair, scars, and ornate engraved armor.
- + Very high-quality textures on the skin, showing realistic sweat and dirt.
- + Good use of cinematic lighting and bokeh sparks that create a sense of atmosphere.
- − The braided hair lacks the specific 'small beads' requested in the prompt.
- − The face appears slightly overly bronzed/saturated from the warm light.
FLUX1.1 [pro] Ultra
- − The image failed to load or is a solid black block.
- − Completely fails to meet any prompt requirements.
Verdict: FLUX.1 Kontext [max] produced a high-quality, detailed portrait that follows almost every part of the complex prompt, including specific armor details and atmospheric lighting. FLUX1.1 [pro] Ultra failed to generate a visible image, resulting in a black frame. As a result, FLUX.1 Kontext [max] is the winner by default and on merit of its strong visual execution.
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.”
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent grid alignment with consistent spacing
- + Very clean professional layout following the minimalist brief
- + Clear sans-serif typography for the main headings
- − Text is largely gibberish with inconsistent font styles for subheaders
- − Subject matter is heavily repetitive, showing mostly the same pizza
FLUX1.1 [pro] Ultra
- + Successfully included specific sections for Appetizers, Pizza, and Mains
- + Highly vibrant and diverse food photography within the grid
- + Better text rendering with fewer spelling artifacts in the body
- − The 'For Pizzzans' header has a noticeable typo
- − Layout feels slightly cluttered with overlapping elements compared to Image A
Verdict: FLUX1.1 [pro] Ultra followed the complex layout instructions more precisely by including the specific requested sections (Appetizers, Pizza, Mains) and providing diverse food imagery. While FLUX.1 Kontext [max] has a cleaner aesthetic that better fits the 'minimalist' prompt, its content is overly repetitive and it failed to define the distinct sections requested.
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.”
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent typography style that matches the 'fiery, glowing' prompt requirement.
- + Good use of high-quality textures on the burger bun and embers.
- − The burger is not truly 'exploded' with components suspended separately; it is mostly a whole burger with odd side-bread pieces.
- − Failed to include the price in a starburst as requested.
FLUX1.1 [pro] Ultra
- + Stronger 'exploded' effect with distinct layers shown in mid-air.
- + Very clean, professional lighting and a clear fiery background.
- + Accurate text rendering for all requested strings.
- − The burger design is a triple patty, which wasn't specifically requested and looks a bit cluttered.
- − Missing the starburst requirement for the price tag.
- − Includes some small AI-generated gibberish text at the bottom corners.
Verdict: FLUX1.1 [pro] Ultra is the winner because it better captures the requested 'exploded' burger effect and presents a more dynamic composition. While FLUX.1 Kontext has nicer typography for the main title, its failure to actually separate the burger components in mid-air makes it less responsive to the core prompt.
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.”
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent text legibility and spelling accuracy.
- + Very realistic chalk texture with smudges and varying pressure.
- + Followed all menu item instructions including the unfinished 'Brown But...' intelligently.
- − The title is in print-style caps rather than the requested 'elegant cursive'.
FLUX1.1 [pro] Ultra
- + Good blackboard and cafe background aesthetics.
- + The handwriting has a nice natural slant.
- − Significant spelling errors and repetitive text hallucinations.
- − Failed to follow the specific text for the third menu item, creating a messy layout.
- − Missed the 'S' in 'TODAY'S'.
Verdict: FLUX.1 Kontext [max] is the clear winner as it produced perfectly legible, correctly spelled text that followed the prompt's layout, whereas FLUX1.1 [pro] Ultra suffered from significant text repetition and gibberish. While both models struggled to provide a true 'elegant cursive' for the title, FLUX.1 Kontext [max] captured the realistic chalk texture and smudge marks far more effectively.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent anatomical detail of the horse and astronaut gear.
- + High cinematic quality with realistic lens flares and lighting.
- + Strict adherence to the 'horse riding astronaut' concept with the horse as the mount.
- − The horse lacks space-specific gear, making the surrealism less cohesive.
- − Lighting on the astronaut's back is slightly inconsistent with the primary light source.
FLUX1.1 [pro] Ultra
- + Dynamic composition with a more epic, high-altitude perspective of Earth.
- + Includes creative sci-fi details like the extra satellites and a colorful antenna on the backpack.
- + Better integration of the horse into the scene with harness-like straps that look more functional.
- − The horse's front-right leg has an awkward, distorted structure.
- − The small floating Earth in the top right corner is redundant and logically confusing given the background.
Verdict: Both models followed the prompt correctly, placing the astronaut on top of the horse. FLUX.1 Kontext [max] delivered a cleaner, more anatomically sound image with better texture quality, while FLUX1.1 [pro] Ultra created a more ambitious composition that unfortunately suffered from minor anatomical distortion in the horse's legs.
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.”
AI Judge Analysis
FLUX.1 Kontext [max]
- + Successfully placed the passenger in the back seat as requested
- + Excellent fur texture and lighting on the capybara
- + The taxi driver cap looks realistic and fits the animal naturally
FLUX1.1 [pro] Ultra
- + Very high resolution and sharp details throughout
- − Failed to place the human in the back seat, placing her in the passenger seat instead
- − The human passenger appears to be holding the steering wheel, causing a major logic error
- − The capybara's anatomy and posture look somewhat distorted to fit the seat
Verdict: FLUX.1 Kontext [max] followed the spatial instructions of the prompt much better, correctly placing the business woman in the back seat. FLUX1.1 [pro] Ultra failed the composition logic by placing the passenger in the front seat and having her hands interact with the steering wheel, which contradicted the prompt's intent.
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.”
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent atmospheric lighting with a dark, moody palette.
- + Accurate text rendering of all requested details without repetition.
- + Intricate and cohesive border design using spiderwebs and thorns.
FLUX1.1 [pro] Ultra
- + High visual clarity and sharp detail on the parchment texture.
- + Prominent thorn border and well-rendered twisted trees.
- + Legible typography for the address and date.
- − Included a large spelling error ('noickt') and repeated the invitation text twice.
- − Missing the word 'Party' from the main title header.
- − The lighting on the pumpkin feels slightly disconnected from the parchment background.
Verdict: FLUX.1 Kontext is the clear winner as it accurately followed all text instructions, including the full title and specific details, whereas FLUX1.1 [pro] Ultra missed the word 'Party', included a significant typo, and repeated lines of text. Visually, FLUX.1 Kontext also captured the 'dark parchment' and cinematic mood more effectively, creating 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.”
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent 3D miniature clay-like aesthetic.
- + Strong, bold text rendering with good visual weight.
- + Clean and simple composition that feels ultra-clear.
- − Missed the request for a flag icon.
- − The perspective is slightly lower than the requested 45-degree angle.
FLUX1.1 [pro] Ultra
- + Successfully included all elements, including the small flag icon.
- + Perfect 45-degree isometric perspective and layout.
- + Dynamic scene with high-quality PBR material representation.
- − Includes some excess 'garnish' elements like the large plant and bug that weren't requested.
- − The 'JAPAN' text is slightly less cohesive than the primary subject.
Verdict: While FLUX.1 Kontext produced a charming and clean miniature, FLUX1.1 [pro] Ultra followed the prompt more comprehensively by including the flag icon and hitting the specific isometric angle. FLUX1.1 [pro] Ultra also showcased more detailed material textures on the rice and plate, making it the superior technical dish representation despite some extra visual clutter.
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.”
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent adherence to the tabby kitten requirement with distinct stripes
- + The composition feels more grounded and the animals look more physically presence
- + Successfully depicts subtle god rays and better 'dew sparkles' in the background
- − The fox kit has a slightly awkward mouth expression
- − The butterfly wings are a bit blurry and lack detail
FLUX1.1 [pro] Ultra
- + Beautifully soft lighting and dreamy color palette
- + The animals have very consistent, expressive 'large' eyes as requested
- + Highly professional bokeh and depth of field
- − Failed to include a 'tabby' kitten, rendering it as solid orange/ginger instead
- − The bunny's face is somewhat anthropomorphized to the point of looking less realistic
Verdict: Both models captured the heartwarming, wholesome vibe of the prompt effectively. FLUX.1 Kontext [max] is the winner because it adhered more accurately to the specific animal types requested, particularly the tabby kitten, whereas FLUX1.1 [pro] Ultra produced a ginger kitten and leaned more toward a stylized 'cute' aesthetic rather than the requested hyper-photorealistic look.
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.”
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent typography that perfectly matches the requested text
- + Great vintage vector feel with a textured paper effect
- + Clean and minimalist composition that works well as a logo
- − The steam element is a bit thick, losing some elegance
FLUX1.1 [pro] Ultra
- + Elegant illustration of the cloche dome and steam
- + Sophisticated use of brown and cream tones in a circular emblem
- + High visual quality with professional-looking vector lines
- − Failed to spell the primary text correctly, generating 'Caffè Framilian'
- − Less minimalist than requested, leaning towards a complex seal
Verdict: FLUX.1 Kontext [max] perfectly followed the text requirements and captured the minimalist vintage aesthetic requested. While FLUX1.1 [pro] Ultra produced a more detailed and visually rich emblem, its failure to correctly spell 'Florian' makes it less useful for the specific prompt.
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.”
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent legibility of the main title and crew names.
- + Clean, modern flat-vector aesthetic that matches the requested style.
- + Logical layout with clear arrows despite skipping some steps.
- − Missed several specific steps requested in the prompt (Descent, Earth Orbit).
- − Some garbled text in the middle and right labels.
- − The rocket design is generic rather than a Saturn V style.
FLUX1.1 [pro] Ultra
- + Successfully included almost all requested infographic steps in a sequence.
- + Strong NASA-inspired color palette and vector iconography.
- + Sophisticated composition with a curved lunar surface grounding the design.
- − Significant amount of 'Lorem Ipsum' style garbled text in the descriptions.
- − Some logic errors in the icons (multiple Earths/Moons and inconsistent ship icons).
- − The 'Translunar' icon is very abstract compared to the others.
Verdict: FLUX1.1 [pro] Ultra followed the complex multi-step prompt instructions much better than FLUX.1 Kontext, capturing the sequential nature of the infographic. Although FLUX.1 Kontext produced cleaner text for the main headers, FLUX1.1 [pro] Ultra is the preferred choice for its superior composition, adherence to the specific 'Steps 1-6' list, and overall professional infographic feel.
Explore each model
Black Forest Labs' ultra-high resolution image generation model, an enhanced version of FLUX1.1 [pro] optimized for premium quality output