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 17 shared challenges, with an AI judge weighing in on each.
FLUX.1 Kontext [max]
#23 of 62 in Text-to-Image
FLUX.2 [pro]
#8 of 62 in Text-to-Image
Where the votes landed
FLUX.1 Kontext [max]
0%
win rate
Ties
0%
FLUX.2 [pro]
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 handling of caustics and light refraction through the glass
- + Highly realistic textures on the book and wooden table
- + Accurate fulfillment of all spatial requirements including lighting direction
- − The sphere has a textured, glittery finish rather than being a smooth sphere
FLUX.2 [pro]
- + Perfectly smooth blue sphere that feels more classic
- + Clean, minimalist composition
- + Accurate placement of all elements according to the prompt
- − The plant is completely blurred out, making it hard to see 'through the glass' as requested
- − The lighting and shadows are flatter compared to Model A
Verdict: Both models followed the complex spatial prompt perfectly. FLUX.1 Kontext [max] is the winner because it handled the physics of light much better, showing realistic refractions and caustics on the table, and the plant is clearly visible through the glass as requested, whereas FLUX.2 [pro] blurred the background excessively.
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 streaks and splashing on the ground
- + Realistic skin texture and age details on the hands and face
- + Superior framing that places the viewer at eye-level with the subject
- − The bicycle chain and pedal mechanics are slightly distorted and physically unrealistic
- − The rain effect appears somewhat layered over the subject rather than fully integrated
FLUX.2 [pro]
- + Stronger adherence to the 'motion blur from passing cars' prompt
- + Beautiful ripple effects in the puddles on the ground
- + More natural interaction between the man and the bicycle components
- − The rain falling through the air is very faint/barely visible compared to the first image
- − The composition feels a bit more staged than 'candid'
Verdict: FLUX.1 Kontext [max] captures a more atmospheric and cinematic rain effect with incredible facial and hand detail, making it feel very high-end. FLUX.2 [pro] better handles the specific motion blur requirements and provides a more coherent interaction with the bicycle, though its rain effects are significantly subtler. FLUX.1 Kontext [max] is the winner for its superior visual quality and 'no stylization' realism.
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 metallic texture and intricate engraving detail
- + Lifelike eye iris texture and realistic skin pores
- + High-quality volumetric lighting and depth of field
- − Missed the request for small beads in the braids
- − The skin tone looks slightly oversaturated/orange due to the lighting
FLUX.2 [pro]
- + Perfectly captured the small beads in the hair braids
- + Superior battle-worn details with more prominent scars and dirt
- + Highly detailed leather straps and cloth hood texture
- − The sparks look a bit more artificial and linear than Model A
- − Facial hair looks slightly less distinct compared to the rest of the high-res details
Verdict: While FLUX.1 Kontext [max] produced a more sophisticated lighting setup and beautiful armor engravings, FLUX.2 [pro] followed the prompt more meticulously, specifically including the beads in the braids and more significant battle-worn details. FLUX.2 [pro] captures the 'paladin' aesthetic with a more rugged, accurate interpretation of the requested textures.
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 photo quality with realistic lighting and appetizing food textures.
- + Maintains a high level of minimalist aesthetic consistent with modern casual dining.
- + Clean, professional white space usage and balanced margins.
- − Text rendering is largely illegible gibberish.
- − Fails to clearly define the requested sections like appetizers and mains, focusing mostly on pizza.
FLUX.2 [pro]
- + Successfully includes the requested sections for Appetizers, Pizza, and 'Mains' (misspelled as MINS).
- + Much better text adherence with recognizable dish names and prices.
- + Follows the 'grid' layout instruction more strictly than the competitor.
- − Visual quality of food photos is lower with some AI artifacts and inconsistent lighting.
- − Minor spelling errors in headers like 'MINS' and 'Maghrita'.
- − Layout feels slightly more cluttered and template-like compared to the artistic feel of Model A.
Verdict: FLUX.2 [pro] is the superior choice for this specific task because it accurately followed the structural instructions to include specific sections and readable text. While FLUX.1 Kontext produced more beautiful food photography, it failed to deliver a functional menu layout, whereas FLUX.2 [pro] created a usable design with clear pricing and categorization.
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 photorealistic texture on the meat patty and buns
- + Strong fiery atmosphere with embers and ground-level lava effects
- + Accurate text rendering of all requested phrases
- − The burger is largely assembled rather than 'exploded' with suspended components
- − Missing the starburst element for the price
- − The side-floating buns look more like fruit or rolls than a deconstructed burger
FLUX.2 [pro]
- + Perfect adherence to the 'exploded' request with clear vertical suspension of all layers
- + Incorporates the fiery glowing effect on the text as requested
- + Successfully includes the starburst shape for the price point
- − Text on 'MAGIC BURGER' is slightly less crisp than Model A
- − Large tomato slice appears a bit flat compared to the other high-detail ingredients
Verdict: While FLUX.1 Kontext [max] has slightly better photorealistic textures for the food, it fails to deliver the 'exploded' composition and the starburst element. FLUX.2 [pro] followed the prompt instructions much more accurately, creating a dynamic vertical deconstruction with the correct graphic elements and a superior fiery text effect.
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 alignment
- + Accurately completed the partial prompt for 'Brown Butter Chocolate Chip Cookies'
- + Realistic chalkboard smudge and erasing artifacts
- − The handwriting style is more of a print-script than the requested 'elegant cursive' for the title
- − The chalk lines look a bit too clean/solid, lacking some granular texture
FLUX.2 [pro]
- + Perfect adherence to the 'elegant cursive' requirement for the title and text
- + Exceptional chalk texture with realistic dusty residue and varying opacity
- + Beautifully artistic composition and atmospheric lighting
- − Slightly less legible than Model A due to the thinner cursive strokes
- − The word 'Risotto' looks slightly detached from its line
Verdict: FLUX.2 [pro] is the clear winner as it perfectly captured the 'elegant cursive' requirement and the granular texture of actual chalk, whereas FLUX.1 Kontext [max] used a more standard print handwriting. FLUX.2 [pro] also managed the 'natural variations' and atmospheric café lighting much more convincingly.
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 photographic realism and lighting
- + Clean, cinematic composition with a clear focal point
- + High anatomical accuracy for the horse and suit details
- − Completely failed the negative constraint; the astronaut is riding the horse
FLUX.2 [pro]
- + Followed the specific spatial instruction for the horse to be on top
- + Captures the requested surreal atmosphere well
- + Intricate galactic background with vibrant colors
- − Anatomical anomalies where the horse's legs merge with the astronaut
- − Lower realism compared to Model A
- − Composition is a bit cluttered with multiple horses/half-horses
Verdict: While FLUX.1 Kontext produced a much more visually polished and 'cinematic' image, it completely ignored the core instructional constraint of having the horse on top of the astronaut. FLUX.2 [pro] successfully interpreted the surreal prompt and followed the spatial instructions, despite having some structural merging issues between the subjects.
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]
- + Excellent fur texture rendering and realistic cap design.
- + Better lighting and shallow depth of field that creates a cinematic night atmosphere.
- − Perspective choice makes the passenger look like she is in the front seat next to the driver.
- − Only one paw is clearly resting on the steering wheel.
FLUX.2 [pro]
- + Perfect composition with the passenger clearly in the back seat as requested.
- + Highly detailed interior featuring taxi-specific gadgets like the meter and rain on the window.
- + Correctly depicts both paws on the steering wheel.
- − Anthropomorphic hands/gloves on the capybara are slightly uncanny.
- − Capybara's head shape is slightly elongated and less natural than the other model.
Verdict: FLUX.2 [pro] followed the prompt more accurately by placing the passenger in the back seat and showing both paws on the wheel, while also including rich interior details like the taxi meter. FLUX.1 Kontext [max] produced a more aesthetically pleasing close-up but failed the spatial requirement of having the businesswoman in the back seat.
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 typographic consistency with high-quality gothic fonts
- + Intricate web and thorn border that perfectly fits the theme
- + Moody, dark atmospheric lighting around the jack-o-lantern
- − Redundant text at the bottom repeating the location name twice
- − Misinterpreted the date format requested by using commas instead of periods
- − Text placement feels slightly crowded at the bottom
FLUX.2 [pro]
- + Perfect adherence to specific text and date formatting
- + High-quality central jack-o-lantern with realistic textures and fog effect
- + Clearer hierarchy of information and better use of negative space
- − The parchment texture is less 'dark and aged' compared to the first image
- − The border, while elegant, is less 'spooky' than the thorn-heavy version in the competitor's image
Verdict: FLUX.2 [pro] is the winner due to its superior adherence to the specific text and formatting requested, including correctly using periods in the date and avoiding the redundant text found in FLUX.1 Kontext [max]. While FLUX.1 Kontext [max] has a more intricate border and darker aesthetic, its failure to follow the character-for-character text instructions makes it less useful as a final invitation.
Bald man challenge
Image Editing“Give the person a full, thick head of natural hair with realistic texture, density, and a natural hairline. Preserve facial features and lighting.”
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent preservation of the original facial features and expression.
- + The hair texture and lighting match the environment perfectly.
- + The hairline integration is seamless with the skin.
- − The hair color is slightly darker than the original beard color, creating a minor mismatch.
FLUX.2 [pro]
- + Successfully adds a full head of hair with realistic volume.
- + Maintains the original background and clothing elements.
- − Significantly alters the facial structure, making the person look like a different individual.
- − The hair texture looks a bit messy/digitally smudged on the crown.
- − The glasses and eye area were noticeably changed from the source image.
Verdict: FLUX.1 Kontext [max] is the clear winner as it successfully adds the requested hair while perfectly preserving the identity, facial features, and lighting of the man in the source image. In contrast, FLUX.2 [pro] changes the man's facial structure and eyes too much, failing the 'preserve facial features' part of the instruction.
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 typography with a friendly, cartoonish font choice
- + Soft, clay-like textures that perfectly match the 'cartoon scene' request
- + Logical placement of chopsticks and condiments
- − Missed the small flag icon request
- − The sushi rice texture looks a bit like bubbles rather than grains
FLUX.2 [pro]
- + Successfully included all elements, including the small flag icon
- + Strict adherence to the 45-degree isometric perspective
- + Clean, professional graphic design aesthetic for the text
- − The base diorama texture is very flat and lacks the 'soft refined' feel of the sushi
- − The wasabi is placed awkwardly off the plate on the base edge
Verdict: Both models followed the prompt well, but FLUX.2 [pro] followed the instructions more comprehensively by including the requested flag icon and adhering more strictly to an isometric angle. FLUX.1 Kontext [max] produced a more appealing 3D render with better lighting and material textures, but missed a specific prompt element.
Over-the-top cartoon caricature
Editing“Create a caricature of me and my job. Make it exaggerated and humorous, incorporating my profession as a tv show anchor and my love for dogs and hockey.”
AI Judge Analysis
FLUX.1 Kontext [max]
- + Excellent preservation of the source subject's denim shirt and hair color
- + High caricature quality with exaggerated proportions while maintaining facial likeness
- + Creative inclusion of a dog in professional-themed gear
- − The hockey stick is poorly integrated and cut off at the top
- − The shirt features a strange extra hand/finger artifact near the microphone
FLUX.2 [pro]
- + Features a highly detailed and cohesive TV studio set design
- + Better integration of the hockey theme with sticks, pucks, and a rink graphic
- + Includes multiple dogs as part of the studio panel, enhancing the humor
- − Loss of likeness to the source image, particularly the hair style and eye color
- − Subject is wearing a blazer instead of the iconic denim shirt from the source
Verdict: Both models successfully interpreted the prompt into a caricature style. FLUX.1 Kontext [max] did a significantly better job at preserving the person's identity and specific clothing from the source image, whereas FLUX.2 [pro] created a more elaborate and polished scene but failed to maintain the visual characteristics of the original subject.
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 depiction of warm golden light and god rays
- + Includes all four requested animals clearly
- + Vibrant and saturated color palette that feels very joyful
- − The rabbit's face looks slightly uncanny and less realistic
- − Butterflies are a bit generic and glowy rather than detailed insects
FLUX.2 [pro]
- + More realistic fur textures and animal anatomy
- + Superior interaction between animals, such as the kitten reaching out
- + High detail in the butterflies and foreground grass with dew sparkles
- − Lighting is a bit more muted compared to the prompt's golden sunrise request
- − The puppy's expression is slightly less expressive than Model A
Verdict: Both models followed the prompt exceptionally well, but FLUX.2 [pro] produced a more sophisticated and realistic scene with better physical interactions between the animals. While FLUX.1 Kontext [max] captured the 'god rays' and 'golden light' more intensely, FLUX.2 [pro] exhibited higher technical quality in the fur rendering and naturalness of the subjects.
Studio Ghibli Anime Style
Editing“Transform this photo into a Studio Ghibli–inspired illustration. Use soft pastel colors, hand-painted textures, gentle lighting, dreamy backgrounds, and a warm, nostalgic mood”
AI Judge Analysis
FLUX.1 Kontext [max]
- + Captures the Studio Ghibli character design perfectly with rounded faces and expressive, watery eyes.
- + Maintains excellent color vibrancy while still feeling like a hand-painted illustration.
- + Preserves the exact poses and facial expressions (especially the man's pursed lips) from the source image.
- − The background is slightly less detailed than Model B, opting for a flatter, more washed-out look.
FLUX.2 [pro]
- + Includes beautiful environmental details in the background consistent with Ghibli cityscapes, like signs and balconies.
- + Successfully applies a high-quality watercolor texture across the entire image.
- + Achieves a very warm, nostalgic mood with a soft vignette and muted palette.
- − The man's facial expression is slightly lost, appearing more neutral than the 'distracted' look in the source.
- − The character linework is a bit thinner and less iconic to the specific Ghibli style compared to Model A.
Verdict: Both models performed exceptionally well, perfectly preserving the composition and subject matter of the 'Distracted Boyfriend' meme. FLUX.1 Kontext [max] captures the Ghibli character aesthetic more accurately, particularly in the eyes and facial expressions, whereas FLUX.2 [pro] excels at the environmental art and texture of a Ghibli background.
Golden Hour Stroll
Image Editing“Add dynamic motion to this photo: make hair blow in the wind, add leaves flying, energetic and lively feel.”
AI Judge Analysis
FLUX.1 Kontext [max]
- + Successfully adds wind-blown hair and small flying leaves.
- + Includes an additional pose change with the left hand to interact with the dog.
- + Preserves the overall lighting and texture of the original scene.
- − The leash has become detached and floats in a loop.
- − The hand added over the dog is anatomically awkward.
FLUX.2 [pro]
- + Stronger adherence to the 'windy' prompt with more dramatic hair movement.
- + Higher volume of flying leaves creates a greater sense of motion.
- + Better preserves the original structural integrity of the subjects and the leash.
- − Some leaves in the foreground are slightly blurry/out of focus, which might be distracting.
- − The hair flow looks slightly more artificial compared to Model A.
Verdict: FLUX.2 [pro] followed the edit instructions more effectively by adding significantly more leaves and creating a more dramatic wind effect on the hair, while keeping the person and dog intact. FLUX.1 Kontext [max] introduced anatomical errors and broken geometry in the leash while trying to add more motion. FLUX.2 [pro] is the winner for providing a more coherent and visually impactful edit of the source image.
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 style that fits the vintage aesthetic.
- + Beautifully textured, hand-drawn feel that looks like a linocut or woodblock print.
- + Balanced composition with high contrast and readability.
- − The accent on 'CAFFÊ' is an circumflex rather than the Italian grave accent 'CAFFÈ' requested.
FLUX.2 [pro]
- + Correct Italian accentuation on 'CAFFÈ'.
- + Clean vector-style execution with subtle paper texture background.
- + Accurate interpretation of all prompt elements including the circular layout.
- − The banner is very small and tucked behind the cloche, making it less prominent.
- − The steam lines look a bit more digital/modern compared to the vintage request.
Verdict: Both models followed the prompt exceptionally well. FLUX.1 Kontext [max] has a superior artistic style that feels authentically 'vintage' due to the textured ink effect, though it missed the specific Italian accent mark. FLUX.2 [pro] produced a cleaner, more correct logo in terms of grammar and vector clarity, but it feels slightly more generic. FLUX.1 Kontext [max] is the winner for its more evocative and professional design aesthetic.
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 typography for main titles and names
- + Clean, high-quality vector-style character silhouettes
- + Good usage of the requested color palette
- − Confusing infographic flow with steps and labels not matching icons
- − Missing 'Launch' and 'Earth Orbit' textual labels
- − Rocket design is generic and doesn't resemble a Saturn V
FLUX.2 [pro]
- + Strict adherence to the 6-step logical flow requested in the prompt
- + Clean flat-vector style with consistent iconography for orbits and arcs
- + Excellent representation of the Saturn V and Lunar Module designs
- − Gibberish placeholder text in the sub-descriptions
- − Crew silhouettes at the top are very small compared to the rest of the image
Verdict: FLUX.2 [pro] is the superior infographic, as it successfully creates a logical, sequential flow covering all the requested mission steps with accurate icons for each. While FLUX.1 Kontext [max] has cleaner text rendering, its layout is geographically confusing and fails to follow the step-by-step instructions provided.
Explore each model
Black Forest Labs' state-of-the-art image generation model with maximum quality and speed, supporting text-to-image and multi-reference image editing with up to 4MP output