Black Forest Labs' open-weights multimodal flow transformer for in-context image generation and editing, available for non-commercial use with character consistency and style transfer capabilities
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
FLUX.1 Kontext [dev]
16.5
arena score
#58 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 [dev]
0%
win rate
Ties
0%
FLUX1.1 [pro]
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 Kontext [dev]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.1 Kontext [dev]
- + Excellent adherence to the 'cube' geometry
- + Realistic reflections on the table and glass surfaces
- + Natural lighting depth from the window
- − The plant is somewhat behind the window frame rather than directly behind the cube
FLUX1.1 [pro]
- + Great material texture on the book cover
- + Clean, high-quality rendering of the glass and sphere
- + Strong lighting and focus contrast
- − The glass container is a tall rectangular prism rather than a cube
- − The sphere appears to be levitating inside the container without physics, which looks less grounded
Verdict: FLUX.1 Kontext [dev] followed the spatial instructions more accurately by providing a true cube, whereas FLUX1.1 [pro] generated a tall rectangular prism. FLUX.1 Kontext [dev] also achieved a more realistic sense of gravity and reflection, while FLUX1.1 [pro] had slightly better textures on the book.
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 [dev]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.1 Kontext [dev]
- + Stronger adherence to the rainy atmosphere with visible raindrops and puddles.
- + Excellent facial detail and natural skin texture.
- + Clean composition while still following the 'imperfect framing' requested by being off-center.
- − The man appears to be posing or standing with the bike rather than repairing it.
- − The bicycle is missing its seat, which is a structural inconsistency.
- − Cars in the background are stationary rather than having motion blur.
FLUX1.1 [pro]
- + Successfully captures some sense of the 'repairing' action by its stooped posture.
- + Better captures the cinematic lighting and deep reflections on the pavement.
- + Includes the requested bag and accessories that feel more like a candid street photo.
- − Serious anatomical and structural errors: the man has a third leg/foot near the ground.
- − The bicycle frame is broken/severed in the middle with floating parts.
- − The man's scale relative to the bicycle and background feels slightly off.
Verdict: FLUX.1 Kontext [dev] produces a much higher quality image with better skin textures and a more convincing rain effect, though it misses the 'repairing' action and has a missing bike seat. FLUX1.1 [pro] better captures the cinematic mood and 'candid' feel requested in the prompt, but it suffers from catastrophic AI artifacts including a floating extra foot and a broken bicycle frame. FLUX.1 Kontext [dev] is the winner due to its visual coherence and technical stability.
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 [dev]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.1 Kontext [dev]
- + Excellent depiction of ornate engraved plate armor with high structural clarity
- + Superior usage of warm lighting that feels consistent across the metallic surfaces
- + Clear rendering of leather straps and cloth underlayers
- − Hair lacks requested braids and beads
- − Skin texture appears slightly too smooth and airbrushed for a 'battle-worn' description
- − Framing is slightly more distant than a 'close portrait'
FLUX1.1 [pro]
- + Exceptional skin texture with realistic dirt, grime, and pores
- + Successfully included braids with small beads in the hair
- + Very intense, lifelike eyes that align well with the prompt
- − The 'bokeh sparks' look somewhat like floating digital artifacts or simple glowing dots
- − Engraving on armor is less distinct and more weathered than the 'ornate engraved' description suggests
- − Lighting is a bit cooler and more naturalistic rather than the strong warm torchlight requested
Verdict: FLUX1.1 [pro] provides a much more convincing 'battle-worn' appearance with gritty skin textures, scars, and the requested braids, though its armor detail is less refined. FLUX.1 Kontext [dev] excels at the hardware details like the ornate armor and dramatic lighting but fails to include the specific hair details and has a more stylized, digital character finish. FLUX1.1 [pro] is the winner for its superior realism and closer adherence to the character's physical description.
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 [dev]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.1 Kontext [dev]
- + Excellent high-resolution food photography
- + Clean minimalist layout with strong grid alignment
- + Bold, readable sans-serif headers
- − Nonsense filler text for body copy
- − Failed to include specific section titles like pizza and appetizers clearly
- − Text rendering includes graphic glitches
FLUX1.1 [pro]
- + Successfully included categorized sections for Appetizers and Pizza
- + Better alignment with the user's intent for a functional menu design
- + Professional presentation including a secondary mockup with cutlery
- − Food photos are very small and some look slightly distorted
- − Fine text is blurry and illegible
- − The grid layout of the photos is less consistent than Model A
Verdict: FLUX1.1 [pro] followed the prompt more effectively by creating specific sections for different food categories and including price points, making it feel like a real product. While FLUX.1 Kontext [dev] had much higher quality individual food images and a cleaner aesthetic, it failed the specific organizational requirements of the prompt and produced more text artifacts.
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 [dev]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.1 Kontext [dev]
- + Excellent text legibility and size
- + Strong color saturation consistent with a fiery theme
- + Accurate price and starburst integration
- − Failed to create an 'exploded' burger where components are separated
- − Typography has a minor spelling error in 'ONLY'
FLUX1.1 [pro]
- + Successfully captured a sense of motion with flying ingredients
- + High photorealistic detail on the burger textures
- + Includes almost all requested text elements
- − The burger is not truly 'exploded' as it is still mostly assembled
- − Text is small, cluttered, and repetitive
- − Missing the starburst for the price
Verdict: FLUX.1 Kontext [dev] produced a much more effective advertisement with bold, readable text and a clear price point, though it ignored the 'exploded' instruction. FLUX1.1 [pro] followed the motion instructions better by including flying debris, but the layout is poor with repeating titles and small, difficult-to-read text. FLUX.1 Kontext [dev] is the winner for its superior visual composition and commercial appeal.
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 [dev]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.1 Kontext [dev]
- + Excellent chalk texture and natural handwriting variation.
- + Strong adherence to the requested format and border framing.
- − Significant spelling errors including 'Mashroom', 'Risoktso', and 'Octpus'.
- − Repetitive text such as 'with with' and double '$28' markings.
FLUX1.1 [pro]
- + Much better atmospheric lighting and background context for a café setting.
- + Properly followed the 'elegant cursive' instruction for the title.
- + Higher legibility and cleaner handwriting style.
- − Failed the pricing logic with '$228' and separated the octopus item into two lines erroneously.
- − Misspelled 'Chipkies' and 'gluten' as 'giluten'.
Verdict: FLUX.1 Kontext [dev] captured the gritty texture of real chalk more effectively, but suffered from severe internal text repetition and garbled spelling of the menu items. FLUX1.1 [pro] produced a much more visually appealing image with elegant cursive, and while it also had minor spelling errors, it managed better overall coherence despite the price hallucination.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
FLUX.1 Kontext [dev]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.1 Kontext [dev]
- + Successfully followed the difficult spatial instruction of horse 'on top' of the astronaut.
- + Clean, modern cinematic aesthetic with sharp facial details through the visor.
- + Realistic lighting on the spacesuit fabric.
- − The horse appears to be floating behind/above rather than physically riding the astronaut.
- − The composition is a bit static and literal.
FLUX1.1 [pro]
- + Dynamic, high-energy composition with beautiful lighting and color palettes.
- + Excellent textures on the horse's mane and the rocky landscape.
- − Completely failed the negative constraint/spatial instruction of 'horse on top'.
- − The anatomy of the horse's front legs is distorted and nonsensical.
Verdict: FLUX.1 Kontext [dev] is the winner because it successfully interpreted the 'horse on top' instruction, which was the core challenge of the prompt. While FLUX 1.1 [pro] produced a more visually stunning and vibrant image, it reverted to the standard 'astronaut on horse' cliché, failing the specific semantic requirement.
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 [dev]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.1 Kontext [dev]
- + Excellent photorealistic texture on the capybara's fur and the jacket fabric.
- + Accurately places the passenger in the back seat and the driver in the front seat.
- + High level of detail on the taxi dash, steering wheel, and door frame.
- − Only one paw is on the steering wheel, despite the prompt asking for both.
FLUX1.1 [pro]
- + Successfully renders a cinematic bokeh effect for the city lights in the background.
- + Clear 'TAXI' text on the cap's brim.
- − The passenger appears to be in the front seat next to the driver instead of the back seat.
- − The capybara's anatomy is confusing, with excessive fur and paws that aren't clearly on a steering wheel.
- − The interior layout lacks the structure of a real car, appearing more like a studio set.
Verdict: FLUX.1 Kontext [dev] is the clear winner as it correctly interprets the spatial arrangement of the characters, placing the businesswoman in the back seat as requested. While FLUX1.1 [pro] has nice lighting, it fails the composition by placing both characters in the front and losing the structure of the car interior.
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 [dev]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.1 Kontext [dev]
- + Excellent large title text readability
- + Well-defined thorn/branch border structure
- + Correct date and time formatting
- − Banner text is nonsensical and messy
- − Location name is misspelled as 'The Argiiah's'
- − Lacks the 'moody night sky' element requested
FLUX1.1 [pro]
- + Beautiful cinematic lighting and atmosphere with the moon and sky
- + Successfully includes every requested element including the parchment effect
- + Accurate spelling of 'The Arches, NYC'
- − Redundant text repeated multiple times (Date/Time/Location)
- − Center title text is smaller and slightly repetitive ('Halloween Party Party')
- − Parchment layout is more vertical than the requested square format
Verdict: FLUX1.1 [pro] created a much more visually appealing and atmospheric invitation that captured the gothic mood perfectly, though it struggled with text layout by repeating the event details. FLUX.1 Kontext [dev] had better text legible for the title, but failed on the spelling of the location and missed the atmospheric sky elements.
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 [dev]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.1 Kontext [dev]
- + Excellent typography with clean, bold text and perfect placement
- + Very clean minimalist aesthetic that matches the requested 'soft refined textures'
- + Accurate 45-degree isometric perspective
- − The flag icon is stylized into a graphic shape and does not look like a traditional Japanese flag
- − The sushi design is oversimplified compared to the '3D cartoon scene' request
FLUX1.1 [pro]
- + Beautiful, complex miniature diorama with varied sushi types
- + Excellent soft lighting and material rendering on the food items
- + Follows the 'miniature 3D cartoon scene' prompt more creatively with a full set
- − Fails to include the requested flag icon at the top
- − The text 'SUSHI' is relatively small and lacks the 'bold' presence requested
- − Includes more than 'minimal garnish' with several extra side items
Verdict: FLUX.1 Kontext [dev] followed the text and layout instructions more precisely, including the flag icon and bold typography, though the sushi itself is quite plain. FLUX1.1 [pro] created a much more visually appealing and detailed 3D miniature scene with superior lighting, but missed the flag icon and sacrificed text prominence. FLUX1.1 [pro] is likely preferred for its artistic quality despite the minor prompt omissions.
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 [dev]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.1 Kontext [dev]
- + Captures a dynamic sense of movement with the animals running.
- + Excellent butterfly anatomical detail and varied flower species.
- − Failed to include the baby bunny and the red fox kit, substituting them with extra kittens.
- − Slightly less 'expressive' eyes compared to the other model.
FLUX1.1 [pro]
- + Captured the baby bunny successfully as requested.
- + Beautiful backlit fur texture and very expressive, large eyes.
- + Warmer cinematic lighting that better matches the golden sunrise prompt.
- − Failed to include the red fox kit.
- − The butterflies are less detailed and appear more like glowing yellow shapes.
Verdict: FLUX1.1 [pro] is the winner as it adhered closer to the prompt by including the baby bunny, whereas FLUX.1 Kontext [dev] only generated a puppy and three cats. FLUX1.1 [pro] also delivered superior lighting and fur texture, creating a more 'magical' atmosphere even though both models failed to include the red fox kit.
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 [dev]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.1 Kontext [dev]
- + Perfect text rendering of the requested brand name
- + Clean minimalist vector style
- + Accurate color palette usage
- − Missed the 'banner' element for the date
- − Iconography is slightly too thick for a refined vintage look
FLUX1.1 [pro]
- + Excellent vintage aesthetic with elegant banner and filigree
- + Higher level of detail in the cloche and steam illustration
- + Better adherence to the 'emblem' style request
- − Significant spelling error in the main brand name
- − Less 'minimalist' than the prompt requested
Verdict: FLUX.1 Kontext [dev] followed the text requirements perfectly, producing a clean and usable logo, although it missed the banner element. FLUX1.1 [pro] created a much more visually appealing and appropriately 'vintage' emblem, but failed the basic task of spelling the restaurant name correctly. FLUX.1 Kontext [dev] is preferred for its accuracy and professional clarity.
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 [dev]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.1 Kontext [dev]
- + Successfully captures the requested navy, white, and muted red NASA-inspired palette.
- + Follows the flat-vector style with crisp line work for the icons.
- − Major spelling errors in the main headers ('APOLO' and 'DESCNT').
- − Iconography is abstract and messy, failing to clearly represent the specific mission steps requested.
- − The layout is cluttered and the text is largely garbled and illegible.
FLUX1.1 [pro]
- + Follows the infographic layout much more effectively with clear callouts and a central graphic.
- + Superior spelling for the main title 'APOLLO 11'.
- + Clean, modern composition that feels like a professional poster design.
- − Failed to follow the requested 6-step logical sequence, including duplicate step numbers (two 6s, two 2s).
- − The central Saturn V rocket is somewhat stylized to look like a toy/cartoon rather than a crisp vector icon.
Verdict: FLUX1.1 [pro] is the clear winner as it produces a coherent, professional-looking infographic that actually resembles a poster. While it struggled with the specific numbering of the six steps, FLUX.1 Kontext [dev] failed more significantly with major typos in primary headings and an unorganized layout with illegible icons.
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