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]
#54 of 62 in Text-to-Image
FLUX1.1 [pro] Ultra
#51 of 62 in Text-to-Image
Where the votes landed
FLUX.1 Kontext [dev]
0%
win rate
Ties
0%
FLUX1.1 [pro] Ultra
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 [dev]
- + Excellent adherence to lighting instructions with a clear soft window light from the left
- + Realistic texture on the wooden table and leather-bound book
- + Consistent reflections within the glass and on the bottom surface
- − The glass box lacks a front face, appearing more like a frame or open shelter than a 'cube'
- − The plant behind the glass is quite blurry, reducing the 'visible through' effect
FLUX1.1 [pro] Ultra
- + Perfect structural representation of a glass cube with visible edges and faces
- + High-quality text rendering on the book's spine
- + Clearly demonstrates the plant visible through the glass panels
- − The sphere is levitating rather than sitting on the surface, which may not be physically intuitive
- − The lighting is more diffused and less directed from the left compared to the other model
Verdict: FLUX1.1 [pro] Ultra followed the spatial prompt more accurately by generating a structure that truly looks like a closed glass cube, whereas FLUX.1 Kontext [dev] generated an open-faced frame. Although the sphere in FLUX1.1 [pro] Ultra is floating, it excels in detail and clarity, specifically the visibility of the plant through the glass and the text 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.”
AI Judge Analysis
FLUX.1 Kontext [dev]
- + Excellent skin texture and facial details
- + Accurate depiction of rain droplets and atmospheric haze
- + Strong composition with a centered, engaging subject
- − The subject is posing with the bike rather than 'repairing' it
- − The framing is very clean and centered, missing the 'imperfect framing' request
- − Background cars are static rather than showing motion blur
FLUX1.1 [pro] Ultra
- + Successfully handles the 'motion blur from passing cars' request
- + The subject's pose better reflects the 'repairing' aspect of the prompt
- + Captures the 'candid street photo' feel with more authentic urban movement
- − The bicycle frame geometry is slightly warped near the pedals
- − The rain effect is much less visible compared to Model A
- − The skin texture is slightly smoother and less detailed than Model A
Verdict: FLUX.1 Kontext [dev] produced a more aesthetically pleasing portrait with superior skin textures and rain physics, but it failed to include the requested motion blur. FLUX1.1 [pro] Ultra followed the complex technical requirements of the prompt more accurately, capturing a truly candid moment with motion-blurred traffic and a more natural 'repair' pose, making it the more faithful interpretation of the specific scene requirements.
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 [dev]
- + Excellent handling of the cinematic lighting and bokeh sparks.
- + High detail on the ornate engraving of the plate armor.
- + Clear skin textures including requested scars and dirt.
- − The hair lacks the specific 'braids with small beads' requested in the prompt.
- − The leather straps are barely visible in the composition.
FLUX1.1 [pro] Ultra
- − The image is a complete failure, resulting in a solid black frame.
- − Total lack of prompt adherence or visual information.
Verdict: FLUX.1 Kontext [dev] produced a high-quality, cinematic portrait that captures the atmosphere and most details of the prompt effectively. FLUX1.1 [pro] Ultra failed to generate a visible image, providing only a black square, making FLUX.1 Kontext [dev] the winner by default.
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 [dev]
- + Excellent high-resolution food photography that looks appetizing and professional.
- + Clean, modern grid layout that perfectly balances text and imagery.
- + Strong adherence to the 'bold sans-serif' requirement with high-impact typography.
- − Text consists of gibberish words and non-existent characters.
- − The food items depicted do not clearly align with the 'pizza' or 'mains' labels.
FLUX1.1 [pro] Ultra
- + Includes realistic pricing and structured menu content with correct category headers like 'Appetizers' and 'Mains'.
- + Successful presentation of the menu as a physical object with a realistic perspective mockup.
- + Good use of vibrant accents and icons for a casual dining feel.
- − The food photos look overly cluttered and repetitive, featuring mostly pizza despite other section labels.
- − Text rendering has several spelling errors like 'Pizzzans' and 'Appet Love'.
Verdict: FLUX.1 Kontext [dev] creates a more visually stunning and artistic layout with superior food photography, but the text is complete nonsense. FLUX1.1 [pro] Ultra provides a more functional menu design with better category adherence and realistic pricing, though the repetitive imagery and spelling errors hold it back. FLUX.1 Kontext [dev] is the likely winner for its professional graphic design aesthetic.
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 [dev]
- + Excellent typography rendering for the main title
- + Clean, professional-looking fire and coal assets
- − Failed to create an 'exploded' burger, showing a fully assembled one instead
- − Typographical error in 'LIMITED TIME ONLY' (spelled 'LNHLY')
FLUX1.1 [pro] Ultra
- + Successfully followed the 'exploded burger' and 'motion' prompt requirements
- + Perfect spelling for all text elements
- + Dynamic composition with flying ingredients adds to the sense of action
- − Text size for the secondary message is very small compared to the main title
- − Slightly less 'fiery/glowing' effect on the price text compared to the title
Verdict: FLUX1.1 [pro] Ultra is the clear winner as it successfully captured the core concept of an 'exploded' burger with suspended components, whereas FLUX.1 Kontext [dev] generated a standard assembled burger. Additionally, FLUX1.1 [pro] Ultra exhibited perfect spelling, while FLUX.1 Kontext [dev] had a significant typo in the secondary text.
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 [dev]
- + Excellent chalk texture and realistic handwriting aesthetic.
- + Centered composition on a clean chalkboard frame.
- − Numerous spelling errors like 'Mashroom' and 'Risoktso'.
- − The date text 'APRIL' is mangled and illegible.
FLUX1.1 [pro] Ultra
- + Accurately renders the date 'APRIL 30, 2026' in clear handwriting.
- + Better context with the cafe background visible in the reflection/sides.
- − Repeats words frequently like 'mushroomm', 'fresh fresh', and 'Cookies'.
- − The bottom half of the menu becomes cluttered with repetitive, nonsensical text strings.
Verdict: Both models struggled with the complex task of rendering lengthy handwritten menu text without repetition or spelling errors. FLUX.1 Kontext [dev] captured the best 'chalk' aesthetic and layout, but failed significantly on spelling, whereas FLUX1.1 [pro] Ultra managed the specific date correctly but suffered from severe text loops and repetition in the lower half of the board.
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 [dev]
- + Successfully followed the specific instruction of having the horse on top of the astronaut.
- + High facial detail and realistic skin texture on the human.
- − The 'riding' stance is a bit ambiguous, appearing more like the horse is floating directly behind and slightly above.
- − The background is quite empty and lacks the cinematic quality of the competitor.
FLUX1.1 [pro] Ultra
- + Superior cinematic composition with dynamic lighting and high-quality planet details.
- + Extremely high level of background detail including multiple space objects and atmosphere.
- − Failed the negative constraint/specific instruction; the astronaut is riding the horse, not the other way around.
- − The astronaut's anatomy and gear show minor clipping with the horse's back.
Verdict: This comparison highlights the difference between prompt adherence and visual spectacle. FLUX.1 Kontext [dev] is the winner because it successfully followed the complex 'horse on top' instruction which creates a surreal image, whereas FLUX1.1 [pro] Ultra defaulted to a standard (though beautiful) interpretation of an astronaut riding a horse.
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 [dev]
- + Excellent adherence to the composition prompt by placing the woman in the back seat.
- + Accurately represents the businessman's bored expression while looking at her phone.
- + High-quality fur texture and capybara facial expression.
- − The capybara only has one paw on the steering wheel instead of two.
- − The lighting on the capybara's head is slightly flat compared to the background city lights.
FLUX1.1 [pro] Ultra
- + Beautiful cinematic lighting and highly realistic city bokeh through the window.
- + Correctly places both paws on the steering wheel as requested in the prompt.
- + Crisp text rendering of the word 'TAXI' on the cap.
- − Failed the spatial part of the prompt by placing the passenger in the front passenger seat.
- − The passenger is looking at her phone with two hands on the dashboard/wheel area, which is ergonomically confusing.
Verdict: FLUX.1 Kontext [dev] followed the complex layout instructions much better, correctly placing the woman in the back seat to establish the 'taxi ride' dynamic. While FLUX1.1 [pro] Ultra produced a more aesthetically polished image with better lighting and 'paws on wheel' adherence, it ultimately failed the core compositional requirement of the prompt by putting the passenger in the front 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 [dev]
- + Excellent typography for the main title and event dates
- + Effective spooky thorn border and jack-o-lantern illustration
- + High contrast with a clean layout suitable for a digital invite
- − Text in the scroll banner is garbled and unreadable
- − Failed to incorporate the 'parchment' texture, opting for a flat black background
- − Location text is misspelled as 'The Argiiah's'
FLUX1.1 [pro] Ultra
- + Beautiful parchment scroll texture and lighting that fits the 'cinematic' prompt
- + Accurate rendering of the secondary scroll banner text and all event details
- + Highly intricate background featuring twisted trees and a moody sky
- − Included a redundant and slightly misspelled line of text below the banner
- − Main title text omitted the word 'Party'
- − Overall design is a bit crowded compared to Model A
Verdict: FLUX1.1 [pro] Ultra is the clear winner for its superior rendering of textures and complex textual instructions, though it did include a strange redundant text block. While FLUX.1 Kontext [dev] has a very strong graphic design style, its inability to spell the location or render the scroll text correctly makes it less functional as an invitation.
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 [dev]
- + Excellent text readability and bold typography
- + Very clean, minimalist aesthetic
- + Solid bold colors that pop against the background
- − The flag icon is stylized incorrectly as a geometric shape rather than the Japanese flag
- − Text textures are flat and lack the requested 3D cartoon depth
- − The sushi anatomy is slightly nonsensical with the nori wrapping
FLUX1.1 [pro] Ultra
- + High-quality miniature 3D rendered textures with realistic lighting
- + Correct depiction of the Japanese flag alongside legible text
- + Detailed sushi variety on a well-composed diorama base
- − Includes more garnish and elements than the 'minimal' request specified
- − Small bug artifact visible on the wooden plate
- − Text is slightly less prominent than the bold style requested
Verdict: FLUX1.1 [pro] Ultra is the clear winner for its superior 3D rendering quality, realistic PBR-style textures, and accurate flag icon, perfectly capturing the 'miniature diorama' request. FLUX.1 Kontext [dev] produced a much more simplistic 2D-looking graphic with an incorrect flag representation.
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 [dev]
- + Captures a sense of motion and playfulness
- + Excellent lighting and depth of field
- + Clean, high-resolution textures on the flowers and fur
- − Failed to include all four animal types requested
- − Includes two cats instead of a fox and a bunny
- − The 'tumble' looks more like a synchronized run
FLUX1.1 [pro] Ultra
- + Successfully included all four distinct animals: puppy, kitten, bunny, and fox kit
- + Beautifully rendered god rays and soft morning atmosphere
- + High detail in the fur and 'big expressive eyes' characteristic
- − Animals are sitting relatively still rather than 'playfully chasing' or 'tumbling'
- − The anatomy is slightly stylized/painterly rather than 'hyper-photorealistic'
Verdict: FLUX1.1 [pro] Ultra is the clear winner for prompt adherence, as it successfully managed to generate all four distinct animal species while FLUX.1 Kontext [dev] missed two of them. Although FLUX.1 Kontext [dev] captured better action and more realistic textures, FLUX1.1 [pro] Ultra better fulfilled the complex multi-subject requirement with a beautiful, illustrative quality.
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 [dev]
- + Excellent typography accuracy with the name and date
- + Clean minimalist vector style
- + Perfect adherence to the requested color palette
- − Missing the 'banner' element specified in the prompt
- − Steam effect is very basic and looks slightly detached
- − The cloche icon looks more like a cupcake or a crown
FLUX1.1 [pro] Ultra
- + Sophisticated vintage visual aesthetic
- + Included the banner element requested in the prompt
- + Superior shading and texture details
- − Misspelled 'Florian' as 'Framilian'
- − Less minimalist than Image A
- − The cloche looks a bit like a dome/building
Verdict: FLUX.1 Kontext [dev] followed the text instructions perfectly but failed to include the requested banner element and produced a somewhat generic icon. FLUX1.1 [pro] Ultra produced a much more professional and aesthetically pleasing 'vintage' logo with better texture, but it hallucinated the name 'Framilian' instead of 'Florian'. FLUX.1 Kontext [dev] is the winner for its superior text rendering and adherence to minimalist vector principles.
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 [dev]
- + Strongly adheres to the requested color palette
- + Good vector-style flat icons
- + Accurate spelling of 'Apollo' (mostly)
- − Text is highly garbled and messy throughout the bottom half
- − Layout is unorganized and hard to follow as a mission sequence
- − Poor font rendering makes it look like a placeholder
FLUX1.1 [pro] Ultra
- + Excellent layout that uses the lunar surface as a stylistic base
- + Strict adherence to the 6-step sequence including specific requested icons
- + High visual appeal and professional infographic composition
- − Text contains several gibberish phrases and typos in headers
- − Includes some orange tones that weren't in the requested NASA palette
Verdict: FLUX1.1 [pro] Ultra is the clear winner as it successfully creates a coherent, professional-looking infographic that follows the specific mission steps requested. While both models struggled with perfect text legibility, FLUX.1 Kontext [dev] produced a chaotic and disorganized layout with significantly worse text rendering compared to the structured approach of FLUX1.1 [pro] Ultra.
Explore each model
Black Forest Labs' ultra-high resolution image generation model, an enhanced version of FLUX1.1 [pro] optimized for premium quality output