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]
#58 of 62 in Text-to-Image
FLUX.1 [schnell]
#48 of 62 in Text-to-Image
Where the votes landed
FLUX.1 Kontext [dev]
0%
win rate
Ties
0%
FLUX.1 [schnell]
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 spatial relationships mentioned in the prompt
- + High-quality textures, especially the paper edges of the book and the wood grain
- + Natural lighting and reflections on the glass and sphere
- − The glass cube looks more like a frame or open box due to the lack of visible front glass face
FLUX.1 [schnell]
- + Successfully renders a solid glass cube with realistic refractive qualities
- + Good lighting that matches the requested direction
- − Included an extra blue sphere on top of the book not requested in the prompt
- − The sphere inside the cube appears to be floating rather than resting on the bottom
Verdict: FLUX.1 Kontext [dev] followed the prompt more accurately, placing all objects exactly where requested. FLUX.1 [schnell] failed on prompt adherence by adding an extra blue sphere on top of the book and making the internal sphere float, which was not specified.
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 depiction of rain with visible streaks in the air.
- + Beautifully rendered wet pavement with clear, colorful reflections.
- + Accurate and sharp facial details for the main subject.
- − The subject is not 'repairing' the bike; he is simply sitting on it.
- − The cars in the background are static and lack the requested motion blur.
- − The bike's frame geometry is slightly warped near the pedals.
FLUX.1 [schnell]
- + Successfully captures the subject in an active 'repairing' pose.
- + Strong background composition with realistic Japanese street signage.
- + Good depth of field and natural lighting integration.
- − The man's right hand and the bicycle handlebars have significant anatomical and structural clipping issues.
- − Fails to show visible 'light rain' streaks as requested in the prompt.
- − The 'motion blur from passing cars' is minimal to non-existent.
Verdict: FLUX.1 Kontext [dev] produced a far more beautiful and atmospheric image with convincing rain effects and reflections, though it failed the specific action of 'repairing'. FLUX.1 [schnell] followed the repairing intent better but suffered from significant mangling of the hands and bicycle handlebars, making it a weaker technical output. FLUX.1 Kontext [dev] is preferred for its superior visual quality and realism, despite the minor prompt adherence issues regarding the specific activity.
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 depiction of ornate engraved plate armor with highly detailed metalwork
- + Clear atmospheric lighting with realistic bokeh sparks in the background
- + Strong composition that follows the 'close portrait' instruction while showing the gear
- − The hair lacks the specific 'braid with small beads' requested in the prompt
- − The skin texture appears slightly smoother and less 'battle-worn' than Model B
FLUX.1 [schnell]
- + Highly successful interpretation of the 'braided hair with beads' requirement
- + Extremely detailed skin texture showing pores, scars, and fine wrinkles
- + Intense, lifelike eye detail and dramatic lighting contrast
- − The armor is mostly cropped out, failing to showcase the 'ornate engraved plate' as requested
- − The tight cropping loses the impact of the 'paladin' archetype, appearing more like a generic warrior
Verdict: FLUX.1 Kontext [dev] provides a superior overall composition that captures the 'paladin' aesthetic and the engraved armor beautifully, though it misses the specific hair braids. FLUX.1 [schnell] captures the character's facial details and hair instructions more accurately but fails to include the requested armor and leather textures in the frame due to an overly tight crop.
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]
- + High-resolution, vibrant food photography with complex textures.
- + Strong bold sans-serif typography that matches the 'modern' aesthetic request.
- + Excellent use of the full frame with a balanced, alternating grid layout.
- − The text is largely nonsensical and 'Appetizers' is misspelled as 'APPETIZRS'.
- − Does not follow the traditional layout of a functional menu, feeling more like a magazine spread.
FLUX.1 [schnell]
- + More realistic representation of an actual menu page with white space.
- + Clearly defined sections for Pizza and Mains as requested in the prompt.
- + Professional column-based layout suitable for a casual dining establishment.
- − Graphic quality of the food photos is lower and less appetizing than Model A.
- − Text rendering becomes illegible and messy in the body copy paragraphs.
- − Composition is centered and safe, lacking the high-end design feel of Model A.
Verdict: FLUX.1 [schnell] followed the prompt more literally by creating a functional page layout with distinct sections for pizza and mains, whereas FLUX.1 Kontext [dev] focused on a high-impact visual design. However, FLUX.1 Kontext [dev] is the winner because its image quality is significantly higher, featuring vibrant, professional food photography that is essential for a restaurant menu context.
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 with clean, readable text
- + Photorealistic burger rendering with sharp details
- + Vibrant, high-contrast lighting that fits the fiery theme
- − Failed the 'exploded' instruction as the burger is assembled
- − The secondary text has a minor spelling artifact ('LNHLY' instead of 'ONLY')
FLUX.1 [schnell]
- + Successfully captured the 'exploded' and 'mid-air' motion requested in the prompt
- + Dynamic composition with many floating elements
- + Good integration of glowing effects and embers
- − Significant text errors including a missing 'M' in 'AGIC BURGER' and a redundant price starburst
- − Lower visual clarity on the floating food bits which look more like croutons than burger ingredients
Verdict: FLUX.1 Kontext [dev] produced a much higher quality, professional-looking advertisement with superior text rendering, though it ignored the instruction for an exploded burger. FLUX.1 [schnell] followed the structural layout of the prompt better but failed significantly on text accuracy and overall image polish. FLUX.1 Kontext [dev] is the preferred choice for a usable ad despite the lack of deconstructed components.
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 on the 'TODAY SPECIALS' text
- + More legible text overall compared to the competitor
- + High quality framing and realistic wood grain on the chalkboard
- − Several spelling errors including 'Risoktso' and 'Octpus'
- − Muddled the date formatting significantly
- − Failed to use elegant cursive for the title as requested
FLUX.1 [schnell]
- + Successfully captured a more diverse café background environment
- + Good spacing between lines of text
- − Severe spelling errors and nonsensical words like 'Mushmnctiomn' and 'Catetectalialion'
- − Text lacks the authentic dusty chalk texture requested
- − Failed significantly on the specific prompt items and prices
Verdict: FLUX.1 Kontext [dev] is the clear winner as it produced a much more realistic chalkboard with higher legibility, whereas FLUX.1 [schnell] devolved into nonsensical gibberish for most of the menu items. While both models struggled with certain aspects of the prompt like specific dates and cursive headers, FLUX.1 Kontext [dev] maintained a consistent style that felt more like a physical object.
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]
- + Excellent anatomical detail on the astronaut and horse
- + Clean, high-resolution rendering with a cinematic feel
- + Accurately places the horse behind/on top of the astronaut as requested
- − The composition is a bit static and less surreal than requested
- − The horse's placement feels more like it is standing behind him rather than riding him
FLUX.1 [schnell]
- + Stronger adherence to the 'surreal' aspect of the prompt
- + More dynamic lighting and warm cinematic color palette
- + Creative interpretation of the horse actually riding the astronaut's equipment
- − The horse has two heads which appears to be a generation artifact
- − The composition is a bit muddled, making it difficult to discern the astronaut's orientation
Verdict: While FLUX.1 Kontext [dev] produced a much cleaner and higher-quality image with better anatomical accuracy, FLUX.1 [schnell] captured the surreal 'horse riding human' concept more effectively. However, the severe anatomical glitch of the two-headed horse in the FLUX.1 [schnell] output makes FLUX.1 Kontext [dev] the better overall image despite its safer interpretation of the prompt.
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]
- + The lighting on the capybara's fur and the taxi interior is highly realistic for a night scene.
- + The businesswoman's expression perfectly matches the 'bored' and 'normal' requirement.
- + The capybara's jacket and hat look authentic and well-fitted.
- − Only one paw is on the steering wheel, failing the 'both front paws' instruction.
- − The capybara looks a bit more like a groundhog or marmot due to the facial proportions.
FLUX.1 [schnell]
- + Successfully captured the 'Taxi' text on the hat clearly.
- + The composition provides a wider view of the street lights and taxi exterior.
- + The capybara's facial structure is more recognizable as a capybara.
- − The businesswoman looks slightly cross-eyed and her hands holding the phone are poorly rendered.
- − Fails the prompt to have 'both front paws on the steering wheel'.
- − The capybara's body and fur look somewhat more artificial and less integrated with the jacket.
Verdict: Both models failed to place both paws on the steering wheel, but FLUX.1 Kontext [dev] produced a much higher quality image with superior lighting and realistic human features. FLUX.1 [schnell] had noticeable artifacts in the woman's face and hands, making it the weaker choice despite the clear 'TAXI' text on the hat.
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]
- + Strong prompt adherence regarding the border of webs and thorns.
- + Accurate rendering of the jack-o-lantern and surrounding bats.
- + Clear and bold main title text.
- − The text inside the scroll banner is highly garbled and unreadable.
- − The location name 'The Arches' is misspelled as 'The Argiiah's'.
FLUX.1 [schnell]
- + Beautiful gothic aesthetic with atmospheric moody lighting and a glowing moon.
- + Layout feels more balanced with the use of graphic banners.
- + Better interpretation of the 'parchment' texture and twisted trees.
- − Repetitive and confusing text in the event details section.
- − Major spelling errors in several text areas, particularly the banners and time field.
- − The date/time information is duplicated and poorly formatted.
Verdict: Both models struggled significantly with the complex text requirements of the invitation. FLUX.1 Kontext [dev] followed the border and primary layout instructions more closely but failed to spell the specific location correctly, whereas FLUX.1 [schnell] produced a more atmospheric and visually appealing gothic illustration but failed to organize the data into a coherent, readable 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 typography with bold, clear text as requested
- + Clean, soft cartoonish textures that match the miniature style
- + Great use of a diorama base with simple, appealing geometry
- − The flag icon is abstract and does not represent the Japanese flag
- − The sushi anatomy is slightly unusual, appearing like a hybrid between nigiri and gunkan
FLUX.1 [schnell]
- + Perfect rendition of the Japanese flag icon
- + Higher detail in textures, particularly the salmon and rice grains
- + Follows the isometric diorama perspective very accurately
- − Failed to include the word 'SUSHI' in the text
- − The 'JAPAN' text has low contrast against the background
- − The layout feels slightly sparse with a large amount of empty space
Verdict: FLUX.1 Kontext [dev] followed the text requirements more completely, including both 'JAPAN' and 'SUSHI' in bold, clear fonts, though it failed on the specific flag icon. FLUX.1 [schnell] produced a more realistic and traditionally 'isometric' miniature with better individual textures, but missed half of the requested text and had poor text visibility.
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]
- + Excellent sense of motion and playfulness
- + High quality textures on the puppy
- + Clean background lighting
- − Failed to include a rabbit and a fox kit
- − Included three animals instead of the requested four
- − The 'tabby' markings on the third animal are very faint
FLUX.1 [schnell]
- + Successfully included all four requested animals (dog, cat, rabbit/fox-like kit)
- + Excellent fur texture and 'big expressive eyes' adherence
- + Better color variety in the wildflower meadow
- − The anatomy of the two center animals is slightly ambiguous
- − The composition feels a bit crowded compared to Model A
- − Less dynamic action than Model A
Verdict: While FLUX.1 Kontext [dev] produced a more dynamic and high-quality image, it failed significantly on prompt adherence by omitting the fox and rabbit. FLUX.1 [schnell] followed the complex prompt more accurately, including all four species requested with distinct fur textures and the specified 8K masterpiece feel.
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 rendering for both the main name and established date.
- + Accurately represents the cloche dome with steam as requested.
- + Clean, minimalist vector aesthetic that adheres to the logo style.
- − The steam element is a bit thick and less 'subtle' than it could be.
- − Lacks the requested 'banner' for the date, placing it as plain text instead.
FLUX.1 [schnell]
- + The cloche dome is elegantly designed with good shading.
- + Succesfully incorporates a banner element and circular frame for a 'vintage emblem' feel.
- + The background texture is more noticeable and fits the prompt.
- − Significant spelling errors: 'CAFEÉ FRAMILAN' instead of 'Caffè Florian'.
- − Date error: 'EST. 7720' instead of '1720'.
- − Failed to include the requested steam element.
Verdict: FLUX.1 Kontext [dev] is the clear winner as it correctly spelled 'Caffè Florian' and '1720', whereas FLUX.1 [schnell] hallucinated several characters and missed the steam requirement. While FLUX.1 [schnell] had a more complex emblem composition, its complete failure in text accuracy makes it unusable for a logo task.
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]
- + Features a bold, clear title that establishes the theme immediately.
- + Good adherence to the navy, white, and muted red color palette.
- + Includes distinct icons for different mission phases.
- − The text below the icons is largely gibberish and poorly rendered.
- − Spelled the main title incorrectly as 'APOLO'.
- − The icons are somewhat cluttered and lack clear vector precision.
FLUX.1 [schnell]
- + Excellent vector aesthetic with a clean, centered composition.
- + Superior iconography that feels more modern and professional.
- + Layout intelligently uses the orbit rings to represent mission steps.
- − The text content is mostly placeholder-style gibberish.
- − The rocket icon looks more like a cartoon shuttle than a Saturn V rocket.
- − Missing a clear main title at the top of the poster.
Verdict: FLUX.1 [schnell] is the winner due to its superior vector aesthetic and professional layout, which much better matches the 'modern infographic' request. While FLUX.1 Kontext [dev] includes a title and follows the steps chronologically, its poor text rendering and 'Apolo' misspelling significantly detract from the quality compared to the clean visuals of the other model.
Explore each model
Black Forest Labs' 12 billion parameter distilled image generation model optimized for speed, capable of generating high-quality images in just 4 inference steps