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
FLUX.1 Krea [dev]
#48 of 62 in Text-to-Image
Where the votes landed
FLUX.1 Kontext [dev]
0%
win rate
Ties
0%
FLUX.1 Krea [dev]
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]
- + Perfect adherence to all spatial instructions
- + Excellent light rendering with window reflections on the sphere
- + Vibrant colors and realistic plant texture
- − The glass cube appears slightly open on the sides like a display case rather than a sealed cube
FLUX.1 Krea [dev]
- + Highly realistic glass refraction with a secondary reflection inside the cube
- + Stunning soft atmospheric lighting
- + Elegant book texture and spine details
- − The sphere is quite dark and lacks the requested 'blue' saturation
- − The plant is very dark and difficult to see through the glass
Verdict: Both models show exceptional understanding of complex spatial relationships. FLUX.1 Kontext [dev] is the winner for its superior clarity and adherence to the 'blue' sphere and plant visibility requirements, whereas FLUX.1 Krea [dev] produced a more moody, cinematic image that sacrificed color accuracy and visibility of background elements.
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 sharpness and subject isolation.
- + Realistic rain effects and detailed reflections.
- + Natural skin texture and believable elderly features.
- − The cars in the background lack the requested motion blur, appearing mostly static.
- − The subject is posing with the bike rather than repairing it.
- − The composition feels too centered and clean for 'imperfect framing'.
FLUX.1 Krea [dev]
- + Successfully captures the 'imperfect framing' and motion blur from passing cars.
- + The candid, slightly overhead angle feels more like real street photography.
- + Great atmosphere with wet pavement and muted tones.
- − Missing the 'repairing' action as requested in the prompt.
- − The rain is less visible compared to Model A.
- − The bike's rear wheel and chain area have some structural inconsistencies.
Verdict: FLUX.1 Krea (Model B) better captures the requested photographic style, specifically the motion blur and 'imperfect' street photography aesthetic. FLUX.1 Kontext (Model A) produces a much higher quality portrait but fails on several technical prompts like motion blur and feels too staged. Both models struggled to depict the actual action of 'repairing' the bicycle.
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]
- + Strong warm torchlight highlights on the face and armor
- + Excellent texture on the engraved chestplate
- + Realistic skin tones and subtle scarring
- − Missed the request for hair braided with beads
- − The background bokeh is somewhat soft and lacks the 'sparks' feel
FLUX.1 Krea [dev]
- + Perfect adherence to the hair braids and beads request
- + Great depiction of 'battle-worn' with grit and dried blood
- + Exceptional detail on leather straps and cloth underlayers
- − The lighting is a bit flatter compared to the warm glow in the other model
Verdict: FLUX.1 Krea [dev] is the clear winner as it followed every specific detail of the prompt, most notably the braided hair with beads and the detailed texturing of the leather straps. While FLUX.1 Kontext [dev] had more dramatic lighting, it failed to include several key descriptors that define the character's hairstyle and accessories.
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 professional photography in the food grid
- + Very bold, high-contrast typography that fits the minimalist theme
- + Creative layout that uses the grid and white space effectively
- − Nonsense text throughout the layout
- − Misspelled the word 'Appetizers' as 'Appetizrs'
FLUX.1 Krea [dev]
- + Successfully included specific sections for Appetizers and Mains
- + Layout looks more like a functional, real-world menu document
- + Good use of color accents to highlight headers and prices
- − The font rendering is quite messy and distorted even for non-text areas
- − Image quality on the food photos is lower with some blurred artifacts
- − Small text is completely illegible
Verdict: FLUX.1 Kontext [dev] produced a more visually striking and artistic design with superior food photography, but the text is mostly gibberish. FLUX.1 Krea [dev] followed the structural requirements of the prompt more closely, including specific requested sections, but suffered from poor font rendering and lower image clarity. FLUX.1 Kontext [dev] is the winner for its professional aesthetics and clean minimalist composition.
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]
- + Strong text placement and readability for the main title.
- + Clean, professional-looking graphics for the price starburst.
- + Vibrant color palette and excellent use of glowing embers and fire at the base.
- − Failed to create an 'exploded' burger as requested, presenting a mostly intact sandwich.
- − A typo is present in the secondary text ('LNHLY' instead of 'ONLY').
FLUX.1 Krea [dev]
- + Successfully followed the instructions for an 'exploded' burger with suspended components.
- + High level of photorealistic texture on the meat and buns.
- + Accurate spelling for almost all requested text elements.
- − The pricing text is clipped at the bottom and has some artifacts around the euro symbol.
- − Includes some AI-generated gibberish text at the very bottom of the image.
Verdict: While FLUX.1 Kontext [dev] has cleaner overall graphic design and better color, it failed the primary architectural request of an 'exploded' burger and included a noticeable typo. FLUX.1 Krea [dev] captured the 'exploded' motion perfectly with high physical detail, making it the more accurate despite some minor text artifacts.
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 variation.
- + Strong composition that fills the board naturally.
- − Multiple spelling errors and repeated words like 'with with' and 'Mashroom'.
- − The date at the top is largely illegible/gibberish.
FLUX.1 Krea [dev]
- + Elegant cursive handwriting that matches the 'cozy café' aesthetic.
- + Highly legible date and prices.
- + Better adherence to the requested items list.
- − Includes some hallucinations like 'Gruffle' and 'Lcoman'.
- − The chalk texture is slightly less grainy and authentic than Model A's.
Verdict: FLUX.1 Krea [dev] is the clear winner for its superior legibility and overall aesthetic, capturing the elegant cursive requested in the prompt. While FLUX.1 Kontext [dev] has a very realistic chalk texture, its text is riddled with repeated words and significant spelling errors that make the menu incoherent.
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 placed the horse on top of the astronaut as requested by the prompt.
- + High facial realism and clean rendering of the space suit.
- + Logical lighting and sharp textures.
- − The astronaut appears to be sitting on nothing, as the horse is technically behind/on top rather than being 'ridden' in a traditional sense.
- − The horse's body proportions feel slightly unnatural where it connects behind the astronaut.
FLUX.1 Krea [dev]
- + Dynamic, cinematic composition with high-quality planet rendering.
- + Clever integration of scifi machinery onto the horse's body.
- − Failed the negative constraint entirely by showing the astronaut riding the horse.
- − Significant anatomical errors with the horse's legs, which appear mangled and poorly attached.
- − The lighting on the horse is inconsistent with the planet's light source.
Verdict: FLUX.1 Kontext [dev] is the winner because it successfully followed the difficult spatial instruction to place the horse on top of the astronaut. In contrast, FLUX.1 Krea [dev] ignored the core prompt logic and produced a standard astronaut-riding-horse image with severe anatomical artifacts.
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 photorealistic texture on the capybara fur and jacket fabric.
- + Captured the 'bored' expression of the passenger perfectly.
- + Accurate interior lighting from the streetlights through the window.
- − The capybara only has one hand on the wheel despite the prompt requesting both.
- − The capybara's head looks slightly disembodied from the torso.
FLUX.1 Krea [dev]
- + Successfully placed both front paws on the steering wheel as requested.
- + The cap wearing the 'TAXI' sign is a creative and relevant touch.
- + Strong composition showing the exterior and interior of the vehicle simultaneously.
- − Added an extra person in the passenger seat who was not in the prompt.
- − The woman in the back seat has a strange glowing artifact over her eye.
- − The facial features of the humans are less realistic than in the first image.
Verdict: FLUX.1 Kontext [dev] provides a more grounded and photorealistic image with better lighting and texture, though it missed the detail about both paws on the wheel. FLUX.1 Krea [dev] followed the 'both paws' instruction better but introduced unwanted elements like a third passenger and visual artifacts on the faces. Overall, FLUX.1 Kontext [dev] is the superior image due to its higher realism and closer adherence to the requested mood.
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 adherence to the main title text spelling.
- + High contrast, vibrant glowing jack-o-lantern.
- + Captures the thorn border request well.
- − Internal scroll text is completely garbled and unreadable.
- − Location details are misspelled ('The Argiiah's' instead of 'The Arches').
- − Background lacks the requested 'moody night sky' and 'twisted trees' detail.
FLUX.1 Krea [dev]
- + Superb atmospheric depth with twisted trees and a moody sky.
- + Much higher quality 'vintage parchment' texture and ornate border details.
- + Effective use of the scroll banner for secondary text.
- − Major spelling errors in the main title ('Pasty Halloween').
- − Duplicate words and spelling issues in the bottom scroll ('You are are invited').
Verdict: Both models struggled significantly with the complex text requirements, providing several typos and garbled sentences. FLUX.1 Kontext [dev] is more functional as an invitation because it correctly spelled the primary header, but FLUX.1 Krea [dev] has far superior artistic quality, better parchment textures, and more detailed gothic elements, despite the 'Pasty Halloween' typo.
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 clarity and bold typography
- + Very clean, rounded cartoon aesthetics
- + Strong 3D clay-like material rendering
- − The flag icon is stylized into an abstract shape rather than a recognizable Japanese flag
- − Sushi anatomy is a bit strange, combining a nigiri top with a gunkan-style wrap
FLUX.1 Krea [dev]
- + Features a correct and recognizable Japanese flag icon
- + Higher detail on the sushi textures and rice grains
- + Better adherence to the 'diorama base' and 'plate' instructions
- − The 'JAPAN' text is slightly less crisp and has minor letter irregularities
- − Composition is slightly lower in the frame compared to the prompt's request for top-center text
Verdict: FLUX.1 Kontext [dev] produced a much cleaner graphic design with bold, professional-grade typography, though it struggled with the specific flag icon. FLUX.1 Krea [dev] adhered better to the scene's composition, including the requested plate and a correct flag, and provided more realistic textures on the food. FLUX.1 Krea [dev] is the winner for following all visual elements of the prompt more accurately.
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 dynamic lighting with backlight and rim light effects
- + Dynamic posing and sense of motion
- − Failed to include the fox kit and baby bunny
- − Includes three animals instead of the requested four
- − Anatomy issues with the center kitten's limbs
FLUX.1 Krea [dev]
- + Successfully included the golden retriever, tabby kitten, and fox kit
- + High detail in fur texture and facial expressions
- + Strong adherence to the lighting and atmosphere requirements
- − Failed to include the baby bunny
- − The floating tabby kitten in the background has a slightly awkward perspective
Verdict: FLUX.1 Krea [dev] is the winner as it captured three out of the four requested animals, including the distinct fox kit, while FLUX.1 Kontext [dev] only generated three puppies/kittens. Both models failed to include the baby bunny, but FLUX.1 Krea [dev] provided superior prompt adherence and cleaner animal anatomy.
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]
- + Perfect text rendering of the requested brand name
- + Clean minimalist vector aesthetic
- + High contrast and balance
- − Missed the requested banner element
- − Steam graphic is very abstract and lacks detail
FLUX.1 Krea [dev]
- + Excellent vintage texture and retro feel
- + Intricate illustrative style for the cloche and steam
- + Includes the requested banner element
- − Significant spelling error in the primary brand name
- − Text and icons overlap in a cluttered way
Verdict: FLUX.1 Kontext [dev] produced a clean, professional logo with perfect typography that adhered exactly to the name 'Caffè Florian', though it missed the banner detail. FLUX.1 Krea [dev] captured the vintage aesthetic and textured background much better but failed on the most critical aspect: the spelling of the restaurant name. Because accurate text is paramount for a logo, FLUX.1 Kontext is the superior choice.
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]
- + Closer adherence to the navy and muted red color palette palette.
- + The icons feel more unified and stylistically consistent as an infographic set.
- + Includes more of the requested textual headings for the steps.
- − Significant spelling error in the main title ('Apolo' instead of 'Apollo').
- − Text rendering for the smaller descriptions is illegible and messy.
- − Layout is somewhat cluttered and lacks a clear flow.
FLUX.1 Krea [dev]
- + Clean, professional composition with a logical flow from space to the lunar surface.
- + Accurately spelled the primary title 'Apollo 11'.
- + Vector graphics are crisp with clear iconography like the Earth and Moon.
- − Fails to include the specific steps and labels requested (e.g., Launch, Earth Orbit, Descent).
- − Includes a random Saturn-like planet that was not in the prompt.
- − The 'translunar trajectory' and numbering do not align with physics or the actual mission sequence.
Verdict: FLUX.1 Kontext [dev] followed the specific textural requirements and color palette of the prompt much more closely, but suffered from a major spelling error in the header and poor legibility. FLUX.1 Krea [dev] produced a much more visually polished and clear graphic, but ignored almost all of the specific mission steps requested in the prompt. FLUX.1 Krea [dev] is the likely winner for its superior visual quality and correct title spelling, despite the factual and prompt-adherence inaccuracies.
Explore each model
Black Forest Labs' aesthetically-tuned 12-billion parameter flow transformer optimized for high-quality images with incredible aesthetics, suitable for personal and commercial use