Black Forest Labs' 12-billion parameter multimodal flow transformer for in-context image generation and editing with character consistency, typography handling, and commercial-ready quality
Settled by community votes across 17 shared challenges, with an AI judge weighing in on each.
FLUX.1 Kontext [pro]
#41 of 62 in Text-to-Image
FLUX.2 [pro]
#8 of 62 in Text-to-Image
Where the votes landed
FLUX.1 Kontext [pro]
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 [pro]
- + Excellent adherence to lighting instructions with clear directional light from the left.
- + Highly realistic textures on the sphere and the wooden table grain.
- − The cube looks more like a hollow glass frame than a solid or thick-walled glass box.
- − The sphere appears to be floating unnaturally within the cube.
FLUX.2 [pro]
- + Superior rendering of the glass material, featuring realistic thickness and reflections.
- + Beautiful book detailing, including subtle spine text and realistic paper edging.
- + Great depth of field with the plant perfectly positioned as requested.
- − The blue sphere is partially clipped or merged into the bottom pane of the glass cube.
Verdict: Both models followed the prompt instructions perfectly regarding object placement and composition. FLUX.1 Kontext [pro] has a more tactile, felt-like texture on the sphere and very clean lines, but FLUX.2 [pro] captures the physics of glass and the 'academic' aesthetic of the book much more convincingly, despite the minor clipping of the sphere at the base.
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 [pro]
- + Excellent natural skin texture and facial detail.
- + Includes rain streaks and realistic wetness on clothing.
- + Captures the requested 'imperfect framing' with a close-up candid feel.
- − The man appears to be riding the bike rather than repairing it.
- − Misses the motion blur effect for the background cars.
- − Lower bicycle detail with some messy brake cable rendering.
FLUX.2 [pro]
- + Perfectly adheres to the 'repairing' action with the man kneeling by the chain.
- + Excellent reflection and ripples on the wet pavement.
- + Accurately represents the motion blur and bokeh from passing city traffic.
- − The bicycle frame geometry is incoherent near the handlebars.
- − The man's right hand and the chain/pedal area have significant anatomical and mechanical merging artifacts.
- − Skin texture is slightly more smoothed and less 'natural' than Model A.
Verdict: While FLUX.1 Kontext [pro] produces a more convincing human portrait with superior rain effects, it fails the primary action of the prompt, showing the man riding rather than repairing the bike. FLUX.2 [pro] captures the overall scene, action, and lighting environment much more accurately, including specific details like the ripples in the puddles and the motion of traffic, making it the better interpretation of the full prompt despite some technical artifacts in the bicycle's mechanical parts.
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 [pro]
- + Subtle and realistic skin texture with faint scars as requested
- + Highly detailed and believable metal engraving
- + Sophisticated use of shallow depth of field and soft lighting
- − Missed the request for beads in the hair braids
- − The 'battle-worn' appearance is very clean compared to the prompt
FLUX.2 [pro]
- + Strong adherence to all prompt elements including beads and sparks
- + Excellent grit and 'battle-worn' texture on face and armor
- + Dynamic lighting and high contrast
- − Armor engravings look slightly more digital/artificial than Model A
- − The sparks look a bit like floating flat lines rather than glowing embers
Verdict: FLUX.2 [pro] followed the prompt much more literally, including the specific beads in the hair and a more convincing battle-worn appearance. While FLUX.1 Kontext [pro] produced a more polished, cinematic portrait, it missed some of the finer character details like the beads and the level of dirt requested.
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 [pro]
- + Excellent typography with clean, bold sans-serif fonts and readable layouts.
- + High-quality, professional food photography that fits the modern aesthetic.
- + Better adherence to the 'Mains' category requirement.
- − The grid is asymmetrical and less structured than a traditional design grid.
- − The text content contains nonsensical words (e.g., 'duly hegas praise').
FLUX.2 [pro]
- + Successfully implements a logical grid layout for the photos as requested.
- + Includes realistic currency symbols and pricing structure.
- + Clean two-column layout that feels very practical for a real-world menu.
- − Confused categorization, listing 'Pizza' under 'Appetizers' and 'Garlic Bread' under 'Mains'.
- − Spelling error in the category header ('MINS' instead of 'MAINS').
- − Repetitive menu items that don't match the corresponding photos.
Verdict: FLUX.1 Kontext [pro] creates a much more visually polished and artistic menu that looks ready for a high-end casual restaurant, despite the nonsensical placeholder text. FLUX.2 [pro] follows the 'grid' instruction more literally and includes currency symbols, but fails significantly on logical content organization and basic spelling. Overall, FLUX.1 Kontext [pro] is the preferred choice for its professional image quality and superior 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 [pro]
- + Excellent photorealistic texture on the burger bun and patty
- + Vibrant, high-contrast lighting with a strong sense of heat
- + Clear, legible typography for all requested text elements
- − Failed to include the starburst element for the price
- − Repeated the price text twice unnecessarily
- − The burger is barely separated, losing the 'exploded' effect
FLUX.2 [pro]
- + Successfully captured the 'exploded' dynamic with separated components
- + Correctly included the starburst shape for the price as requested
- + Text effect perfectly matches the fiery/glowing prompt
- − The bottom bun texture looks slightly artificial and flat
- − The overall composition feels a bit more like a graphic design than a raw photo
Verdict: FLUX.2 [pro] followed the complex layout instructions much better than FLUX.1 Kontext [pro], successfully rendering the exploded view and the specific starburst element. While FLUX.1 Kontext [pro] produced a more photorealistic burger texture, it failed on several prompt details and cluttered the image with duplicate 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 [pro]
- + Excellent chalk texture and realistic handwriting variation
- + Perfect spelling including the correctly guessed third item
- + Framed composition looks clean and professional
- − The title is in print-style rather than the requested 'elegant cursive'
FLUX.2 [pro]
- + Successfully followed the instruction for 'elegant cursive' in the title
- + Higher level of realism in the chalkboard surface and surrounding cafe lighting
- + Complete and accurate text rendering including prices
- − Slightly less 'natural' chalk texture on some letters compared to Model A
Verdict: Both models performed exceptionally well, accurately completing the partial prompt with identical item names and prices. FLUX.2 [pro] is the winner as it correctly followed the specific stylistic instruction for 'elegant cursive' in the title, whereas FLUX.1 Kontext [pro] used a block print style for the entire 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 [pro]
- + Perfectly adheres to the subverted 'horse riding human' prompt by having a small astronaut figure on top of the horse.
- + The large astronaut's hand becoming a horse hoof is a clever surreal element.
- + High cinematic quality with realistic lighting and texture on the spacesuit.
- − The anatomy is a bit chaotic where the horse connects to the large astronaut's back.
FLUX.2 [pro]
- + Striking, vibrant composition with detailed nebulae and galaxy formations.
- + Clean rendering and high resolution.
- − Fails the specific prompt instruction to have the horse riding the astronaut, showing the horse standing on another horse/human hybrid instead.
- − Lacks the specific surreal logic requested in the prompt.
Verdict: FLUX.1 Kontext [pro] successfully interpreted the difficult 'horse on top' instruction, creating a humorous and surreal scene where a horse literally rides an astronaut. FLUX.2 [pro] produced a beautiful space image but failed the core logic of the prompt, showing a standard horse standing on an ambiguous figure.
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 [pro]
- + The capybara's fur texture is exceptionally realistic.
- + Good adherence to the calm and professional expression request.
- − The passenger is holding two phones to her ears rather than looking at one as requested.
- − The composition is a bit tight, losing some of the taxi interior's context.
FLUX.2 [pro]
- + Excellent interior composition showing the dashboard, passenger, and city lights simultaneously.
- + Accurately depicts the businesswoman looking at her phone with a bored expression.
- + Includes both paws on the steering wheel as requested.
- − The capybara's hands/paws look slightly more like gloved human hands than natural paws.
- − The hat is slightly clipping with the capybara's ear.
Verdict: FLUX.2 [pro] followed the prompt much more accurately, correctly depicting the businesswoman looking at her phone and providing a superior wide-angle composition of the taxi interior. While FLUX.1 Kontext [pro] had slightly better fur rendering, it failed the specific instruction for the passenger's action by showing her talking on two phones.
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 [pro]
- + Excellent typography for the main title and banner
- + Elegant spiderweb border design
- + Strong atmospheric lighting on the jack-o-lantern
- − Includes several lines of garbled hallucinated text in the event details section
- − A bit less 'parchment' texture than requested
FLUX.2 [pro]
- + Perfect text accuracy with no hallucinations
- + Stronger parchment texture and torn edge effects
- + Great interpretation of the 'webs and thorns' border prompt
- − The jack-o-lantern rendering feels slightly more like a photo than a vintage poster
- − The banner texture is a bit repetitive
Verdict: Both models followed the complex prompt very well, but FLUX.2 [pro] is the clear winner due to perfect text rendering. While FLUX.1 Kontext [pro] creates a beautiful gothic atmosphere, it fails by adding multiple lines of gibberish text in the event details, whereas FLUX.2 [pro] follows all instructions accurately and provides a more authentic parchment feel.
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 [pro]
- + Excellent preservation of the original facial anatomy and identity.
- + Natural integration of the hair with the existing sideburns and beard.
- + Consistent lighting and image texture compared to the source.
- − The hairline is slightly high, though still within the realm of realism.
FLUX.2 [pro]
- + Successfully adds a full head of hair with realistic volume.
- + Preserves the background and clothing perfectly.
- − Significantly alters the person's facial features, making them look like a different individual.
- − The hair texture appears slightly more painterly and less integrated than the source beard texture.
- − The forehead and eyes were modified unnecessarily.
Verdict: FLUX.1 Kontext [pro] is the superior model for this task because it successfully added the requested hair while perfectly preserving the original person's identity and facial features. In contrast, FLUX.2 [pro] changed the structure of the face and eyes, resulting in an image of a different man, which fails the primary requirement of a localized edit.
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 [pro]
- + Excellent 3D cartoon surface textures on the salmon and rice.
- + Text rendering is clean and stylistically consistent with the scene.
- + Effective use of isometric perspective and lighting.
- − The flag icon is slightly distorted and lacks the precision of the other elements.
FLUX.2 [pro]
- + Perfect execution of the Japanese flag icon.
- + Higher variety of sushi types on the plate while maintaining a clean look.
- + Accurate interpretation of the 45-degree isometric diorama base.
- − The salmon Nigiri in the foreground has an unusual cube-like shape compared to traditional sushi.
- − The lighting is a bit flatter compared to the soft shadows in the other model.
Verdict: FLUX.1 Kontext [pro] creates a more tactile and visually appealing 3D cartoon texture for the food, though it only depicts a single piece of sushi. FLUX.2 [pro] followed the layout and icon instructions more precisely, offering a more complete diorama with a perfect flag and clean typography. FLUX.2 [pro] is slightly preferred for its overall composition and superior icon rendering.
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 [pro]
- + Captures the user's likeness accurately in a caricature style
- + Preserves the clothing and pose of the source image perfectly
- − Completely fails to include the requested profession, dogs, or hockey elements
FLUX.2 [pro]
- + Successfully incorporates all requested elements: TV anchor desk, dogs, and hockey gear
- + Excellent illustration style with vibrant colors
- + Captures the essence of the user's facial features and hair color
- − Changes the clothing from a denim shirt to a blazer
- − Eyes are changed to green whereas the source appears to have brown/hazel eyes
Verdict: FLUX.1 Kontext [pro] creates a great stylistic transformation of the original photo but ignores the secondary prompt instructions regarding the specific details of the profession and hobbies. FLUX.2 [pro] captures the full scope of the requested scene, and while it takes more liberties with the clothing to fit the 'TV Anchor' theme, it is the only model that actually fulfilled the editing requirements.
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 [pro]
- + Excellent adherence to the 'golden sunrise' and 'god rays' lighting request
- + Consistent and vibrant color palette throughout the scene
- + High-quality fur texture and expressive facial features on all animals
- − The 'bunny' looks like a hybrid between a kitten and a rabbit
- − The animals are sitting rather than 'tumbling' or 'chasing'
FLUX.2 [pro]
- + Successfully captured all four distinct animal types with accurate anatomy
- + Interaction between species feels more dynamic and 'wholesome'
- + Photorealistic butterfly details and dew sparkles on the grass
- − The lighting is a bit more muted and less like a 'golden sunrise' compared to image A
- − Minor anatomical blending where the dog's tongue appears to touch the rabbit's ear
Verdict: Both models performed exceptionally well, but FLUX.2 [pro] is the winner due to its superior ability to accurately render four distinct animal species, whereas FLUX.1 Kontext [pro] struggled with the rabbit's anatomy. FLUX.2 [pro] also managed more complex interactions and better butterfly detailing, despite having slightly less dramatic lighting than its competitor.
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 [pro]
- + Excellent adherence to the iconic meme composition and character poses.
- + Effective use of watercolor-style textures that mimic hand-painted Ghibli backgrounds.
- + Maintains clear character expressions that translate the original humor into animation style.
- − The color palette is slightly more saturated than the requested 'soft pastels'.
- − Some line work is a bit thick, losing some of the Ghibli delicacy.
FLUX.2 [pro]
- + Perfectly captures the 'soft pastel' and 'nostalgic' mood requested in the prompt.
- + Background details are more intricate and characteristic of Ghibli's urban scenery.
- + The lighting is gentle and dreamy, creating a high-quality artistic aesthetic.
- − The central male character's expression is a bit too neutral compared to the original meme's 'distracted' look.
- − The woman in the foreground has a slightly flatter face compared to the other characters.
Verdict: Both models did an exceptional job of re-imagining a famous meme in a new art style. FLUX.1 Kontext [pro] is better at preserving the specific facial expressions and intensity of the original photo, while FLUX.2 [pro] is more successful at fulfilling the stylistic requirements of the prompt, particularly the soft pastel colors and dreamy, nostalgic lighting common in Studio Ghibli films.
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 [pro]
- + Excellent source preservation of the person and dog
- + Subtle, realistic hair movement
- − The 'flying leaves' are very small and sparse
- − Failed to capture a truly 'energetic' feel beyond the hair
FLUX.2 [pro]
- + Strong prompt adherence with many dynamic flying leaves
- + Hair motion is significant and captures the 'windy' request well
- + Adds motion to the jacket as well, increasing the lively feel
- − The leaf in the bottom left has some artifacts where it meets the ground
- − The large number of leaves slightly obscures the original scenery
Verdict: FLUX.2 [pro] followed the instructions much better by including a significant number of flying leaves and creating a clearer sense of motion in both the hair and clothing. While FLUX.1 Kontext [pro] preserved the original image more accurately, it was too subtle with the requested edits, making the scene feel less 'energetic' than requested.
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 [pro]
- + Excellent typography rendering for 'Caffè Florian'
- + Strong adherence to the minimalist prompt requirement
- + Good textured paper effect on the background
- − Spelling error in the banner text ('EEST' instead of 'EST')
- − The steam icon is slightly too abstract compared to the rest of the logo
FLUX.2 [pro]
- + Perfect spelling on all text elements including 'Est. 1720'
- + Sophisticated vector emblem style with balanced circular framing
- + More detailed and visually appealing cloche dome illustration
- − Slightly less 'minimalist' than requested due to the extra border lines
- − The typography for the main name is less bold than Model A
Verdict: Both models followed the prompt closely, but FLUX.2 [pro] is the superior choice because it handled the text perfectly, whereas FLUX.1 Kontext [pro] included a spelling error ('EEST'). FLUX.2 [pro] also produced a more cohesive emblem design that felt professionally balanced and refined.
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 [pro]
- + Features a bold and high-impact central illustration.
- + Adheres reasonably well to the requested color palette.
- + Crisp text rendering for the main title.
- − Confuses Saturn V with the planet Saturn by putting rings and a planetoid on the rocket.
- − Logic of the infographic steps is messy and visually confusing.
- − The vector style is mixed with more painterly textures in the lunar surface.
FLUX.2 [pro]
- + Excellent list-style infographic layout that clearly follows the requested steps.
- + Very clean, professional flat-vector aesthetic with consistent iconography.
- + Highly accurate details including the astronaut names and specific module shapes.
- − Supporting body text is nonsensical filler/gibberish.
- − The rocket icon looks more like a generic shuttle than the Saturn V.
Verdict: FLUX.2 [pro] followed the infographic structure much more effectively, producing a clear step-by-step layout that matches the 'modern vector' request perfectly. In contrast, FLUX.1 Kontext [pro] misinterpreted the 'Saturn V' prompt by literally drawing the planet Saturn around the rocket, leading to a nonsensical and cluttered composition.
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