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 [klein] 9B
#13 of 32 in Image Editing
Where the votes landed
FLUX.1 Kontext [pro]
0%
win rate
Ties
0%
FLUX.2 [klein] 9B
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 the 'behind' spatial instruction for the plant.
- + High-quality rendering of thin, elegant glass edges.
- + Clean, modern aesthetic with realistic lighting from the left.
- − The blue sphere appears fuzzy/felt-like rather than a smooth sphere.
- − The book is slightly floating above the glass surface instead of resting directly on it.
FLUX.2 [klein] 9B
- + Beautiful marble-like texture on the blue sphere.
- + Authentic thick glass material with realistic light refraction.
- + Textured wooden table grain adds to the realism.
- − The plant is more alongside/around the cube than clearly behind it.
- − The glass cube shape is slightly irregular and blocky.
Verdict: Both models followed the complex spatial instructions well, but FLUX.1 Kontext [pro] provided a cleaner composition that more accurately placed the plant 'behind' the cube. FLUX.2 [klein] 9B excelled in material textures, particularly the blue sphere and the wooden table, though the glass cube's geometry was slightly less precise.
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]
- + Natural skin and clothing textures that look highly realistic under the lighting.
- + Captures the somber atmosphere of a rainy day effectively.
- − The subject looks more like he is riding/leaning on the bike rather than repairing it.
- − The rain effect looks a bit like a static filter rather than interacting with the scene.
FLUX.2 [klein] 9B
- + Excellent adherence to the 'repairing' action with tools and professional crouching pose.
- + Superior compositional depth with tools in the foreground and a clear street scene.
- + Rich detail in the red bicycle and environmental reflections.
- − The car in the background lacks the specific 'motion blur' requested.
- − The shallow depth of field is a bit aggressive on the handlebars relative to the face.
Verdict: FLUX.2 [klein] 9B is the clear winner as it accurately depicts the action of 'repairing' the bicycle, including tools and a realistic pose, which FLUX.1 Kontext [pro] misses by simply showing a man holding the handlebars. FLUX.2 [klein] 9B also creates a much more complex and visually interesting environment with better reflections and a stronger sense of place.
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]
- + Excellent skin texture with realistic fine pores and subtle scarring.
- + Superior lighting effects with warm torchlight naturally wrapping around the face and armor.
- + High-quality rendering of the engraved armor and fabric textures.
- − Missed the request for 'beads' in the hair.
- − The 'bokeh sparks' are quite subtle and limited to one side.
FLUX.2 [klein] 9B
- + Perfect adherence to the 'hair braided with small beads' part of the prompt.
- + Stronger interpretation of the 'battle-worn' descriptor with more prominent scars and dirt.
- + Good inclusion of bokeh sparks and visible torches in the background.
- − The eyes look slightly glassier and less lifelike than Model A.
- − The scar on the forehead looks a bit like a surface smudge or stamp rather than integrated skin tissue.
Verdict: FLUX.1 Kontext [pro] produces a more photorealistic portrait with superior lighting and skin shaders, whereas FLUX.2 [klein] 9B followed the prompt instructions more closely regarding the hair ornaments and overall battle-worn aesthetic. FLUX.1 Kontext [pro] is likely preferred for its artistic depth and cinematic quality, though FLUX.2 [klein] 9B wins on technical prompt adherence.
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]
- + Features a very clean, professional minimalist layout that looks like a real menu.
- + Correctly identifies and separates the three requested sections: Appetizers, Pizza, and Mains.
- + Bold sans-serif typography is highly legible and follows the prompt's aesthetic.
- − The food photos are not in a strict grid as requested, instead alternating sides.
- − Some pricing numbers are unrealistically high or inconsistent with the food items.
FLUX.2 [klein] 9B
- + Successfully follows the 'photos in grid' instruction with 4 uniform images.
- + Includes currency symbols which add to the realism of a menu design.
- + Captures the 'vibrant accents' request with colorful underlines and text.
- − The text is highly garbled with significant spelling errors in the headers and body.
- − The layout is repetitive and confusing, featuring 'Appetizers' twice and 'Mains' twice.
- − Visual quality of the text characters is poor, with many letters merging together.
Verdict: FLUX.1 Kontext [pro] is the superior model because it produces a coherent, professional-looking design that functions as a structural menu. While FLUX.2 [klein] 9B followed the grid instruction more literally, its text rendering and layout logic were significantly lower in quality, resulting in a cluttered and unusable design compared to the clean aesthetic of FLUX.1 Kontext [pro].
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 meat patty and dripping cheese
- + Accurate rendering of the price text with comma decimal
- + Atmospheric background with realistic embers and coals
- − Missed the 'starburst' requirement for the price
- − Redundant price information appears twice in the frame
- − Composition is very static despite the 'dynamic' request
FLUX.2 [klein] 9B
- + Perfect adherence to the 'starburst' request for the price
- + Highly dynamic composition with an angled burger and flying sauce drops
- + Stronger 'fiery' texture applied specifically to the main title text
- − Price uses a period instead of the requested comma
- − The 'starburst' shape is slightly inconsistent with the overall graphic style
- − Food lighting is a bit flatter compared to the atmospheric lighting in Model A
Verdict: FLUX.2 [klein] 9B is the winner as it adhered to all layout instructions, including the specific starburst requirement and the 'dynamic' sense of motion. While FLUX.1 Kontext [pro] produced more realistic textures for the food itself, it failed to include the starburst and produced a somewhat redundant and static composition.
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 text layout and vertical alignment.
- + High contrast and very clear legibility for all menu items.
- + Realistic chalk-on-blackboard texture on the letters.
- − The font looks a bit too perfect and uniform for handheld chalk writing.
- − Glitchy text at the bottom including 'ous gluten tree' instead of 'about our'.
FLUX.2 [klein] 9B
- + Beautiful cursive style that matches the elegant request for the title.
- + The chalkboard surface has realistic smudge and wipe marks.
- + Handwriting has more natural variation in tilt and character width.
- − One typo in the bottom text ('fress' instead of 'fresh').
- − A slight glare at the top center obscures some of the board.
Verdict: FLUX.2 [klein] 9B followed the prompt's request for elegant cursive more effectively than FLUX.1 Kontext [pro], and it captured the organic feel of a real chalkboard with smudges and natural handwriting variations. While FLUX.1 Kontext [pro] produced very legible text, it failed the specific instruction for cursive in the title and had more significant spelling errors in the footer.
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 specific 'horse on top' request
- + Cleverly reverses the anatomy by giving the astronaut hooves
- + High cinematic quality with realistic space lighting
- − The small astronaut silhouette riding the horse creates a slightly confusing recursive element
FLUX.2 [klein] 9B
- + Vibrant colors and a sense of cosmic scale
- + Good technical rendering of the horse and astronaut gear
- − Completely failed the negative constraint to put the horse on top
- − Contains nonsensical AI-generated text at the bottom
- − Composition feels like a standard stock image despite the surreal prompt
Verdict: FLUX.1 Kontext [pro] followed the complex spatial instructions perfectly, creating a truly surreal image where a horse rides an astronaut, whereas FLUX.2 [klein] 9B ignored the specific 'horse on top' instruction and produced a standard astronaut-on-horse image with unwanted text. FLUX.1 Kontext [pro] shows a much higher level of prompt intelligence and creative interpretation.
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]
- + Excellent texture on the capybara's fur and the leather steering wheel.
- + The capybara's facial expression perfectly matches the 'calm, professional' prompt.
- − The passenger is on a phone call rather than 'looking at her phone' as requested.
- − The perspective makes it difficult to see the full interior or the 'photorealistic scene inside' requested.
FLUX.2 [klein] 9B
- + Stronger adherence to the passenger prompt, showing her looking down at her phone with a bored expression.
- + Better interior composition showing the full scene, dashboard, and Manhattan streets through the rear window.
- + Highly realistic lighting, including the glow from the phone on the passenger's face.
- − The text on the hat is gibberish ('NEIM TALA').
- − The capybara's paws look slightly like gloved human hands rather than animal paws.
Verdict: FLUX.2 [klein] 9B followed the prompt details much more accurately, specifically capturing the bored businesswoman looking at her phone and providing a wider interior view. While FLUX.1 Kontext [pro] had superior fur texture, it missed the mark on the passenger's behavior and the overall interior composition.
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 style that fits the gothic theme
- + Fine, intricate spiderweb border details
- + High-contrast cinematic lighting on the jack-o-lantern
- − Includes hallucinations in the text details (unrequested line)
- − The composition feels a bit cramped at the bottom
- − Parchment texture is very dark, losing some 'vintage' feel
FLUX.2 [klein] 9B
- + Perfect text accuracy without any hallucinations
- + Stronger illustration of elements like twisted trees and thorns
- + Clearer parchment texture that nails the vintage poster aesthetic
- − Lighting is a bit more 'digital' and less 'cinematic' than Model A
- − The moon is partially obscured by trees, slightly reducing impact
Verdict: FLUX.2 [klein] 9B is the superior choice because it followed the text instructions perfectly without adding gibberish, and it balanced all visual elements like the thorns and trees more effectively. While FLUX.1 Kontext [pro] had impressive typography, the inclusion of nonsensical text and a cluttered bottom section made it less functional as an invitation.
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]
- + Successfully added a full head of hair that follows the skull shape
- + Good preservation of the background and jacket
- − Significantly altered the facial features, making the person look like a different individual
- − The hair looks slightly synthetic and overly groomed for the setting
FLUX.2 [klein] 9B
- + Excellent preservation of the original facial features and identity
- + The curly hair texture looks realistic and matches the lighting of the scene
- + Seamless transition between the new hair and the existing beard/sideburns
- − Minor blurring where the hair curls overlap with the background
Verdict: FLUX.2 [klein] 9B is the clear winner as it successfully added the requested hair while perfectly preserving the identity of the person in the source image. In contrast, FLUX.1 Kontext [pro] significantly altered the facial structure, making the subject unrecognizable compared to the original.
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 art style with soft, appealing textures.
- + Accurate rendering of the Japanese flag and typography.
- + Clean and balanced composition with a high-quality miniature feel.
- − The sushi rice grains are slightly oversized and spherical, looking more like pearls.
FLUX.2 [klein] 9B
- + Good variety of sushi types on the plate.
- + Accurate 45-degree isometric perspective.
- + Clean, bold text rendering.
- − The flag icon is incorrect, showing a red/white/black tricolor instead of the Japanese flag.
- − The wood texture on the base is somewhat stretched and less refined.
Verdict: FLUX.1 Kontext [pro] followed the prompt more accurately, specifically regarding the flag icon and the 'cartoon scene' aesthetic. FLUX.2 [klein] 9B provided a good isometric layout but failed on a key detail by generating a non-Japanese flag and had slightly less polished textures.
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 cartoon style
- + Preserves the original outfit (denim shirt and black top) perfectly
- − Completely misses the core request to include the hockey, dog, and TV anchor elements
- − Fails as a 'caricature of a job' and only produces a stylized portrait
FLUX.2 [klein] 9B
- + Successfully incorporates all requested elements: TV anchor desk, hockey arena background, and dogs in the crowd
- + Excellent use of caricature style with exaggerated features while maintaining likeness
- + Shows high creativity in blending the various hobbies and profession into one scene
- − Changes the original clothing to a professional suit, though this aligns better with the 'TV anchor' prompt
- − Some minor artifacts with the hands and fingers as typical in AI generation
Verdict: FLUX.1 Kontext [pro] failed the primary task, as it only converted the image into a cartoon style while ignoring all the specific content instructions regarding hockey, dogs, and a TV anchor job. FLUX.2 [klein] 9B followed the prompt perfectly, creating a humorous, exaggerated caricature that successfully integrated every requested element into a cohesive and visually interesting scene. FLUX.2 [klein] 9B is the clear winner for prompt adherence and creativity.
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 soft lighting and atmospheric god rays
- + Extremely cute facial expressions that feel cohesive
- + Beautiful rendering of backlighting on the fur
- − Failed to include exactly four distinct species, merging the kitten and bunny into one hybrid-looking animal
- − Static composition that feels more like a portrait than 'chasing' and 'tumbling'
FLUX.2 [klein] 9B
- + Better captures the action of 'chasing' with more dynamic poses
- + Stronger butterfly details and variety in the wildflower meadow
- + Distinct and recognizable animal features for the fox, puppy, and kitten
- − Missing the baby bunny entirely
- − The kitten's facial expression looks slightly startled or unnatural compared to the others
Verdict: Both models failed to correctly count and render all four requested animals, with FLUX.1 Kontext [pro] merging characteristics and FLUX.2 [klein] 9B omitting one entirely. FLUX.2 [klein] 9B is the preferred image because it better captures the requested 'playful' action and has superior detail in the butterflies and flowers, whereas FLUX.1 Kontext [pro] is more of a static group portrait.
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 preservation of the source image's urban composition and background elements.
- + Accurately replicates the distinctive character expressions from the original meme.
- + Strong hand-painted watercolor texture that fits the Ghibli aesthetic perfectly.
- − The color palette is slightly more saturated than the requested 'soft pastels'.
FLUX.2 [klein] 9B
- + Beautifully soft, dreamy pastel color palette and lighting.
- + Successful integration of Ghibli-esque landscape elements like rolling hills and cottages.
- − Fails to preserve the original street setting, moving the scene to a garden/rural area.
- − Loses the specific character dynamics, particularly the girlfriend's iconic angry expression.
- − Added an unnecessary fourth character in the background.
Verdict: FLUX.1 Kontext [pro] is the clear winner as it successfully applies the Ghibli art style while perfectly preserving the composition, setting, and expressions of the source image. FLUX.2 [klein] 9B creates an aesthetically pleasing illustration with a better pastel palette, but it fails as an edit by completely changing the background and softening the necessary emotions of the characters.
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, maintaining the woman's face and the dog's features almost perfectly.
- + Subtle and realistic blowing hair that looks integrated with the lightning.
- − Very few leaves added, making the 'energetic and lively' instruction feel under-delivered.
- − One leaf appears to be floating directly in front of her face in an awkward way.
FLUX.2 [klein] 9B
- + Strongly adheres to the request for 'energetic and lively' feel with a high density of leaves.
- + The hair motion is very dynamic and significantly changed to match the wind effect.
- − Noticeable change to the subject's facial features compared to the source image.
- − Some leaves show artifacts or lack of depth, appearing layered on top of the image rather than in the scene.
Verdict: FLUX.1 Kontext [pro] is much better at preserving the identity of the person and dog from the source image, but its additions are too subtle to truly fulfill the creative brief. FLUX.2 [klein] 9B successfully creates a dynamic and energetic scene with lots of leaves and hair movement, though it fails to perfectly preserve the original face and suffers from some layering artifacts. FLUX.2 is the better choice for this specific task because it actually delivers on the requested emotional and physical changes.
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]
- + Perfectly rendered 'EEST.' abbreviation (Italian for 'East/Est' although slightly redundant) and '1720'.
- + Authentic letterpress texture that fits the vintage aesthetic well.
- + Balanced, clean composition that adheres strictly to the minimalist vector request.
- − Simple steam graphic is a bit abstract compared to the rest of the logo.
- − Includes an extra 'E' in 'EEST.' which while stylistically common for 'Established' in some contexts, may be considered a typo.
FLUX.2 [klein] 9B
- + Graceful typography with consistent kerning and clear legibility.
- + Sophisticated use of negative space and shading on the cloche dome.
- + Excellent subtle parchment-like texture on the background.
- − The 'f' in 'Caffè' has a slightly awkward tail interaction with the 'è'.
- − The composition feels a bit more modern/commercial rather than truly vintage minimalist.
Verdict: Both models followed the prompt exceptionally well, but FLUX.1 Kontext [pro] captures a more authentic vintage 'ink-on-paper' feel. FLUX.2 [klein] 9B provides a cleaner, more polish-looking graphic, but FLUX.1 Kontext [pro] is preferred for its superior textural details and better overall balance as a minimalist logo.
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]
- + Excellent typography rendering for 'APOLLO 11' and several labels.
- + Captures the flat-vector aesthetic with a cohesive, professional navy palette.
- + More dynamic and scientifically illustrative composition showing a trajectory path.
- − Includes Factually incorrect elements, such as Saturn rings around the Moon and rocket.
- − The numbering and labeling for the steps are jumbled and logical flow is confused.
- − Failed to include a distinct lunar module icon for the descent and landing steps.
FLUX.2 [klein] 9B
- + Follows the step-by-step sequential structure more clearly than Model A.
- + Includes specific requested icons like the Lunar Module and astronaut silhouettes.
- + Adheres better to the requested clean, compartmentalized infographic layout.
- − Frequent spelling errors in labels such as 'AOILLO', 'EARDHT', and 'TRANSLURAL'.
- − The rocket design is generic and less like the iconic Saturn V requested.
- − Visual quality of the Earth icon is slightly less sophisticated than the overall poster style.
Verdict: FLUX.1 Kontext [pro] creates a much more visually appealing and professional-looking poster with accurate fonts, but it hallucinates rings around the moon and rocket, which undermines the educational value. FLUX.2 [klein] 9B follows the logical six-step prompt sequence much better and includes the specific Lunar Module icons requested, but suffers from significant spelling errors and a slightly more cluttered layout. FLUX.2 [klein] 9B is the preferred choice for a functional infographic despite the typos, as it correctly identifies the mission stages.
Explore each model
Black Forest Labs' distilled 9 billion parameter image generation model with sub-second inference and multi-reference support