Black Forest Labs' distilled 9 billion parameter image generation model with sub-second inference and multi-reference support
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
FLUX.2 [klein] 9B
#13 of 32 in Image Editing
FLUX1.1 [pro] Ultra
#51 of 62 in Text-to-Image
Where the votes landed
FLUX.2 [klein] 9B
0%
win rate
Ties
0%
FLUX1.1 [pro] Ultra
0%
win rate
Challenge by challenge
The strongest take from each model on every shared challenge, with the AI judge's read.
Geometric Composition
Text-to-Image“A glass cube on a wooden table. Inside the cube is a small blue sphere. On top of the cube sits a red book. A green plant is behind the cube, partially visible through the glass. Soft window light from the left.”
AI Judge Analysis
FLUX.2 [klein] 9B
- + Natural glass thickness and realistic refraction of the sphere
- + Table texture is highly detailed and weathered
- + Lighting feels very soft and integrated with the environment
- − The glass cube has a strange inner rounded container rather than being a simple hollow cube
- − The sphere appears to be sitting inside a glass column rather than floating or resting in the cube center
FLUX1.1 [pro] Ultra
- + Accurate thin-pane glass construction for the cube
- + Clean and professional photographic quality with realistic book spine details
- + Perfect adherence to the placement of all requested objects
- − The sphere appears to be floating mid-air inside the cube, which may lack physical realism
- − Refraction where the glass meets the table is slightly less complex than Image A
Verdict: FLUX1.1 [pro] Ultra is the winner as it perfectly follows the spatial instructions of the prompt with a clean, modern aesthetic. While FLUX.2 [klein] 9B offers a more rustic and warm atmosphere, the structural logic of the glass cube and sphere placement is less intuitive and slightly messy compared to FLUX1.1 [pro] Ultra.
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.2 [klein] 9B
- + Excellent skin and fabric textures with a very realistic 50mm lens look
- + Strong adherence to the 'repairing' part of the prompt with tools and a crouched posture
- + High attention to detail in the wet pavement reflections and raindrops
- − Missed the specific 'motion blur from passing cars' instruction as the car is static
- − The bicycle anatomy has minor issues near the front fork and handlebars
FLUX1.1 [pro] Ultra
- + Successfully incorporates the 'motion blur from passing cars' request
- + Good composition with clear leading lines from the crosswalk and reflections
- + Clean rendering of the red bicycle and wet street environment
- − The subject appears to be merely holding the bike rather than repairing it
- − Skin and clothing textures look slightly smoother and less natural than Model A
- − The background motion blur feels a bit artificial compared to the subject's sharpness
Verdict: FLUX.2 [klein] 9B captures the 'repairing' action and 'natural skin texture' much more effectively, creating a believable and gritty candid street photo that feels like a real moment. FLUX1.1 [pro] Ultra followed the 'motion blur' instruction significantly better, but it failed to depict the man actually repairing the bike, resulting in a more generic 'man with bike' scene. Overall, FLUX.2 [klein] 9B is preferred for its superior realism and adherence to the core narrative of the prompt.
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.2 [klein] 9B
- + Excellent adherence to details like the braided hair with beads and engraved armor.
- + Very high texture quality on the leather straps and underlayer fabric.
- + Effective lighting with warm torchlight tones and bokeh sparks.
- − The scars appear a bit like superficial scratches rather than battle-worn history.
- − The torch in the background looks slightly disconnected from the character's depth.
FLUX1.1 [pro] Ultra
- − The image failed to load or is a solid black square.
- − Total failure to generate a usable image.
Verdict: FLUX.2 [klein] 9B successfully rendered a highly detailed and atmospheric portrait that followed every aspect of the prompt, from the bead-adorned braids to the textural quality of the armor. FLUX1.1 [pro] Ultra failed to generate a visible image, resulting in a black square and an automatic loss. FLUX.2 [klein] 9B is the winner by default and by merit of its high-quality output.
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.2 [klein] 9B
- + Stronger adherence to the section requirements (Appetizers, Pizza, Mains)
- + Clearer, more readable bold sans-serif fonts
- + The professional grid layout feels more like a finished menu template
- − Repetitive food photography (all images are variants of pizza)
- − Frequent gibberish text in the body and headings
FLUX1.1 [pro] Ultra
- + Better graphic design elements like the logo and red banner
- + The presentation as a 3D mockup is visually appealing
- + More varied food photography showing different dishes
- − Confusing layout where section headers don't clearly align with the content below
- − Typo in the header ('Pizzzans') and overall weaker text rendering
- − The grid feels a bit cluttered and unorganized compared to the other model
Verdict: FLUX.2 [klein] 9B followed the structural prompt more accurately by creating a clear, frontal grid with the specific requested headers (Appetizers, Pizza, Mains), whereas FLUX1.1 [pro] Ultra created an angled mockup that was harder to read. Although FLUX1.1 [pro] Ultra has better artistic variety in the photos, FLUX.2 [klein] 9B's superior font clarity and logical organization make it more successful for a menu design task.
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.2 [klein] 9B
- + Excellent adherence to the starburst container for the price as requested.
- + The text effects perfectly match the fiery, glowing theme specified.
- + Dynamic composition with a strong sense of motion through flying sparks and sauce droplets.
- − The burger components are less 'exploded' or separated than in the competing image.
- − The background relies more on abstract sparks than a defined fiery environment.
FLUX1.1 [pro] Ultra
- + Superior separation of burger components, creating a clearer 'exploded' view.
- + High level of photorealistic detail on the textures of the meat and sesame seed bun.
- + Includes a literal fiery ground with embers that enhances the requested theme.
- − Failed to place the price inside a starburst as requested.
- − The 'LIMITED TIME ONLY' text is very small and plain compared to the other text.
- − Includes some hallucinated small text at the bottom of the image.
Verdict: FLUX.2 [klein] 9B followed the prompt details much more accurately overall, successfully integrating the fiery text effects and the specific starburst requirement for the price. While FLUX1.1 [pro] Ultra produced a more detailed 'exploded' burger and crisp textures, it missed the starburst instruction and included messy artifact text at the bottom.
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.2 [klein] 9B
- + Excellent text rendering with near-perfect spelling and alignment.
- + High-quality chalk texture and realistic erased smudges on the board.
- + Strong adherence to the requested cursive title and layout.
FLUX1.1 [pro] Ultra
- + Natural, casual handwriting style that looks very human.
- + Good environmental context showing a slice of the café interior.
- − Significant spelling errors and repetitive text (e.g., 'mushrooomm', 'fresh fresh').
- − Failed to render the title in an elegant cursive style as requested.
- − Layout is cluttered with nonsensical repeated words and symbols.
Verdict: FLUX.2 [klein] 9B followed the prompt with much higher precision, delivering clear, correctly spelled text and beautiful chalk textures. FLUX1.1 [pro] Ultra struggled with the text-heavy requirements, resulting in numerous spelling errors and repetitive lines which made the menu nonsensical. FLUX.2 [klein] 9B is the clear winner for its superior legibility and adherence to style constraints.
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.2 [klein] 9B
- + Excellent anatomical detail on the horse and astronaut gear.
- + Rich, cinematic color palette with vibrant celestial objects.
- + High rendering quality with sharp textures.
- − Completely failed the negative constraint to have the horse on top.
- − Includes nonsensical AI-generated text at the bottom.
FLUX1.1 [pro] Ultra
- + Clean composition with a beautiful curved horizon.
- + Great sense of scale and motion with the horse's mane and tail.
- + Technically high visual quality with no gibberish text.
- − Completely failed the negative constraint to have the horse on top.
- − The horse lacks ears, which is a noticeable anatomical error.
Verdict: Both models completely failed the specific prompt instruction to place the horse on top of the astronaut, instead providing the conventional 'astronaut riding a horse' image. FLUX.2 [klein] 9B produced a more detailed horse and suit but included distracting gibberish text, while FLUX1.1 [pro] Ultra offered a cleaner composition but suffered from anatomical errors like the horse missing its ears.
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.2 [klein] 9B
- + Follows the 'back seat' positioning instruction perfectly.
- + The lighting from the phone screen onto the woman's face is very realistic.
- + Captures the 'bored' expression of the passenger accurately.
- − The text on the cap is slightly garbled ('NEW TALA').
- − The capybara's paws look somewhat like human hands/gloves rather than realistic paws.
FLUX1.1 [pro] Ultra
- + High visual clarity and vibrant, saturated colors.
- + Realistic fur texture on the capybara.
- − Fails the spatial prompt; the woman is sitting in the front passenger seat instead of the back seat.
- − The woman is holding her phone over the steering wheel area, creating a confusing composition.
- − The perspective of the car interior is anatomically incorrect for a vehicle.
Verdict: FLUX.2 [klein] 9B is the clear winner as it correctly places the passenger in the back seat, creating the intended narrative of a normal taxi ride. FLUX1.1 [pro] Ultra fails the spatial requirements of the prompt by placing the human in the front, and the resulting composition is cramped and illogical.
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.2 [klein] 9B
- + Perfect text accuracy for all components including the title, banner, and event details.
- + Integrated composition where the jack-o-lantern acts as a central light source for the background elements.
- + Superior aesthetic balance with the thorns and webs forming a cohesive border.
- − The text 'Halloween Party Invitation' is slightly crowded near the top.
FLUX1.1 [pro] Ultra
- + High visual clarity with a distinct scroll-within-a-frame composition.
- + Strong gothic atmosphere with the inclusion of a silhouette castle in the distance.
- − Failed to include the word 'Party' in the main title.
- − Contains redundant and misspelled text ('a noickt or') below the banner.
- − The composition feels more like a template than a cinematic poster.
Verdict: FLUX.2 [klein] 9B followed the prompt instructions perfectly, rendering all text strings accurately and creating a balanced, atmospheric composition. FLUX1.1 [pro] Ultra suffered from significant text hallucinations and omissions, including a misspelled repetition and missing a word from the main title. FLUX.2 [klein] 9B is the clear winner for its functional correctness and superior cinematic lighting.
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.2 [klein] 9B
- + Features a bold, clear typography style that is easy to read.
- + Accurately represents a wood-textured miniature base.
- − Displays an incorrect flag icon (looks like Yemen/Sudan variant instead of Japan).
- − The composition feels slightly off-center and cramped vertically.
FLUX1.1 [pro] Ultra
- + Correctly identifies and renders the Japanese flag icon.
- + Higher level of detail in the 'miniature' aesthetic, including steam and small garnish elements.
- + Excellent centering and overall visual balance.
- − Text is somewhat faint and stylized compared to the 'large bold' request.
- − Includes unexpected elements like an insect-like garnish on the tray.
Verdict: FLUX1.1 [pro] Ultra is the clear winner for its superior conceptual accuracy, specifically providing the correct Japanese flag which FLUX.2 [klein] 9B failed to do. While FLUX.2 [klein] 9B had bolder text, FLUX1.1 [pro] Ultra produced a much more polished 3D render with better lighting and a more professional miniature diorama appearance.
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.2 [klein] 9B
- + Excellent fur detail and texture realism
- + Clear, well-defined butterflies with natural patterns
- + Good interpretation of god rays and dynamic lighting
- − Prompt adherence failure: missing the baby bunny
- − Anatomy issues with the fox's front right leg
FLUX1.1 [pro] Ultra
- + Successfully included all four animals requested: puppy, kitten, bunny, and fox
- + Consistent and adorable aesthetic for the animal characters
- + Soft, dreamy lighting that fits the 'wholesome vibe'
- − The characters look more like digital illustrations/3D renders than 'hyper-photorealistic'
- − Butterflies are stylized and lack realistic detail compared to Model A
Verdict: FLUX1.1 [pro] Ultra is the winner because it successfully included all four animals requested in the prompt, whereas FLUX.2 [klein] 9B omitted the bunny. While FLUX.2 [klein] 9B achieved a much higher level of photographic realism and texture detail, the failure to follow the core subject list makes FLUX1.1 [pro] Ultra the more reliable choice for this specific prompt.
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.2 [klein] 9B
- + Excellent typography with perfect spelling of 'Caffè Florian'
- + Clean and minimalist vector style following the prompt accurately
- + Great use of a subtle paper texture for the background
- − The steam element is a bit thick and less elegant than the rest of the logo
FLUX1.1 [pro] Ultra
- + Detailed and sophisticated emblem composition
- + Nice shading on the cloche dome design
- − Spelling error in the main text rendering it as 'Caffè Framilian'
- − The composition is a bit crowded for a minimalist logo prompt
Verdict: FLUX.2 [klein] 9B followed the prompt more effectively by delivering a minimalist design with zero spelling errors. While FLUX1.1 [pro] Ultra created a more complex and visually interesting emblem, it failed the primary requirement of accurately spelling the brand name 'Caffè Florian'.
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.2 [klein] 9B
- + Clean vector illustration style that fits the flat-design request.
- + Better layout of the specific spacecraft icons requested, including a clear lunar module.
- + Follows the NASA-inspired color palette accurately.
- − Numerous spelling errors in header and labels (e.g., 'AOILLO', 'EARDHT', 'TRANSLURAL').
- − The flow of the steps is confusing and non-linear.
FLUX1.1 [pro] Ultra
- + Excellent typography for the main 'APOLLO 11' title.
- + Professional infographic layout with a consistent vertical timeline structure.
- + High-quality vector iconography and better overall visual balance.
- − Included a large rocket on the moon surface for the 'Landing' phase, which is factually incorrect and ignores the 'lunar module' instruction.
- − The small body text is mostly gibberish.
- − The number of steps and their sequence is slightly disorganized compared to the prompt sequence.
Verdict: FLUX1.1 [pro] Ultra produced a much more professional-looking infographic with superior composition and typography, though it failed the technical detail of the landing phase by placing a large rocket on the moon. FLUX.2 [klein] 9B followed the specific icon instructions for the lunar module more closely, but the image is marred by significant spelling errors and a cluttered layout. FLUX1.1 [pro] Ultra is the likely winner for its overall aesthetic quality and better adherence to the 'modern vector infographic' style.
Explore each model
Black Forest Labs' ultra-high resolution image generation model, an enhanced version of FLUX1.1 [pro] optimized for premium quality output