Black Forest Labs' 12 billion parameter distilled image generation model optimized for speed, capable of generating high-quality images in just 4 inference steps
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
FLUX.1 [schnell]
18.7
arena score
#48 of 62 in Text-to-Image
Skill signature
· Text-to-Image
FLUX1.1 [pro] Ultra
18.5
arena score
#49 of 62 in Text-to-Image
Vote tally
Where the votes landed
FLUX.1 [schnell]
0%
win rate
Ties
0%
FLUX1.1 [pro] Ultra
0%
win rate
Shared challenges
13
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.”
FLUX.1 [schnell]
FLUX1.1 [pro] Ultra
AI Judge Analysis
FLUX.1 [schnell]
- + Excellent lighting and depth of field
- + High resolution textures on the book and table
- − Failed the prompt by adding a second blue sphere on top of the book
- − The plant behind the cube has a strange, overly-smooth plastic texture
FLUX1.1 [pro] Ultra
- + Perfect adherence to all spatial instructions and object counts
- + Transparent glass properties and reflections are very realistic
- + Natural-looking foliage for the plant behind the cube
- − The sphere appears to be floating without a visible support structure which may look slightly unnatural
Verdict: While FLUX.1 [schnell] has high visual fidelity, it failed the core logic of the prompt by adding an extra sphere on top of the book. FLUX1.1 [pro] Ultra followed every instruction perfectly, including the specific placement of the plant and objects, while maintaining superior realism in the glass and lighting effects.
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.”
FLUX.1 [schnell]
FLUX1.1 [pro] Ultra
AI Judge Analysis
FLUX.1 [schnell]
- + Natural skin texture on the man's face and hands
- + Excellent pavement reflections that align with the background lighting
- + Strong cinematic atmosphere with realistic 50mm depth of field
- − Failed to include motion blur on passing cars as requested
- − Minor structural issues with the bicycle front wheel alignment
FLUX1.1 [pro] Ultra
- + Successfully captured heavy motion blur on a passing car
- + Realistic lighting and wet-street aesthetics
- + Accurate representation of an elderly Japanese man
- − The red frame of the bicycle is broken/disconnected near the man's hands
- − The man appears to be standing through the rear wheel of the bike
- − Image looks a bit more clean/digital than 'no stylization' implies
Verdict: FLUX1.1 [pro] Ultra followed the prompt more closely by including the requested motion blur, but it suffered from significant anatomical and mechanical clipping errors where the man and bike intersect. FLUX.1 [schnell] missed the motion blur but produced a much more coherent and realistic-looking subject with better skin textures and lighting, making it the more believable photograph.
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.”
FLUX.1 [schnell]
FLUX1.1 [pro] Ultra
AI Judge Analysis
FLUX.1 [schnell]
- + Excellent adherence to textural details like braided hair and leather straps.
- + Captures the intense, life-like gaze requested in the prompt.
- + Atmospheric lighting with warm torchlight highlights on the face and armor.
- − The skin texture appears slightly over-sharpened, bordering on hyper-realistic but less natural.
- − The 'bokeh sparks' requested are very subtle or missing in the background.
FLUX1.1 [pro] Ultra
- − The image failed to render or is a completely black solid, representing a total failure in generation.
Verdict: FLUX.1 [schnell] successfully interpreted and generated a high-quality portrait that met almost all the prompt requirements, including intricate armor details and specific hair styling. FLUX1.1 [pro] Ultra provided a broken output of a solid black image, making it impossible to evaluate in the context of the prompt.
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.”
FLUX.1 [schnell]
FLUX1.1 [pro] Ultra
AI Judge Analysis
FLUX.1 [schnell]
- + Clean and highly organized layout with logical vertical alignment.
- + Strong adherence to the 'sections' requirement with clear headers.
- + Realistic food photography that matches the casual dining aesthetic.
- − The placeholder text for menu items is garbled and unreadable.
- − The 'Orfefus' text is a nonsensical hallucination that doesn't follow the section requirements.
FLUX1.1 [pro] Ultra
- + Dynamic and modern composition with a professional angled mockup presentation.
- + Vibrant color palette and better integration of red accents as requested.
- + Higher visual quality in the food photography with more variety.
- − The grid layout is a bit cluttered, making it harder to distinguish the specific sections.
- − Text rendering contains spelling errors (e.g., 'Pizzzans') and less structure in the list descriptions.
Verdict: FLUX.1 [schnell] follows the structural layout of a menu more traditionally, using clear vertical columns and large headers, though its text quality is poor. FLUX1.1 [pro] Ultra creates a much more appealing 'modern' design with vibrant colors and a high-end mockup feel, even if the grid is slightly more chaotic. FLUX1.1 [pro] Ultra is the likely winner for its superior visual fidelity and more creative interpretation of 'vibrant accents'.
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.”
FLUX.1 [schnell]
FLUX1.1 [pro] Ultra
AI Judge Analysis
FLUX.1 [schnell]
- + Excellent photorealistic texture on the patty and melting cheese.
- + Dynamic debris adds a strong sense of an explosion.
- + High level of detail in the embers and lighting.
- − Significant text errors including 'AGIC BURGER' and a repeated price '€699'.
- − The burger is largely intact rather than being a fully 'exploded' view of individual components.
- − Failed to apply a fiery, glowing effect to the typeface.
FLUX1.1 [pro] Ultra
- + Perfect text rendering for the main title with the requested fiery glow.
- + Better interpretation of 'exploded' burger showing multiple layers and ingredients suspended.
- + Clean, professional advertisement layout that follows all prompt instructions.
- − Missed the 'starburst' element for the price tag.
- − Small artifact text appeared at the bottom of the image.
Verdict: FLUX1.1 [pro] Ultra is the clear winner as it successfully rendered the challenging text requirements and provided a better 'exploded' view of the burger. While FLUX.1 [schnell] had impressive textures, its significant spelling errors and repetitive price tags made the advertisement unusable compared to the professional layout of the other model.
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.”
FLUX.1 [schnell]
FLUX1.1 [pro] Ultra
AI Judge Analysis
FLUX.1 [schnell]
- + Excellent chalk-like texture on the background board.
- + Good framing of the chalkboard within the environment.
- − Significant spelling errors and gibberish text throughout the menu items.
- − Failed to render the full date, truncating April to 'Pril'.
- − Failed to use elegant cursive for the title as requested.
FLUX1.1 [pro] Ultra
- + Successfully spelled most of the requested menu items including 'Truffle mushroom' and 'Grilled Octopus'.
- + Correctly included the full date 'APRIL 30, 2026'.
- + More realistic wood frame and ambient lighting for a café setting.
- − Did not use an 'elegant cursive' style for the title text.
- − Includes repetitive text at the bottom ('fresh fresh daily', 'gluten-free options' twice).
- − Text spacing for prices is a bit cluttered and messy.
Verdict: Both models failed to deliver the 'elegant cursive' handwriting requested in the prompt, opting for standard print-style chalk lettering. FLUX1.1 [pro] Ultra is the winner because it significantly outperformed FLUX.1 [schnell] in text accuracy, correctly spelling the date and specific food items that were rendered as gibberish in the other model.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
FLUX.1 [schnell]
FLUX1.1 [pro] Ultra
AI Judge Analysis
FLUX.1 [schnell]
- + Successfully placed the horse on top of the astronaut as requested by the specific reversal prompt.
- + Cinematic lighting with a cohesive gold and black color palette.
- + Creative interpretation of the surreal requirement.
- − Anatomical glitching where the horse appears to have two heads or a conjoined body.
- − The astronaut's suit geometry is somewhat muddled and lacks clear definition.
FLUX1.1 [pro] Ultra
- + High visual clarity and sharp resolution.
- + Excellent detail in the planet's atmosphere and the horse's fur.
- + Consistent composition without anatomical artifacts.
- − Failed the negative constraint; the astronaut is riding the horse, not the other way around.
- − The small floating objects in the background feel somewhat disconnected from the main subject.
Verdict: While FLUX1.1 [pro] Ultra produced a much cleaner and higher-quality image, it completely ignored the specific spatial constraint to have the horse on top of the astronaut. FLUX.1 [schnell] successfully followed the difficult prompt logic, creating a surreal image of a horse riding an astronaut, despite having significant anatomical glitches.
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.”
FLUX.1 [schnell]
FLUX1.1 [pro] Ultra
AI Judge Analysis
FLUX.1 [schnell]
- + Excellent character placement and spatial logic
- + High level of fur detail and realistic capybara facial anatomy
- + Perfectly captures the 'bored' expression requested for the passenger
- − The steering wheel is positioned awkwardly beneath the capybara's paw
- − Missing a clear view of BOTH paws on the steering wheel as requested
FLUX1.1 [pro] Ultra
- + Beautiful cinematic lighting and blurred city background
- + Follows the 'both paws on steering wheel' instruction more closely
- + High resolution with sharp details on the capybara's whiskers
- − Major compositional error: the passenger is sitting in the driver's seat/front passenger seat rather than the back
- − The capybara's head is not facing the road
Verdict: FLUX.1 [schnell] followed the spatial instructions much better, correctly placing the human businesswoman in the back seat and the capybara in the driver's seat. FLUX1.1 [pro] Ultra failed the primary compositional request by placing both subjects in the front of the vehicle, which ruins the narrative of the prompt.
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.”
FLUX.1 [schnell]
FLUX1.1 [pro] Ultra
AI Judge Analysis
FLUX.1 [schnell]
- + Strong moody atmosphere with glowing lighting.
- + Followed the request for twisted trees and a foggy night sky well.
- − Numerous spelling errors including 'firiichts' and 'butistigtion'.
- − Text layout is messy with redundant/overlapping date and time lines.
- − Failed to incorporate the 'small scroll' for the subtext.
FLUX1.1 [pro] Ultra
- + Excellent adherence to the 'parchment scroll' and 'spooky border' requests.
- + Near-perfect text rendering for the title and event details.
- + Balanced and professional gothic layout.
- − Minor text repetition below the scroll banner.
- − The border is very busy with thorns, slightly obscuring the background trees.
Verdict: FLUX1.1 [pro] Ultra is the clear winner as it successfully rendered almost all required text accurately and integrated the gothic scroll and border elements beautifully. FLUX.1 [schnell] struggled significantly with text legibility and layout, resulting in a cluttered and nonsensical bottom section.
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.”
FLUX.1 [schnell]
FLUX1.1 [pro] Ultra
AI Judge Analysis
FLUX.1 [schnell]
- + Clean isometric perspective and diorama base
- + Excellent texture on the salmon and rice
- + Adheres well to the request for minimal garnish
- − Failed to include the word 'SUSHI' below 'JAPAN'
- − Lower visual complexity compared to the prompt's potential
FLUX1.1 [pro] Ultra
- + Perfectly followed all text instructions including 'JAPAN', 'SUSHI', and the flag
- + Rich 3D cartoon aesthetic with soft, refined textures
- + Exceptional composition that fills the diorama space effectively
- − Includes slightly more than 'minimal' garnish/items
- − Small inexplicable red insect-like artifact on the wooden board
Verdict: FLUX1.1 [pro] Ultra is the clear winner as it followed every part of the complex prompt, including all text elements and the specific flag placement. While FLUX.1 [schnell] produced a very clean and realistic 3D model, it missed the word 'SUSHI', whereas FLUX1.1 [pro] Ultra captured the '3D cartoon' style perfectly with superior lighting and detail.
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.”
FLUX.1 [schnell]
FLUX1.1 [pro] Ultra
AI Judge Analysis
FLUX.1 [schnell]
- + Successfully included all four requested animals: puppy, kitten, bunny, and fox.
- + Warm color palette and glowing light effects create a joyful mood.
- + Butterfly details are sharp and clearly defined.
- − The 'bunny' looks more like a hybrid kitten-rabbit due to the face shape and ear structure.
- − The composition feels a bit crowded at the bottom center.
FLUX1.1 [pro] Ultra
- + Stronger adherence to the 'god rays' and 'sun sparkles' aspect of the prompt.
- + Superior textures on the fur, particularly on the fox and kitten.
- + Better distinct animal features, specifically with the rabbit ears and facial structures.
- − The kitten and fox share very similar facial profiles and colors, reducing contrast between them.
- − The composition is a bit more static than 'playfully chasing and tumbling'.
Verdict: While both models captured the core essence of the prompt, FLUX1.1 [pro] Ultra produced a much higher quality image with better fur texture and more distinct animal features, particularly the bunny which looked like a hybrid in the other version. FLUX.1 [schnell] had vibrant butterflies, but the lighting and overall 'masterpiece' feel of FLUX1.1 [pro] Ultra was superior.
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.”
FLUX.1 [schnell]
FLUX1.1 [pro] Ultra
AI Judge Analysis
FLUX.1 [schnell]
- + Clean vector aesthetic
- + Minimalist layout
- − Major spelling errors in the brand name and the date
- − Missing requested steam element
FLUX1.1 [pro] Ultra
- + Successfully includes the steam element
- + Higher level of detail and better shading
- + Accurate establishment date
- − Misspelled name as 'Caffé Framilian'
- − Slightly less 'minimalist' than requested due to high detail
Verdict: While both models struggled with the exact name 'Caffè Florian', FLUX1.1 [pro] Ultra produced a significantly higher quality graphic with better textural details and fewer errors. FLUX.1 [schnell] failed on the date and the steam requirement, while the pro model captured more of the prompt's specific instructions.
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.”
FLUX.1 [schnell]
FLUX1.1 [pro] Ultra
AI Judge Analysis
FLUX.1 [schnell]
- + Successfully follows the requested color palette
- + Clean vector style with high-contrast elements
- − Nonsensical infographic flow that does not clearly represent steps 1-6
- − Text is completely illegible and garbled
- − Failed to use consistent or recognizable iconography for the specific mission stages
FLUX1.1 [pro] Ultra
- + Clearly labels the steps and attempts to replicate the requested 1-6 sequence
- + Superior layout with a clear title and structured data points
- + Maintains the flat vector style and NASA-inspired color theme perfectly
- − Text contains several spelling errors and 'AI gibberish' despite having clear labels
- − Includes a strange person-head icon for 'Landing' that does not match the prompt
Verdict: FLUX1.1 [pro] Ultra is the clear winner as it successfully follows the infographic structure and sequential steps requested in the prompt, whereas FLUX.1 [schnell] creates a visual composition that lacks any logical flow. FLUX1.1 [pro] Ultra also features a much more professional layout with a central title and organized captions, even though the text spelling is imperfect.
Next steps
Explore each model
Black Forest Labs' ultra-high resolution image generation model, an enhanced version of FLUX1.1 [pro] optimized for premium quality output