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
Nano Banana Pro
28.1
arena score
#2 of 62 in Text-to-Image
Best Image Editing right now
Top 2 in Text-to-Image
Vote tally
Where the votes landed
FLUX.1 [schnell]
0%
win rate
Ties
0%
Nano Banana Pro
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]
Nano Banana Pro
AI Judge Analysis
FLUX.1 [schnell]
- + Excellent clean aesthetic and vibrant colors.
- + High-quality rendering of the Monstera plant and window light.
- + Unique modern design for the objects.
- − Failed prompt instructions by placing an extra blue sphere on top of the red book.
- − The large blue sphere inside appears to be floating unnaturally.
Nano Banana Pro
- + Perfect adherence to the spatial prompt instructions.
- + Highly realistic lighting and photographic textures.
- + Convincing glass refraction and plant visibility through the cube.
- − The composition feels slightly more cluttered compared to the clean look of the other model.
Verdict: Nano Banana Pro followed all spatial instructions perfectly, including the specific placement of the small blue sphere and the red book, whereas FLUX.1 [schnell] hallucinated an additional sphere on top of the book. Nano Banana Pro also achieved a much higher level of photographic realism and accurate glass physics.
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]
Nano Banana Pro
AI Judge Analysis
FLUX.1 [schnell]
- + Excellent high-resolution detail on the skin and clothing.
- + Strong adherence to the 'reflections on wet pavement' prompt with realistic light streaks.
- + Very clear and structurally sound bicycle rendering.
- − The background cars are too static, missing the requested 'motion blur'.
- − The man appears more Caucasian than Japanese, missing the specific demographic prompt.
- − The composition feels slightly too staged rather than a 'candid street photo'.
Nano Banana Pro
- + Perfectly captures the 'imperfect framing' and 'candid street photo' aesthetic.
- + Authentic representation of a Japanese man and a typical Japanese street scene.
- + Includes visible rain droplets and motion blur in the background as requested.
- − Lower resolution with more grain/noise compared to model A.
- − The bicycle's rear structure is a bit physically confusing near the seat/fender.
Verdict: Nano Banana Pro significantly outperformed FLUX.1 [schnell] in following the specific atmospheric and aesthetic requirements of the prompt, successfully delivering the candid, rainy, and motion-blurred street scene. While FLUX.1 [schnell] produced a cleaner and more detailed image, it failed to accurately represent the subject's ethnicity and ignored the motion blur request.
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]
Nano Banana Pro
AI Judge Analysis
FLUX.1 [schnell]
- + Intense facial expression and piercing lifelike eye detail
- + Very clean, high-resolution skin texture
- + Strong composition with a focus on the character's gaze
- − Missed the request for beads in the hair braids
- − The plate armor is barely visible in the crop
- − Includes some facial skin artifacts that look over-sharpened
Nano Banana Pro
- + Excellent adherence to all prompt elements including beads, scars, dirt, and sparks
- + Beautifully detailed engraved plate armor that feels authentic
- + Very clear depiction of the cloth underlayer and leather straps
- − The torch in the foreground is slightly distracting with its blurriness
- − Skin texture is slightly less sharp than Model A
Verdict: Model B (Nano Banana Pro) provided a much more complete adherence to the prompt, successfully incorporating the braided beads, extensive armor detail, and bokeh sparks. While Model A (FLUX.1 [schnell]) has a more striking and intimate facial capture, it missed several specific descriptors from the request.
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]
Nano Banana Pro
AI Judge Analysis
FLUX.1 [schnell]
- + Clean, professional minimalist layout
- + Effective use of white space
- + Includes specific headers for Pizza and Mains as requested
- − Text is largely gibberish or illegible except for headers
- − Image grid is slightly repetitive with mostly pizza-looking dishes
Nano Banana Pro
- + Excellent typography with mostly legible and relevant text
- + Clear organization of sections into a functional grid layout
- + High-quality, distinct food photos that match the categories well
- − Small minor spelling errors in some dish names
- − Layout is a bit denser, leaning slightly away from minimalist
Verdict: Nano Banana Pro is the winner because it successfully integrates high-quality food photography with mostly legible text that follows the prompt's structural requirements. FLUX.1 [schnell] creates a visually pleasing minimalist aesthetic but fails significantly on text execution, providing mostly unreadable filler.
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]
Nano Banana Pro
AI Judge Analysis
FLUX.1 [schnell]
- + Excellent photorealistic lighting and texture on the burger bun and meat.
- + Dynamic composition with embers and a strong sense of depth.
- + Included all requested text elements and currency.
- − Significant spelling error in the main title ('AGIC' instead of 'MAGIC').
- − Price text is repetitive and cluttered at the bottom.
- − The burger is mostly assembled rather than 'exploded' as requested.
Nano Banana Pro
- + Perfect adherence to the 'exploded' burger concept with vertically suspended layers.
- + Text rendering is flawless and follows the 'fiery, glowing' stylistic instructions exactly.
- + Balanced, professional ad layout with a clear focal point.
- − The meat patty looks slightly less detailed/textured compared to Model A.
- − A few minor digital artifacts in the sauce splash.
Verdict: Nano Banana Pro followed the prompt instructions much better than FLUX.1 [schnell], specifically by correctly spelling 'MAGIC BURGER' and delivering the requested 'exploded' burger view. While FLUX.1 [schnell] had impressive textures, the spelling error and lack of structural deconstruction make it a poorer advertisement.
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]
Nano Banana Pro
AI Judge Analysis
FLUX.1 [schnell]
- + Natural handwriting style with realistic chalk texture
- + Good composition of the chalkboard frame
- − Significant spelling errors throughout the text
- − Failed to include the full year and date correctly as 'April 30, 2026'
- − Messy repetitions and gibberish in the bottom half of the board
Nano Banana Pro
- + Excellent prompt adherence with near-perfect spelling and date accuracy
- + Beautiful chalk texture including realistic smudges on the board
- + Superior background composition showing a cozy café atmosphere
- − The text style leans slightly toward a digital font aesthetic rather than rough handwriting
- − The 'elegant cursive' request for the title was not fully met, as it is a slanted print style
Verdict: Nano Banana Pro is the clear winner as it accurately followed all text instructions, including specific prices and food items with perfect spelling. FLUX.1 [schnell] struggled heavily with the text content, resulting in numerous spelling errors and gibberish that made the menu unreadable.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
FLUX.1 [schnell]
Nano Banana Pro
AI Judge Analysis
FLUX.1 [schnell]
- + Excellent adherence to the 'horse on top' spatial instruction
- + Cinematic lighting and high-quality textures on the space suit
- + Stronger surrealist interpretation of the rider/mount dynamic
- − The horse has two heads/torsos fused together
- − Anatomical failure where the horse's tail grows out of the astronaut's pack
Nano Banana Pro
- + Atmospheric background with diverse space elements like nebulae and satellites
- + Anatomically correct horse model
- + Creative addition of a cape that matches the galaxy background
- − Fails the specific 'horse riding astronaut' instruction, showing the astronaut holding the horse up instead
- − The composition feels like a collage with inconsistent lighting sources
Verdict: FLUX.1 [schnell] followed the difficult spatial prompt of the horse riding the astronaut much better than Nano Banana Pro, which depicted the astronaut carrying the horse. While Nano Banana Pro has better horse anatomy, FLUX.1 [schnell] captures the 'surreal' and 'cinematic' aspects of the prompt through superior lighting and a tighter composition.
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]
Nano Banana Pro
AI Judge Analysis
FLUX.1 [schnell]
- + Excellent photographic quality and lighting
- + Captures the bored expression of the passenger perfectly
- + The capybara's fur detail is highly realistic
- − Failed to place both paws on the steering wheel correctly; only one is visible and positioned awkwardly
- − The perspective makes the capybara look slightly too large for the vehicle interior
Nano Banana Pro
- + Strong composition showing both the taxi meter and the full scene within the car
- + Accurately places both paws on the steering wheel as requested
- + The hat and jacket styling look very grounded and realistic
- − The passenger's face is slightly distorted and less detailed
- − The overall lighting is a bit flat compared to Model A
Verdict: Model B (Nano Banana Pro) wins because it successfully navigates the complex spatial logic of the scene, including the positioning of the steering wheel and both paws, and provides a more comprehensive car interior. While Model A (FLUX.1 [schnell]) has superior texture and lighting quality, it fails the specific prompt instruction to have both paws on the steering wheel.
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]
Nano Banana Pro
AI Judge Analysis
FLUX.1 [schnell]
- + Strong cinematic lighting on the jack-o-lantern.
- + Clear, legible typography for the date and location.
- − Numerous spelling errors including 'a a night of frights', 'firiichts', and 'butistigtion'.
- − Text layout is repetitive and cluttered at the bottom.
- − The border and parchment texture are less pronounced than requested.
Nano Banana Pro
- + Excellent adherence to the 'vintage dark parchment' aesthetic with distressed edges.
- + Perfect text rendering of the title, banner, and event details.
- + Highly detailed border consisting of thorns, webs, and spiders as requested.
- − The jack-o-lantern stem is slightly distorted.
- − The composition is very centered and symmetrical, which might feel a bit static to some.
Verdict: Nano Banana Pro followed the prompt perfectly, delivering an authentic vintage parchment look with complex borders and accurate text. In contrast, FLUX.1 [schnell] struggled significantly with the text, producing incoherent sentences and repetitive data lines while failing to capture the 'vintage gothic' texture as effectively.
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]
Nano Banana Pro
AI Judge Analysis
FLUX.1 [schnell]
- + Excellent 3D miniature diorama feel with clean PBR textures
- + High clarity and minimalist composition that feels very professional
- + Accurate 45-degree isometric projection
- − Failed to include the word 'SUSHI' below the JAPAN text
- − The sushi roll presentation looks a bit lonely on the large base
Nano Banana Pro
- + Followed all text instructions including 'JAPAN' and 'SUSHI'
- + Includes a diverse and visually appealing platter of different sushi types
- + Beautiful artistic details like cherry blossoms and moss on the base
- − Text layout is slightly less clean with the flag placement
- − Slightly busier than the 'minimalist' request preferred
Verdict: Nano Banana Pro is the winner because it successfully followed all text-related instructions, whereas FLUX.1 [schnell] omitted the word 'SUSHI'. Nano Banana Pro also provided a more rich and interesting interpretation of the sushi platter while still maintaining the requested 3D miniature isometric style.
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]
Nano Banana Pro
AI Judge Analysis
FLUX.1 [schnell]
- + Warm, cinematic lighting with a soft bokeh effect
- + Excellent fur texture on the puppy and fox
- − Failed to generate a bunny, instead creating two cat-like creatures
- − The animals are mostly static rather than chasing butterflies
- − Anatomical issues with the center-right creature
Nano Banana Pro
- + Successfully included all four requested animals: puppy, kitten, bunny, and fox
- + Strong dynamic composition that captures the 'running and chasing' action
- + Captures the god rays and dew sparkles mentioned in the prompt
- − The kitten looks slightly less realistic compared to the other animals
- − Visible AI artifacts around the butterfly's wings and antenna
Verdict: Nano Banana Pro is the clear winner as it successfully followed the complex prompt by including all four distinct animal species (puppy, kitten, bunny, and fox), whereas FLUX.1 [schnell] missed the bunny entirely. Nano Banana Pro also better captured the dynamic energy of 'chasing and tumbling' in a lush environment with clear god rays.
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]
Nano Banana Pro
AI Judge Analysis
FLUX.1 [schnell]
- + Strong minimalist vector aesthetic
- + Clean symmetrical composition
- + Excellent color palette consistency
- − Significant spelling errors in the brand name and date
- − Missing the requested steam element
- − Typography is a bit generic
Nano Banana Pro
- + Perfect adherence to text and date prompts
- + Beautiful illustrative style with steam and texture
- + Excellent typography and banner integration
- − Slightly less 'minimalist' than the other model
- − Small shading artifact on the left side of the cloche
Verdict: Nano Banana Pro followed every aspect of the prompt, including the specific name, date, and visual elements like steam, whereas FLUX.1 [schnell] failed significantly on text accuracy and omitted the steam. Nano Banana Pro also provided a more appealing vintage texture that fits the 'classic' theme better.
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]
Nano Banana Pro
AI Judge Analysis
FLUX.1 [schnell]
- + Strong minimalist vector aesthetic
- + Follows the NASA-inspired color palette effectively
- + Clean layout that feels like a modern art poster
- − Text is largely illegible gibberish
- − Fails to follow the specific 6-step sequence requested in the prompt
- − Iconography is abstract and doesn't clearly represent the Saturn V or Lunar Module
Nano Banana Pro
- + Exceptional text rendering and adherence to the 6-step sequence
- + Highly accurate iconography representing the Saturn V and Lunar Module
- + Excellent information design that functions as a real infographic
- − Slightly more cluttered composition compared to a minimalist poster style
- − Small inconsistencies in line thickness between different icons
Verdict: Nano Banana Pro significantly outperforms FLUX.1 [schnell] by following every instruction in the prompt, including the specific 6-step infographic sequence and legible text. While FLUX.1 [schnell] captures a nice minimalist aesthetic, its failure to generate readable information or accurate mission steps makes it unsuccessful as an infographic.
Next steps
Explore each model
Gemini 3 Pro with image generation capabilities. Combines advanced reasoning with the ability to generate and edit images.