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]
#48 of 62 in Text-to-Image
Nano Banana 2
#1 of 62 in Text-to-Image
Where the votes landed
FLUX.1 [schnell]
0%
win rate
Ties
0%
Nano Banana 2
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 [schnell]
- + Excellent handling of glass thickness and internal reflections.
- + High aesthetic quality with vibrant colors.
- + Accurate lighting direction from the left.
- − Added an extra blue sphere on top of the book that was not requested.
- − The sphere inside the cube is floating rather than sitting on the surface.
Nano Banana 2
- + Perfect adherence to all spatial instructions and object counts.
- + Impressive text rendering on the book spine.
- + Realistic integration of the plant visible through the glass.
- − The glass cube looks more like a small aquarium or display case with visible seams.
- − The lighting is a bit flat compared to the other model.
Verdict: Nano Banana 2 followed the prompt's instructions perfectly, correctly placing a single blue sphere inside the cube and a single red book on top. FLUX.1 [schnell] produced a more polished image with better glass physics, but it failed the logic test by adding a second sphere on top of the book.
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 [schnell]
- + Excellent shallow depth of field effect with smooth bokeh.
- + Highly realistic skin textures and lighting.
- + Clean composition and high resolution.
- − Misses the 'motion blur from passing cars' request as cars look static.
- − The man's interaction with the bicycle handlebars is physically illogical.
- − Lacks the grit and 'candid' feel requested.
Nano Banana 2
- + Much better atmospheric storytelling with realistic tools and bike parts.
- + Captures the 'candid street photo' aesthetic with authentic Japanese signage.
- + Strong adherence to the repair action with a more natural pose.
- − Lower technical image quality with visible noise and softer focus.
- − The wrench is blending strangely into the bicycle chain.
- − Less distinct 'motion blur' from cars than expected, though the overall environment feels more dynamic.
Verdict: Nano Banana 2 succeeds significantly better at capturing the 'candid' and realistic 'no stylization' feel requested, featuring authentic street details and a believable repair scenario. FLUX.1 [schnell] produces a cleaner, higher-quality image, but it feels more like a staged portrait and fails to accurately render the mechanics of the requested action.
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 [schnell]
- + Strong lifelike detail in the eyes and skin texture.
- + Intense, dramatic facial expression that conveys a battle-worn character.
- − The composition is a bit too zoomed in, cutting off most of the requested ornate plate armor.
- − Lacks the requested 'bokeh sparks' in the background.
Nano Banana 2
- + Excellent adherence to all prompt elements including ornate engraved armor, beads in hair, and bokeh sparks.
- + Superior composition that balances the character, weapons, and environment.
- + Highly detailed textures on the leather straps and underlayer fabric.
- − The 'close portrait' instruction is interpreted more as a medium shot than a tight close-up.
- − Slightly less realistic skin pores compared to the competing model.
Verdict: Nano Banana 2 followed the prompt much more accurately, incorporating the specific armor details, hair beads, and environmental effects like sparks that FLUX.1 [schnell] largely ignored. While FLUX.1 [schnell] produced a very high-quality facial study, Nano Banana 2 succeeded in creating the full scene and character 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 [schnell]
- + Strong minimalist aesthetic with clean white space.
- + Accurate sans-serif font choice for headers.
- − Text is largely illegible gibberish.
- − The grid layout of food photos feels repetitive and lacks variety.
Nano Banana 2
- + Exceptional text rendering with legible names, descriptions, and prices.
- + Professional layout that directly maps specific photos to menu items.
- + Vibrant colorful accents that enhance the 'casual dining' feel.
- − Some minor spelling errors in small sub-text (e.g., 'cizza', 'somon').
Verdict: Nano Banana 2 is significantly better, producing a fully functional and highly professional menu design with legible text, realistic food photography, and a logical layout. FLUX.1 [schnell] creates a nice aesthetic shell but fails to generate readable content or a practical information hierarchy.
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 [schnell]
- + Strong photorealistic textures on the main burger patty and bun.
- + Vibrant color palette and good use of depth with the flying crouton-like debris.
- − Failed the text rendering significantly, showing 'AGIC BURGER' and a messy price starburst.
- − The burger is mostly assembled rather than properly 'exploded' as requested.
Nano Banana 2
- + Perfect text rendering with the requested fiery, glowing effects for all required phrases.
- + Excellent 'exploded' composition with clear separation of ingredients and dynamic splashes of sauce.
- + Strong adherence to the background details including embers and smoke.
- − The lighting on the lettuce looks a bit flat and artificial compared to the rest of the image.
Verdict: Nano Banana 2 followed the prompt's structural and textual requirements perfectly, delivering a high-quality 'exploded' layout with crisp, fiery typography. FLUX.1 [schnell] failed on nearly all text elements and did not fully execute the exploded view, resulting in a much weaker ad 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 [schnell]
- + Legible chalk-style handwriting
- + Captures the requested date correctly as 'April 30, 2026' although the word April is misspelled
- − Numerous spelling errors in the menu items like 'Taffle Mushmnctiomn' and 'Octtoopus'
- − The text feels more like a digital pen than actual chalk on a board
- − Composition is very flat and lacks the 'cozy café' background depth
Nano Banana 2
- + Excellent prompt adherence with near-perfect spelling of all complex menu items
- + Highly realistic chalk texture with smudges and natural variations in stroke weight
- + Beautiful environmental composition that captures the 'cozy café' atmosphere
- − The 'cursive' request for the title is interpreted as stylized print rather than traditional connected cursive
Verdict: Nano Banana 2 is the clear winner as it followed the complex text instructions perfectly, including the long menu item descriptions, and captured a realistic chalk texture. FLUX.1 [schnell] struggled significantly with spelling and provided a very basic composition that lacked the requested environmental context.
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 [schnell]
- + Excellent cinematic lighting and atmospheric depth
- + Clean, high-resolution textures on the spacesuit and horse fur
- + Successfully placed the horse on top of the astronaut as requested
- − Anatomical failure resulting in a horse with two heads
- − The composition feels somewhat static despite the surreal concept
Nano Banana 2
- + Dynamic and highly surreal composition with vibrant colors
- + Strong attention to detail in the nebula-filled background
- + Follows the 'horse on top' instruction with a clear rider-steed role reversal
- − The astronaut's leg is clipping through the horse's back irregularly
- − The horse's legs and hooves appear slightly distorted in their orientation
Verdict: FLUX.1 [schnell] creates a more visually polished and 'cinematic' image with superior lighting, but suffers from a major anatomical glitch with a two-headed horse. Nano Banana 2 better captures the 'surreal' and 'riding' aspects of the prompt with more active posing, even though it has minor clipping issues and a noisier style.
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 [schnell]
- + Excellent fur texture rendering
- + Deep cinematic lighting and color
- − Anatomy error with the paws (only one visible, appearing to sprout from the chest)
- − Poorly rendered 'TAXI' text on the visor
- − Capybara is facing the camera rather than looking at the road
Nano Banana 2
- + Outstanding prompt adherence with both paws on the steering wheel
- + Exceptional attention to detail with the NYC hack license and taxi meter
- + Complex and realistic wide-angle composition from the dashboard
- − The driver's hat is black/dark blue instead of the requested yellow
- − Slightly less 'photorealistic' fur compared to FLUX
Verdict: Nano Banana 2 was the clear winner for its incredible environmental storytelling and technical accuracy, including a custom hack license for 'Captain Cappy' and the correct placement of paws on the wheel. While FLUX.1 [schnell] had more realistic lighting and fur, it failed on basic anatomy and the capybara looked more like a passenger in a costume than a driver.
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 [schnell]
- + Strong cinematic lighting with a vibrant glowing jack-o-lantern.
- + The background art of the twisted trees and bats has a nice moody silhouette.
- − Significant text issues including misspellings ('firiiichts') and repetitive/garbled information for the time and location.
- − The layout feels unbalanced with large empty spaces and disconnected elements.
Nano Banana 2
- + Perfect text rendering for all requested strings with beautiful gothic typography.
- + Rich compositional detail including a gothic cathedral, skulls, and a highly intricate thorny bordner with webs.
- + Strong source preservation of the 'vintage parchment' feel across the whole image.
- − The jack-o-lantern is slightly off-center, though this is a minor artistic choice.
Verdict: Nano Banana 2 followed the prompt perfectly, delivering all requested text accurately and within a highly detailed, professional-looking illustration. FLUX.1 [schnell] struggled significantly with the text, producing hallucinations and repetitive lines, while its overall composition lacked the vintage parchment aesthetic requested. Nano Banana 2 is the clear winner for its superior layout and text fidelity.
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 [schnell]
- + Excellent 3D miniature diorama aesthetic
- + Perfectly clean and minimal layout
- + Accurate 45° isometric perspective
- − Missed the word 'SUSHI' in the text
- − The salmon texture on top looks a bit messy and lacks the 'refined' quality of the rice
Nano Banana 2
- + Successfully included all requested text and the flag icon
- + High variety of 3D sushi models with great material detail
- + Composed with a beautiful, rich diorama base
- − Does not strictly follow the 45° isometric requirement, opting for a standard 3D perspective
- − Slight overlap issue with the sushi on the right side of the board
Verdict: Nano Banana 2 is the better overall image as it adhered to all text instructions, including the word 'SUSHI' which FLUX.1 [schnell] omitted. While FLUX.1 [schnell] captured the isometric 'miniature' look more accurately according to technical definitions, Nano Banana 2 provided a much more complete and visually interesting interpretation of the prompt's subject matter.
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 [schnell]
- + Features very vibrant, warm golden lighting.
- + Highly detailed fur texture on all animals.
- + Expressive and endearing facial features.
- − Failed to include the requested baby bunny.
- − The animal in the middle appears to be a hybrid between a kitten and a fox/bunny/cat, lacking species clarity.
- − The composition feels a bit static and posed rather than playful.
Nano Banana 2
- + Successfully included all four requested animals: puppy, kitten, bunny, and fox.
- + Captures the 'playfully chasing' and 'tumbling' movement much better than image A.
- + Excellent use of god rays and dew sparkles in a realistic manner.
- − The fox's front right leg has a some anatomical blurring with the grass.
- − The lighting is slightly less stylized which some might find less 'masterpiece' like.
Verdict: Nano Banana 2 is the clear winner as it followed the prompt precisely, including the specific list of animals (puppy, kitten, fox, and bunny) which FLUX.1 [schnell] failed to do. Nano Banana 2 also better captured the requested action of the animals playing and tumbling, whereas FLUX.1 [schnell] presented a clustered, static group portrait.
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 [schnell]
- + Clean vector aesthetic
- + Good use of warm brown tones
- − Significant text errors including 'FRAMILAN' instead of 'Florian'
- − Incorrect date '7720'
- − Missing the steam element requested in the prompt
Nano Banana 2
- + Perfect text accuracy for both the brand name and the date
- + Includes all prompt elements like the steam and the banner
- + Excellent vintage texture and sophisticated woodcut-style illustration
- − Slightly more complex than a 'minimalist' logo, though very fitting for the theme
Verdict: Nano Banana 2 is the clear winner as it followed every instruction in the prompt, rendering the text perfectly. FLUX.1 [schnell] failed significantly on the text, misspelling the name as 'FRAMILAN' and the year as '7720', while also omitting the requested steam.
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 [schnell]
- + Successfully follows the requested navy color palette.
- + Includes a visually interesting centralized composition.
- − Failed to include 6 distinct steps as separate icons.
- − Text is completely illegible and nonsensical.
- − The rocket icon looks more like a shuttle or stylized plane than a Saturn V.
Nano Banana 2
- + Perfectly follows all 6 requested steps with accurate iconography.
- + Excellent text rendering for headings and labels.
- + Strict adherence to the modern vector style and NASA-inspired palette.
- − Minor layout imbalance with the landing section being smaller than the header icons.
- − The crew section includes a fourth silhouetted figure which is historically inaccurate.
Verdict: Nano Banana 2 followed the prompt instructions near-perfectly, providing all six requested infographic steps with crisp lines and legible text. FLUX.1 [schnell] failed to logically sequence the steps and produced garbled text that is unusable for a functional infographic. Nano Banana 2 is the clear winner for its superior prompt adherence and layout execution.
Explore each model
Gemini 3.1 Flash with image generation capabilities. High-efficiency image generation model with support for text rendering, reference images, search grounding, and thinking mode. The efficient counterpart to Gemini 3 Pro Image.