Black Forest Labs' ultra-high resolution image generation model, an enhanced version of FLUX1.1 [pro] optimized for premium quality output
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
FLUX1.1 [pro] Ultra
18.5
arena score
#49 of 62 in Text-to-Image
Skill signature
· Text-to-Image
Nano Banana 2
28.4
arena score
#1 of 62 in Text-to-Image
Best Text-to-Image right now
Top 2 in Image Editing
Vote tally
Where the votes landed
FLUX1.1 [pro] Ultra
0%
win rate
Ties
0%
Nano Banana 2
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.”
FLUX1.1 [pro] Ultra
Nano Banana 2
AI Judge Analysis
FLUX1.1 [pro] Ultra
- + Excellent glass physics with realistic refraction and edge highlights
- + High-fidelity textures on the book leather and table surface
- + Clean, minimalist composition that feels professional
- − The sphere is levitating rather than sitting on the bottom of the cube
- − The plant behind the glass is somewhat blurry and less distinct
Nano Banana 2
- + Perfect adherence to physics with the sphere resting on the bottom
- + Exceptional text rendering on the book spine
- + Realistic room environment with natural window light
- − The cube edges look more like a glass tank/aquarium than a solid glass cube
- − The proportions of the cube feel slightly tall and narrow
Verdict: Both models followed the prompt instructions perfectly, including the placement of objects and lighting direction. FLUX1.1 [pro] Ultra produced a more aesthetically pleasing, clean image with superior glass shaders, while Nano Banana 2 excelled in logic by placing the sphere on the floor of the cube and rendering legible text on 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.”
FLUX1.1 [pro] Ultra
Nano Banana 2
AI Judge Analysis
FLUX1.1 [pro] Ultra
- + Excellent execution of long-exposure motion blur on passing vehicles.
- + High fidelity in the man's expression and clothing texture.
- + Composition feels very clean and professional.
- − The man appears to just be touching the bike rather than actively repairing it.
- − The background cars and architecture feel generic rather than specifically Japanese.
Nano Banana 2
- + Perfect adherence to the 'repairing' prompt with tools and a realistic squatting posture.
- + Strong sense of place with authentic Japanese signage and street environment.
- + Film-like grain and color grading match the 'candid street photo' request.
- − Missed the request for motion blur from passing cars.
- − There are minor anatomical artifacts in the fingers holding the wrench.
Verdict: Nano Banana 2 captures the authentic candid atmosphere and cultural context much better than the competitor, showing a man actually performing a repair with tools. FLUX1.1 [pro] Ultra has superior technical resolution and motion blur effects, but the scene feels staged and the man is not actually repairing the bicycle.
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.”
FLUX1.1 [pro] Ultra
Nano Banana 2
AI Judge Analysis
FLUX1.1 [pro] Ultra
- − Failed to render any image content.
- − Output is a completely black image.
Nano Banana 2
- + Excellent adherence to the complex prompt including braids with beads, scars, and ornate armor.
- + Impressive textural detail on the leather straps and the metallic engraving.
- + Strong atmosphere created by the torchlight reflection and bokeh sparks.
- − The sword hand has some slight anatomical inconsistencies in the finger positioning.
- − The face is a bit heavily shadowed, which might obscure some of the requested 'lifelike eyes' detail.
Verdict: FLUX1.1 [pro] Ultra failed to generate a visible image, providing only a black screen. Nano Banana 2 successfully captured every element of the prompt with high fidelity, creating a gritty and atmospheric portrait with exceptional detail in the armor and character features.
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.”
FLUX1.1 [pro] Ultra
Nano Banana 2
AI Judge Analysis
FLUX1.1 [pro] Ultra
- + Clean minimalist aesthetic with plenty of white space
- + Professional 3D mockup presentation
- + High-quality, vibrant food photography
- − Nonsensical text and spelling errors throughout
- − Poor text alignment in the description sections
- − Fragmented layout that feels slightly disjointed
Nano Banana 2
- + Excellent typography with nearly perfect legibility
- + Superior adherence to the grid-based food photo request
- + Cohesive design that looks like a real-world functional menu
- − The layout extends a bit close to the bottom edge
- − The food images are slightly less vibrant than Model A
Verdict: Nano Banana 2 is the clear winner because it generates actual readable text and follows the layout instructions with high precision, including the specific sections requested. While FLUX1.1 [pro] Ultra has a stylish mockup feel, its text is illegible and the layout is messy by comparison.
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.”
FLUX1.1 [pro] Ultra
Nano Banana 2
AI Judge Analysis
FLUX1.1 [pro] Ultra
- + Excellent photorealistic texture on the meat and buns
- + Perfect text rendering with high legibility
- + Clean composition with a sophisticated color balance
- − Missed the starburst requirement for the price tag
- − The burger height is slightly unrealistic with too many repeating patties
Nano Banana 2
- + Highly accurate adherence to all elements including the starburst and fiery text effect
- + Excellent sense of motion and dynamic splash effects
- + Background perfectly matches 'dark, fiery with glowing embers' instruction
- − The '6' in the price tag has a slight visual artifact
- − The text 'MAGIC BURGER' is a bit cluttered with the fire effects
Verdict: FLUX1.1 [pro] Ultra produces a cleaner, more commercial-looking image with superior texture rendering, though it missed the starburst requirement. Nano Banana 2 followed the prompt's layout instructions more closely, including the starburst and specific fiery text effects, resulting in a more 'dynamic' advertising feel. Nano Banana 2 is the winner for its better adherence to the specific formatting and background elements requested in the prompt.
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.”
FLUX1.1 [pro] Ultra
Nano Banana 2
AI Judge Analysis
FLUX1.1 [pro] Ultra
- + Natural wood framing and simple composition
- + Accurate date rendering
- − Significant spelling errors and repetitions (e.g., 'fresh fresh daily', 'mushroomm')
- − Text becomes illegible gibberish in several lines
- − Flat blackboard texture lacks authentic chalk dust smears
Nano Banana 2
- + Excellent spelling accuracy for a complex menu prompt
- + Superior chalk texture with realistic smears and dusting
- + High-quality 'cozy café' background with appropriate depth of field
- − Included a slight flourish/border not explicitly requested
- − Layout is quite tight at the bottom of the board
Verdict: Nano Banana 2 is the clear winner as it successfully rendered all the requested text with near-perfect spelling and a highly realistic chalk texture. FLUX1.1 [pro] Ultra suffered from significant hallucinations, repeating words and generating nonsensical text strings in the middle of the menu items.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
FLUX1.1 [pro] Ultra
Nano Banana 2
AI Judge Analysis
FLUX1.1 [pro] Ultra
- + Excellent visual clarity and cinematic lighting
- + Clean, balanced composition with high detail
- + Natural look to the horse's musculature and the astronaut's suit
- − Failed to follow the logical constraint 'horse on top'
- − Standard interpretation rather than the requested surreal arrangement
Nano Banana 2
- + Correctly followed the specific instruction 'horse on top'
- + Achieved a more surreal atmosphere as requested
- + Glow effects and starfield are vibrant and detailed
- − Anatomical issues with the astronaut's limbs and harness integration
- − Lower resolution and less 'cinematic' polish compared to the competitor
- − The tether/reins have confusing geometry
Verdict: While FLUX1.1 [pro] Ultra produced a much higher quality image with superior clarity and lighting, it completely failed to follow the specific spatial instruction for the horse to be on top. Nano Banana 2 successfully interpreted the 'horse on top' constraint and the 'surreal' descriptor, despite having more technical glitches in the character anatomy and harness details.
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.”
FLUX1.1 [pro] Ultra
Nano Banana 2
AI Judge Analysis
FLUX1.1 [pro] Ultra
- + Excellent fur texture rendering
- + Cinematic lighting consistent with a professional camera
- − Failed the spatial logic by placing the passenger in a second front seat with a steering wheel
- − Very poor prompt adherence regarding the passenger sitting in the back seat
Nano Banana 2
- + Perfectly follows all spatial instructions including the passenger in the back seat
- + Rich in relevant environmental details like the taxi meter and NYC license
- + Realistic placement of paws on the steering wheel
- − The cap is black instead of the requested yellow
- − The texture of the woman's face is slightly less detailed than Model A
Verdict: Nano Banana 2 followed the complex spatial instructions of the prompt much better than FLUX1.1 [pro] Ultra, which incorrectly placed the human passenger in a front seat with a second steering wheel. Nano Banana 2 also added creative and realistic details like the hack license and taxi meter which enhanced the storytelling.
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.”
FLUX1.1 [pro] Ultra
Nano Banana 2
AI Judge Analysis
FLUX1.1 [pro] Ultra
- + Excellent clean typography on the date and location details
- + Effective use of the scroll motif to contain the invitation text
- + Clear adherence to the twisted trees and thorns description
- − The main title is missing the word 'Party'
- − Contains significant hallucinated text ('noickt or a night of frights') repeated below the banner
- − The layout feels a bit sparse in the middle
Nano Banana 2
- + Perfect adherence to all text requirements including the full title
- + Sophisticated composition with rich details like skulls and a gothic archway
- + Strong vintage gothic aesthetic with excellent gold-tinted glow on text
- − Small spider details look slightly repetitive
- − The bottom text alignment is a bit unconventional
Verdict: Nano Banana 2 is the clear winner as it perfectly follows the complex text instructions without hallucinations, whereas FLUX1.1 [pro] Ultra misses a keyword in the title and adds gibberish text. Nano Banana 2 also provides a more visually dense and atmospheric composition that feels like a complete piece of art.
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.”
FLUX1.1 [pro] Ultra
Nano Banana 2
AI Judge Analysis
FLUX1.1 [pro] Ultra
- + Excellent 3D miniature style with soft, stylized PBR textures.
- + Clean isometric composition on a square raised diorama base.
- − Text is somewhat transparent and harder to read against the background.
- − Includes unnecessary elements like a plant and random steam.
Nano Banana 2
- + Strong typography and clear visibility of the national flag.
- + Very high detail in the food textures and realistic wooden materials.
- + Precise adherence to the text placement and content requested.
- − The circular plate under the rectangular board makes the 'diorama base' feel slightly cluttered.
- − The photography style leans more toward realistic macro than 'cartoon scene'.
Verdict: FLUX1.1 [pro] Ultra better captured the requested 'cartoon scene' and 'miniature' aesthetic with its soft lighting and stylized models. However, Nano Banana 2 adhered more closely to the specific text layout and provided a much more realistic interpretation of the PBR materials, making it a stronger technical match for the prompt's layout requirements.
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.”
FLUX1.1 [pro] Ultra
Nano Banana 2
AI Judge Analysis
FLUX1.1 [pro] Ultra
- + Captures a very whimsical and cute aesthetic with expressive wide eyes.
- + Excellent rendering of soft, backlit fur textures.
- + Warm, consistent lighting with a dreamlike quality.
- − Fails to show the animals 'playfully chasing' or 'tumbling', as they are mostly sitting still.
- − The animals look more like stylised plush toys than 'hyper-photorealistic' real animals.
- − Repeated anatomy issues, particularly with the paw count on the kitten.
Nano Banana 2
- + Perfect adherence to the 'playfully chasing and tumbling' action described in the prompt.
- + Maintains a much higher degree of photorealism for the animal breeds.
- + Beautiful execution of 'god rays' and dew sparkles on the meadow grass.
- − The blue butterfly has some slight artifacts/blurring around the edges.
- − The kitten's tail is slightly merged with the background lighting effects.
Verdict: Nano Banana 2 is the clear winner as it successfully captures the dynamic action of the animals chasing butterflies, whereas FLUX1.1 [pro] Ultra produced a static, albeit cute, portrait. Nano Banana 2 also achieved a much higher level of realism in the fur and environment, adhering perfectly to the 8K masterpiece and photorealistic requirements.
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.”
FLUX1.1 [pro] Ultra
Nano Banana 2
AI Judge Analysis
FLUX1.1 [pro] Ultra
- + Excellent vector-style illustration of the cloche dome
- + Sophisticated warm brown and cream color palette
- + High-quality subtle texture on the background
- − Missed the spelling of the core name, rendering it as 'Caffé Framilian'
Nano Banana 2
- + Perfect text accuracy for both 'Caffè Florian' and 'Est. 1720'
- + Beautifully executed vintage ribbon/banner element
- + Balanced minimalist composition that fits the logo prompt well
- − The line work on the cloche is slightly less refined than the competitor
Verdict: While FLUX1.1 [pro] Ultra produced a more polished and visually striking vector illustration, it failed at the basic requirement of spelling the requested name correctly. Nano Banana 2 adhered perfectly to all text requirements and captured the vintage aesthetic with a superior banner design, making it the more successful logo overall.
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.”
FLUX1.1 [pro] Ultra
Nano Banana 2
AI Judge Analysis
FLUX1.1 [pro] Ultra
- + Excellent typography and large title rendering
- + Creative layout with a planetary surface base
- − Step numbering is chaotic and non-linear
- − Visual style is inconsistent with some 3D-like elements mixed with flat icons
- − Nonsensical text in the body and descriptions
Nano Banana 2
- + Perfect adherence to chronological steps 1 through 6
- + Consistent, high-quality flat-vector iconography
- + Accurate legibility of names and mission locations
- + Strict adherence to the requested NASA-inspired color palette
- − Composition feels slightly crowded in the bottom left corner
Verdict: Nano Banana 2 followed the prompt's logical structure perfectly, delivering a clean and usable infographic with legible text and consistent iconography. FLUX1.1 [pro] Ultra created a visually striking image, but failed significantly on the informational structure, producing jumbled numbers and largely illiterate text.
Next steps
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.