Gemini 3 Pro with image generation capabilities. Combines advanced reasoning with the ability to generate and edit images.
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
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
Skill signature
· Text-to-Image
Stable Diffusion 3.5 Large Turbo
10.7
arena score
#61 of 62 in Text-to-Image
Vote tally
Where the votes landed
Nano Banana Pro
0%
win rate
Ties
0%
Stable Diffusion 3.5 Large Turbo
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.”
Nano Banana Pro
Stable Diffusion 3.5 Large Turbo
AI Judge Analysis
Nano Banana Pro
- + Excellent photorealism with natural textures and lighting.
- + Higher adherence to spatial reasoning with the red book sitting on top of the cube.
- + Accurate glass refraction and transparency showing the plant behind.
- − The glass cube looks more like a small aquarium or display case without a front panel.
Stable Diffusion 3.5 Large Turbo
- + Clean, modern aesthetic with sharp lines.
- + Good lighting and shadow work on the table surface.
- − Failed the spatial prompt: the red book is inside the cube rather than on top of it.
- − The glass is barely visible, appearing more like an open frame.
- − The green plant is to the side rather than behind the cube.
Verdict: Nano Banana Pro followed all spatial instructions accurately, correctly placing the red book on top of the cube and the plant behind it, while maintaining a highly photorealistic style. Stable Diffusion 3.5 Large Turbo failed multiple spatial requirements, placing the book inside the cube and the plant to the left, and its overall finish looks more like a CGI render than a photograph.
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.”
Nano Banana Pro
Stable Diffusion 3.5 Large Turbo
AI Judge Analysis
Nano Banana Pro
- + Exceptional realism with natural skin textures and film-like quality.
- + Accurately captures complex environmental details like rain reflections and motion blur.
- + Perfectly adheres to the 'candid' and 'imperfect framing' requirements.
- − None notable; the image provides a highly convincing photographic look.
Stable Diffusion 3.5 Large Turbo
- + Correctly identifies the main subjects: a man and a red bicycle.
- + Clear focus on the central figure.
- − Lacks the requested 'candid street' and 'motion blur' effects, appearing static and synthetic.
- − Significant anatomical errors, particularly with the man's head/neck and hand placement.
- − The environment lacks the requested rain-slicked pavement reflections and photographic depth.
Verdict: Nano Banana Pro produced a photo-realistic image that perfectly captures the mood, lighting, and technical specifications of the prompt, including complex elements like motion blur and wet pavement reflections. In contrast, Stable Diffusion 3.5 Large Turbo failed on nearly every quality metric, producing a distorted figure with significant anatomical issues and a clean, 'CG' look that ignored the requested photographic imperfections.
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.”
Nano Banana Pro
Stable Diffusion 3.5 Large Turbo
AI Judge Analysis
Nano Banana Pro
- + Excellent adherence to all prompt details including beads in braids and battle-worn textures
- + Superior lighting and atmospheric integration with realistic torchlight reflections
- + Exceptional detail on the engraved armor and weathered skin textures
- − The sparks around the light source are a bit uniform in size
Stable Diffusion 3.5 Large Turbo
- + Good interpretation of the ornate armor engraving
- + Strong color contrast and bold composition
- − Missed the request for beads in the hair
- − The skin and 'blood' marks look plastic and lacks realistic texture
- − The lighting on the face is inconsistent with a torchlight source
Verdict: Nano Banana Pro delivered a significantly more realistic and detailed image that followed every aspect of the prompt, including specific details like beads in the hair. Stable Diffusion 3.5 Large Turbo produced a much more stylized, almost CGI-like result with flat skin textures and missed Several key descriptors.
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.”
Nano Banana Pro
Stable Diffusion 3.5 Large Turbo
AI Judge Analysis
Nano Banana Pro
- + Strict adherence to all prompt requirements including category sections (Appetizers, Pizza, Mains).
- + Highly legible and realistic typography for headings and prices.
- + Clean, professional grid layout that functions as a real-world menu design.
- − Small body text contains some gibberish characters.
- − The 'Chicken Pizza' photo appears to be pasta rather than a pizza.
Stable Diffusion 3.5 Large Turbo
- + High-contrast, vibrant food photography with a modern aesthetic.
- + Creative top-down composition that feels like a professional food photography spread.
- − Failed to create a unified menu layout, instead producing fragmented sheets and scattered items.
- − Text is completely illegible and contains spelling errors in headers (e.g., 'Mians').
- − Poor logical organization of the requested grid and sections.
Verdict: Nano Banana Pro successfully followed the prompt, delivering a functional and well-structured menu design with clear sections for Appetizers, Pizza, and Mains. Stable Diffusion 3.5 Large Turbo failed to create a cohesive document, producing a scattered array of food items and illegible text fragments that do not resemble a professional menu layout.
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.”
Nano Banana Pro
Stable Diffusion 3.5 Large Turbo
AI Judge Analysis
Nano Banana Pro
- + Excellent text rendering with no spelling errors
- + Accurate exploded view with clearly separated ingredients
- + High photorealistic detail in the food textures
- + Perfect adherence to the starburst pricing requirement
- − The 'fiery' effect on the text is slightly uniform and neon-like
Stable Diffusion 3.5 Large Turbo
- + Dynamic fire and smoke effects
- + Vibrant colors and high contrast
- − Completely failed to include any text or the starburst
- − Failed the 'exploded' requirement as the burger is mostly assembled
- − The food looks more like a 3D render than a photorealistic advertisement
Verdict: Nano Banana Pro followed every instruction in the prompt, including complex text integration and specific layout requirements like the starburst price tag. Stable Diffusion 3.5 Large Turbo failed to generate any text at all and did not provide the requested exploded view, resulting in a significantly lower score for prompt adherence.
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.”
Nano Banana Pro
Stable Diffusion 3.5 Large Turbo
AI Judge Analysis
Nano Banana Pro
- + Excellent text rendering with near-perfect spelling and punctuation.
- + Realistic chalk texture with smudges and natural variations on the board.
- + Authentic cozy café atmosphere with natural depth of field.
- − The font is slightly too uniform, appearing more like a digital handwriting font than natural hand-lettering in some areas.
Stable Diffusion 3.5 Large Turbo
- + Aesthetic layout with clean composition.
- + Includes café elements like plants and lighting.
- − Poor text rendering with numerous spelling errors and gibberish.
- − The chalk effect looks like a solid white digital vector brush rather than powdery chalk.
- − Failed to follow the requested year (renders 20- instead of 2026).
Verdict: Nano Banana Pro significantly outperforms Stable Diffusion 3.5 Large Turbo by delivering perfectly legible, accurately spelled text that matches the requested menu items. While Stable Diffusion 3.5 Large Turbo creates a clean graphic design, it fails the basic prompt requirements for specific text content and realistic chalk texture.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
Nano Banana Pro
Stable Diffusion 3.5 Large Turbo
AI Judge Analysis
Nano Banana Pro
- + Excellent adherence to the 'horse on top' spatial instruction.
- + Highly detailed and creative background featuring galaxies, planets, and a satellite.
- + Cinematic lighting and surreal composition that fits the requested style.
- − The horse's hooves are making awkward physical contact with the astronaut's shoulders.
- − The scale of the satellite and astronaut relative to the horse is slightly inconsistent.
Stable Diffusion 3.5 Large Turbo
- + High resolution with clean, well-defined textures on the space suit and horse.
- + Dynamic composition with an interesting perspective of the Earth's horizon.
- − Completely failed the negative constraint to have the horse on top.
- − The horse's front hoof is mangled and lacks realistic structure.
- − The horse is missing its right hind leg.
Verdict: Nano Banana Pro successfully followed the complex spatial instruction where the horse is on top of the astronaut, creating a truly surreal image. Stable Diffusion 3.5 Large Turbo defaulted to a standard 'astronaut riding a horse' composition, ignoring the core challenge of the prompt while also containing significant anatomical errors in the horse's legs.
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.”
Nano Banana Pro
Stable Diffusion 3.5 Large Turbo
AI Judge Analysis
Nano Banana Pro
- + Excellent photorealism with gritty, cinematic lighting and textures.
- + Perfectly captures the passenger's bored expression while looking at a phone.
- + Comprehensive taxi interior details including the meter, rear-view mirror, and seat textures.
- − The steering wheel placement looks slightly unnatural relative to the capybara's anatomy.
Stable Diffusion 3.5 Large Turbo
- + Clean, high-contrast visual style with vibrant colors.
- + Clearer taxi branding on the hat.
- + Accurately places paws on the steering wheel.
- − Fails to show the woman looking at her phone; she is just a blurred background figure.
- − The capybara's head shape and fur lack the realistic texture seen in the competing model.
- − Composition is tighter and shows less of the 'New York taxi' interior atmosphere.
Verdict: Nano Banana Pro is the clear winner as it fully adheres to all parts of the complex prompt, including the specific actions and expressions of the human passenger. It also achieves a significantly higher level of photorealism and environmental detail compared to Stable Diffusion 3.5 Large Turbo, which missed the passenger's phone interaction and used a more digital/smooth aesthetic.
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.”
Nano Banana Pro
Stable Diffusion 3.5 Large Turbo
AI Judge Analysis
Nano Banana Pro
- + Excellent text adherence, correctly identifying all requested information including the date and location.
- + Rich atmospheric lighting and high-quality illustration style with a vintage parchment feel.
- + Strong composition that incorporates all prompt elements like the scroll and thorn border naturally.
- − None notable for this prompt.
Stable Diffusion 3.5 Large Turbo
- + Features a bold, clean jack-o-lantern illustration.
- + Includes the requested thorn and web border.
- − Failed to include the majority of the text requirements, including the date, time, and location.
- − Missing the scroll banner element entirely.
- − The aesthetic is more like modern clip-art than the requested vintage gothic cinematic style.
Verdict: Nano Banana Pro followed the complex text and layout instructions perfectly, delivering a professional-looking invitation with all relevant data. Stable Diffusion 3.5 Large Turbo failed to include the specific event details requested and produced a much simpler, less atmospheric image.
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.”
Nano Banana Pro
Stable Diffusion 3.5 Large Turbo
AI Judge Analysis
Nano Banana Pro
- + Excellent text rendering with 'JAPAN' and 'SUSHI' perfectly spelled.
- + Beautiful 3D miniature diorama aesthetic with realistic PBR lighting.
- + Extremely high variety of sushi types following the 'cartoon scene' prompt.
- − The 'flag icon' looks slightly off with a blurred edge.
- − The background is slightly more saturated than a typical 'solid light blue' but fits the scene.
Stable Diffusion 3.5 Large Turbo
- + Strong isometric composition that clearly follows the 45-degree angle request.
- + Very clean 3D render style with high-quality surface materials.
- − The text 'SUSHI' is misspelled as 'SIIHI'.
- − The flag icon is a generic red and white rectangle rather than the Japanese flag.
- − The text is placed on a signboard rather than at the top-center of the image.
Verdict: Nano Banana Pro followed almost every instruction perfectly, specifically excelling at the text placement and spelling which Stable Diffusion 3.5 Large Turbo failed. Nano Banana Pro also produced a much more detailed and visually appealing sushi platter that captured the 'miniature diorama' feel more effectively than the simpler output of the other model.
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.”
Nano Banana Pro
Stable Diffusion 3.5 Large Turbo
AI Judge Analysis
Nano Banana Pro
- + Successfully includes all four requested animals: golden retriever, kitten, rabbit, and fox.
- + Excellent adherence to the lighting prompt with clear god rays and dew sparkles.
- + Higher level of detail in fur textures and background elements like wildflowers.
- − The kitten is notably small and slightly floating in the background compared to the other animals.
- − The lighting on the butterfly's wings is slightly inconsistent with the strong backlighting.
Stable Diffusion 3.5 Large Turbo
- + Bold and vibrant colors with clean, high-contrast lighting.
- + Cute character design with 'big expressive eyes' as requested.
- − Failed to include all four requested animals, missing the rabbit and the fox.
- − The fur rendering appears more like a digital painting or illustration than the requested 'hyper-photorealistic' look.
- − Anatomical issues with the paws blending together in the center of the image.
Verdict: Nano Banana Pro is the clear winner as it successfully rendered all four specific animals requested in the prompt, whereas Stable Diffusion 3.5 Large Turbo missed half of the subjects. Additionally, Nano Banana Pro achieved a much higher level of realism and better captured the atmospheric effects like god rays and dew.
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.”
Nano Banana Pro
Stable Diffusion 3.5 Large Turbo
AI Judge Analysis
Nano Banana Pro
- + Perfect text rendering for both the name and the date
- + Cohesive hand-drawn engraving style that fits the 'vintage' prompt
- + Clean, balanced composition with a professional vector emblem feel
- − The steam is a bit stylized/swirly which might detract from a minimalist look
Stable Diffusion 3.5 Large Turbo
- + Strong high-contrast lighting and shadows
- + Good implementation of the paper texture and border effect
- − Spelling error in 'Caffeé' (double 'e') and artifacting on the final 'n'
- − Combined the cloche with a coffee mug, which was not explicitly requested
- − Text layout is cramped inside the banner
Verdict: Nano Banana Pro followed all prompt instructions perfectly, including correct spelling of the Italian name and proper date placement. Stable Diffusion 3.5 Large Turbo struggled with the text rendering, introducing a typo and some graphical glitches on the letters, while also creating a confusing hybrid object between a cloche and a coffee mug.
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.”
Nano Banana Pro
Stable Diffusion 3.5 Large Turbo
AI Judge Analysis
Nano Banana Pro
- + Excellent text rendering with accurate labels and dates.
- + Follows all 6 requested steps in a logical, visual flow.
- + High-quality vector aesthetic with clean iconography and NASA-inspired palette.
- − The 'Descent' icon shows the lunar module with the ascent stage already detached and firing engines, which is technically inaccurate for that stage.
Stable Diffusion 3.5 Large Turbo
- + Captures the 'NASA-inspired' and 'muted red' aesthetic effectively in its color palette.
- + Good use of flat-vector textures and shading.
- − Text is largely illegible gibberish or contains significant typos like 'Apoll.o' and 'Laurch'.
- − Fails to clearly represent the requested 6 steps of the mission journey.
- − The central figure (astronaut) is standing on a ladder-like structure that is poorly integrated with the perspective.
Verdict: Nano Banana Pro is the clear winner as it successfully creates a functional, readable, and highly accurate infographic that follows every step of the prompt. Stable Diffusion 3.5 Large Turbo fails on both text generation and logical structure, providing a decorative layout that lacks the informative value requested.
Next steps
Explore each model
Distilled version of SD 3.5 Large that generates high-quality images in just 4 steps, offering faster inference and reduced costs