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.
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
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
Skill signature
· Text-to-Image
Stable Diffusion 3.5 Medium
16.8
arena score
#58 of 62 in Text-to-Image
Vote tally
Where the votes landed
Nano Banana 2
100.0%
win rate
Ties
0.0%
Stable Diffusion 3.5 Medium
0.0%
win rate
100.0%
0.0% ties
0.0%
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 2
Stable Diffusion 3.5 Medium
AI Judge Analysis
Nano Banana 2
- + Excellent adherence to lighting and placement prompts
- + High level of detail in the wooden texture and book cover
- + Realistic glass physics and refractions of the plant behind it
- − The glass cube has a mirrored base which wasn't specifically requested, though it adds to the aesthetic
Stable Diffusion 3.5 Medium
- + Successfully captures all required elements in the scene
- + Bright, clean photographic style
- − The blue sphere appears to be floating mid-air inside the cube, which is physically illogical
- − The lighting comes from the right/back rather than the left as requested
- − Lower overall resolution and detail compared to the competitor
Verdict: Nano Banana 2 is the clear winner as it followed every instruction, including the specific direction of the light. Stable Diffusion 3.5 Medium failed the spatial logic by having the sphere float and ignored the lighting direction, whereas Nano Banana 2 produced a highly detailed and hyper-realistic scene.
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 2
Stable Diffusion 3.5 Medium
AI Judge Analysis
Nano Banana 2
- + Excellent adherence to the 'imperfect framing' and 'candid' aspects of the prompt.
- + Highly realistic skin textures and believable mechanical interaction with the bicycle.
- + Effective background bokeh and reflections on the wet textures.
- − The bike chain and wrench interaction has some minor logical inconsistencies in the grip.
- − Lacks significant motion blur for the passing cars mentioned in the prompt.
Stable Diffusion 3.5 Medium
- + Successfully captures the light rain falling through the air.
- + Good reflection quality on the wet pavement.
- − The anatomy of the man's hands is mangled and lacks coherence.
- − The bicycle geometry is broken, particularly where the frame meets the handlebars and seat.
- − The image feels more like a generic digital painting than a 50mm candid photograph.
Verdict: Nano Banana 2 is the clear winner as it provides a highly convincing, realistic photograph with authentic Japanese street details and natural skin textures. Stable Diffusion 3.5 Medium fails significantly on anatomical and mechanical details, resulting in a distorted man and a nonsensical bicycle structure.
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 2
Stable Diffusion 3.5 Medium
AI Judge Analysis
Nano Banana 2
- + Excellent depiction of battle-worn textures including grit, blood, and realistic skin imperfections.
- + Highly detailed ornate engraving on the plate armor with consistent runic and lion motifs.
- + Atmospheric lighting with clear torchlight source and believable bokeh sparks.
- − The sword hilt grip texture is slightly repetitive.
- − The character's hand grasping the sword has some slight anatomical blurring at the knuckle.
Stable Diffusion 3.5 Medium
- + Striking, intense eye detail and strong warm lighting contrast.
- + Intricate braiding of the hair meeting the prompt's beads requirement.
- − The skin texture appears somewhat blotchy rather than realistically scarred or dirty.
- − Armor engravings are less distinct and more painterly compared to the metal textures in Image A.
- − The background is very blown out, losing the sense of a physical environment.
Verdict: Nano Banana 2 delivers a much more cohesive and detailed interpretation of the 'battle-worn paladin', specifically excelling in the material textures of the armor and the gritty realism of the character's face. While Stable Diffusion 3.5 Medium captures the lighting and hair braids well, it lacks the fine detail in the metalwork and the grounded composition found in Nano Banana 2.
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 2
Stable Diffusion 3.5 Medium
AI Judge Analysis
Nano Banana 2
- + Excellent typography with legible, meaningful text and prices.
- + High-quality, vibrant food photography that correlates with the item names.
- + Perfect adherence to layout requests including specific sections and a logical grid.
- − Minor spelling errors in fine-print descriptions like 'somon' and 'metrons'.
Stable Diffusion 3.5 Medium
- + Generates a clean grid of images as requested by the prompt.
- + Maintains a minimalist aesthetic with plenty of white space.
- − Text is largely illegible gibberish and does not follow the requested section titles.
- − Food photography is lower resolution and lacks the professional finish of a real menu.
- − Layout is disorganized with prices and headings placed somewhat randomly.
Verdict: Nano Banana 2 outperforms Stable Diffusion 3.5 Medium in every category, producing a nearly production-ready menu with legible English text, accurate sectioning, and appetizing food photography. While Stable Diffusion 3.5 Medium follows the basic layout of a grid, its failure to generate readable text or distinct sections makes it unsuccessful for this specific prompt.
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 2
Stable Diffusion 3.5 Medium
AI Judge Analysis
Nano Banana 2
- + Excellent adherence to the 'exploded' burger request with clearly suspended components.
- + Integrated text perfectly with the requested fiery, glowing effect and starburst.
- + High level of food detail, including realistic textures on the patty and fresh-looking vegetables.
- − The composition is very busy with many sparks, which might distract from the main subject slightly.
Stable Diffusion 3.5 Medium
- + Clean focus on the burger with a strong contrast against the background flames.
- + Accurate pricing and currency symbol rendering in the starburst.
- − Failed to produce an 'exploded' burger, showing a mostly assembled sandwich instead.
- − The text rendering is plain and lacks the requested fiery, glowing effect.
- − The background flame looks like a simple overlay rather than an integrated environment.
Verdict: Nano Banana 2 is the clear winner as it fully captured the 'exploded' nature of the prompt, showing the individual layers of the burger suspended in air. In contrast, Stable Diffusion 3.5 Medium provided a standard assembled burger and failed to apply the requested fiery aesthetic to the typography. Nano Banana 2's image feels like a finished, professional advertisement, whereas Stable Diffusion 3.5 Medium feels like a basic concept missing key instructions.
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 2
Stable Diffusion 3.5 Medium
AI Judge Analysis
Nano Banana 2
- + Excellent text rendering with no spelling errors across all menu items.
- + Highly realistic chalk texture and natural variations in handwriting style.
- + Comprehensive adherence to the prompt, including the date and specific prices.
- − The 'elegant cursive' request for the title was interpreted as a more casual script rather than formal cursive.
Stable Diffusion 3.5 Medium
- + Creative interpretation of chalkboard art with decorative swirls.
- + Good contrast and clean wooden frame.
- − Significant spelling and coherence issues ('Trodalu', 'Ooccluter', 'Cookiies').
- − Text layout is cluttered and confusing, failing to follow the requested menu structure.
- − The date is garbled and includes incorrect numbers and symbols.
Verdict: Nano Banana 2 is the clear winner as it perfectly rendered all requested text with realistic chalk physics and zero spelling errors. Stable Diffusion 3.5 Medium struggled with the text-heavy prompt, resulting in illegible words and a disorganized layout that failed to follow the specific menu instructions.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
Nano Banana 2
Stable Diffusion 3.5 Medium
AI Judge Analysis
Nano Banana 2
- + Excellent adherence to the 'horse on top' prompt instruction
- + Rich, vibrant colors and high level of detail in both the nebula and spacesuit
- + Dynamic cinematic composition with a clear sense of movement
- − The horse's front hoof intersecting the helmet is a bit messy
- − Highly stylized/AI-core aesthetic might feel over-saturated to some
Stable Diffusion 3.5 Medium
- + Clean, photographic lighting on the astronaut and horse
- + High contrast between the subjects and the dark space background
- − Failed the primary prompt instruction by putting the astronaut on top
- − Anatomical issues with the horse's legs and hooves
- − Composition is static and less cinematic than requested
Verdict: Nano Banana 2 successfully interpreted the tricky surrealist prompt by correctly placing the horse on top of the astronaut. In contrast, Stable Diffusion 3.5 Medium ignored the specific positioning instruction and produced a standard 'astronaut riding horse' image with several anatomical glitches 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 2
Stable Diffusion 3.5 Medium
AI Judge Analysis
Nano Banana 2
- + Excellent adherence to the full prompt including specific taxi interior details like the meter and hack license.
- + High level of realism and clarity in the background textures and lighting.
- + Creative addition of the 'Captain Cappy' license which adds to the professional expression requested.
- − The hat is black instead of the requested yellow taxi driver cap.
- − The capybara's paws look slightly more like hands/claws than natural paws.
Stable Diffusion 3.5 Medium
- + Accurately colored yellow taxi driver cap.
- + The passenger is wearing a coat as requested in the prompt.
- − Failed to include the passenger looking at her phone; she is just looking forward.
- − The interior details are very sparse and low resolution compared to Model A.
- − The capybara's 'paws' are distorted and blended into each other.
Verdict: Nano Banana 2 is the superior model, providing a rich, detailed, and highly photorealistic interior that perfectly captures the New York taxi aesthetic. While it missed the specific color of the cap, it followed every other complex instruction including the character's actions and specific props, whereas Stable Diffusion 3.5 Medium failed to include the passenger's phone interaction and lacked coherent anatomical detail for the animal's paws.
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 2
Stable Diffusion 3.5 Medium
100% wins
0% ties
0% wins
AI Judge Analysis
Nano Banana 2
- + Flawless text rendering for every specific detail requested.
- + Excellent composition that integrates the artistic elements and text seamlessly.
- + Strict adherence to all prompt elements including the scroll banner, specific border, and central jack-o-lantern.
- − None identified as it perfectly met the complex text and layout requirements.
Stable Diffusion 3.5 Medium
- + Captures the 'twisted trees' and 'spooky border' requirements reasonably well.
- + Good use of color and high-contrast lighting on the jack-o-lanterns.
- − Failed significantly on text rendering with multiple spelling errors like 'Halloweeen' and 'Inviloween'.
- − Missing the specific requested text for the banner and incorrectly formatted the date and location.
- − Lacks the central jack-o-lantern required by the prompt, placing two off to the sides instead.
Verdict: Nano Banana 2 is the clear winner as it followed every instruction perfectly, specifically excelling at the difficult task of rendering long strings of custom text without a single error. Stable Diffusion 3.5 Medium struggled with the text and failed to include several key compositional elements like the central jack-o-lantern and the specific banner content.
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 2
Stable Diffusion 3.5 Medium
AI Judge Analysis
Nano Banana 2
- + Exemplary text rendering with perfect spelling and placement.
- + Highly detailed and realistic textures on the sushi and wood.
- + Excellent interpretation of the diorama base and miniature scene.
- − The 'flag icon' is slightly stylized with rounded corners rather than a standard flag shape.
Stable Diffusion 3.5 Medium
- + Features vibrant, clean colors.
- + Matches the isometric angle requested.
- − Text rendering is poor with 'SUSHI' having a trailing character and 'JAPAN' being tiny.
- − Completely missed the flag icon requirement.
- − Texture quality is flat and lacks the PBR realism requested.
Verdict: Nano Banana 2 followed every instruction in the prompt, including complex text placement, the specific diorama base, and high-fidelity PBR textures. Stable Diffusion 3.5 Medium failed significantly on the text rendering, missed the flag icon entirely, and produced a much simpler, less detailed scene.
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 2
Stable Diffusion 3.5 Medium
AI Judge Analysis
Nano Banana 2
- + Successfully included all four requested animals (dog, cat, bunny, fox).
- + Excellent lighting with distinct god rays and realistic dew sparkles on the flowers.
- + Superior composition showing movement and interaction as requested by 'playfully chasing'.
- − The fox has black paws which is more characteristic of an adult than a kit.
- − The butterflies appear a bit flat compared to the high-detail animals.
Stable Diffusion 3.5 Medium
- + Vibrant, warm color palette that fits the 'joyful' vibe.
- + Very soft, appealing fur textures on the animals present.
- − Failed to include the requested baby bunny animal.
- − The fox and puppy have nearly identical facial structures, lacking biological distinction.
- − The scene is static and does not capture the 'tumbling' or 'chasing' action requested.
Verdict: Nano Banana 2 is the clear winner as it successfully rendered all four requested animals and captured the dynamic movement described in the prompt. While Stable Diffusion 3.5 Medium has a warm aesthetic, it failed on prompt adherence by missing the bunny and creating a very static, posed composition.
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 2
Stable Diffusion 3.5 Medium
AI Judge Analysis
Nano Banana 2
- + Perfect text rendering for both the name and the date banner.
- + Clean, balanced composition that adheres strictly to the vector emblem style requested.
- + Accurate representation of all prompt elements including the cloche, steam, and vintage color palette.
- − The 'minimalist' aspect is slightly overshadowed by the ornate banner, though it fits the 'vintage' prompt well.
Stable Diffusion 3.5 Medium
- + Uses a unique illustrative style with a coffee cup integration.
- + Correct warm brown and cream color tones.
- − Multiple spelling errors including 'Florrian' and 'Caffee'.
- − The date is incorrect, showing '170' instead of '1720'.
- − The cloche dome is mangled and ill-defined compared to the requested prompt.
Verdict: Nano Banana 2 followed the prompt perfectly, delivering a professional-grade logo with flawless typography and a clear, well-composed emblem. In contrast, Stable Diffusion 3.5 Medium struggled significantly with the text, failing to spell the name correctly or provide the complete date, while also creating a cluttered and less coherent design.
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 2
Stable Diffusion 3.5 Medium
AI Judge Analysis
Nano Banana 2
- + Excellent typography with mostly correct spelling and clear labels.
- + Adheres perfectly to the requested NASA-inspired color palette and flat-vector style.
- + Logical and visually clear progression of all requested mission steps.
Stable Diffusion 3.5 Medium
- + Interesting artistic interpretation of a space infographic.
- + Maintains the requested color palette well.
- − Text is largely illegible and contains numerous spelling errors like 'Lauan strip' and 'Tranllity'.
- − Icons are inconsistent and do not clearly represent the objects described in the prompt.
- − The layout is cluttered and fails to communicate the mission steps effectively.
Verdict: Nano Banana 2 followed the prompt instructions near-perfectly, producing a professional-looking infographic with clean lines, accurate iconography, and correct text. Stable Diffusion 3.5 Medium failed significantly on the 'clean and modern' vector style, producing messy text and icons that don't match the requested mission steps.
Next steps
Explore each model
Stability AI's 2.5-billion parameter Multimodal Diffusion Transformer with improvements (MMDiT-X) text-to-image model optimized for consumer hardware, featuring improved image quality, typography, and complex prompt understanding