Skip to main content
AI image generator and editor
Google
Nano Banana

Nano Banana 2

Kyeo AI offers text-to-image generation and reference-guided editing with Nano Banana 2. You can upload up to 10 reference images, choose from 15 aspect ratios, and output at 1K, 2K, or 4K. Those tiers currently cost 5, 8, and 12 credits, prompts allow 20,000 characters, and the current generation form does not offer web search.

Capability
Text-to-image and image-to-image
Credit cost
5–12 credits per request
Prompt limit
20,000 characters
Upload limit
Up to 10 images
30-second overview
  • Without an upload, Nano Banana 2 generates from text; with uploaded references, it switches to reference-guided editing.
  • Prompts allow 20,000 characters, and each request accepts up to 10 JPG, PNG, or WebP images.
  • The current public source request schema has no `google_search`; Kyeo neither displays nor sends a web-search field.
  • Kyeo currently exposes only 1K, 2K, and 4K, priced at 5, 8, and 12 credits.

Popular searches: How do I use Nano Banana 2 on Kyeo AI? · How many credits do the 1K, 2K, and 4K Nano Banana 2 tiers cost? · Why does Nano Banana 2 not have a web-search control?

Examples

Visual concept

Visual concept

Cartier × Zendaya — "THE GOLDEN RATIO" FORMAT: Ultra-Premium Jewelry SMM Poster | 4:5 | Instagram Hero | Behance Front Page Quality CORE STRATEGY: Chiaroscuro luxury. Monolithic serif typography integrated with model and product. CAMPAIGN: "THE GOLDEN RATIO" MASTER VISUAL: Massive serif CARTIER typography (70% canvas), layered with Zendaya. HERO SUBJECT: Zendaya. Sleek low bun, black velvet tuxedo, large gold panther necklace, gold rings. POSE: Centered, direct lens contact. Hands resting to display gold rings. COLOR SYSTEM: Obsidian Black, Warm Gold, Muted Bronze, Cream. BACKGROUND: Dark studio back with a soft gold gradient halo. GRAPHIC SYSTEM: Thin gold grid lines, catalog coordinates, clean editorial labels. PROMOTIONAL ELEMENTS: NEW COLLECTION | THE PANTHÈRE SERIES | ONLINE EXCLUSIVE TYPOGRAPHY: Top left small wordmark | Center giant C A R T I E R | Title: THE GOLDEN RATIO LIGHTING: High-contrast key light highlights the gold necklace and face profile. CAMERA: ARRI Alexa Mini LF, 85mm Lens, shallow depth of field, sharp metal highlights.

Visual concept

Visual concept

A stylized, retro-futuristic music poster in a synthwave aesthetic. The central focus is a woman in profile with a platinum blonde bob haircut, wearing oversized, chunky pink opaque visor sunglasses and a high-collar, extremely glossy pink vinyl jacket with visible zipper detail. Behind her, the word "HEIS" is written in massive, dark purple, condensed block typography, partially hidden by her head. The background is a clean gradient shifting from soft magenta to deep purple, overlaid with a subtle film grain texture. Lighting: Soft studio lighting with high-specular highlights on the glossy jacket and rim lighting on the hair. Color Palette: Dominant shades of bubblegum pink, deep violet, and lavender. Graphics: A small barcode on the left, a minimalist star logo in the bottom-left corner, and four lines of small sans-serif song lyrics in the bottom-right corner. Atmosphere: High-fashion, electronic dance music vibe, clean and polished composition.

Visual concept

Visual concept

Ultra-modern high-end skincare advertising collage featuring four beautiful young Asian women, each portrait styled in a separate geometric section of a dynamic diagonal layout. Clean editorial beauty photography with soft natural skin texture, glowing healthy complexion, and subtle makeup. Bright vibrant color blocking design using pink, yellow, cyan, and coral tones. Minimal abstract background shapes, smooth gradients, and modern graphic design composition. Studio-quality lighting, fashion magazine aesthetic, premium cosmetic campaign feel. Each woman posed confidently in different angles, smiling softly, fresh and youthful vibe. Balanced symmetry with sharp diagonal divisions and circular portrait frames. Highly polished commercial beauty branding style, cinematic lighting, ultra-detailed, 4k resolution. IMPORTANT NEGATIVE PROMPT: No text, no typography, no logos, no brand names, no product bottles, no packaging, no watermark, no labels, no written elements.

Visual concept

Visual concept

Create a finished premium sports campaign poster, 9:16, full bleed. Intimate film-like sports photography, extreme close-up, strong selective focus, one bold white logo lockup at the center. An adult athlete shot from arm's length, canted off-axis, caught in one felt bodily moment: exertion, breath, water, heat or recovery. Real sweat beads, flushed skin, damp hair, irregular water drops. Moody, slightly underexposed sunlight: warm amber skin highlights, deep natural shadow, muted blue sky or water, gentle bloom on wet highlights, fine restrained grain. Only the nearer eye and a small patch of skin are sharp; a near arm or hand melts into soft blur across the lower foreground, and the background falls away. One tightly joined white lockup: a simple original logo placed directly left of a two-line heavy italic sans-serif wordmark in title case, first word stacked above the second. The lockup spans about 60 to 66% of canvas width (38 to 44% for 16:9) and overlaps the lower cheek, chin and upper body at the optical center. Keep the key eye readable. The photo continues behind it. Wordmark: "[Word One] [Word Two]" Logo: [Simple Original White Symbol] Athlete & Setting: [Sport Wardrobe Environment] Felt Moment: [Bodily State Physical Evidence] Near Foreground: [Blurred Arm / Hand / Prop Close To Lens] No other text, no subtitle, no footer, no side copy panel, no glitch, no neon or colored gel light, no HDR, no plastic skin, no uniform fake sweat, no evenly sharp clinical look. 01 True Motion · open-ring logo · coastal climb road Cyclist in a white vented helmet leaning over the bars after a brutal climb; sweat and poured water drip off flushed cheeks. Near foreground: blurred forearm and handlebar grip. Logo: tilted white open ring with a wedge cut at the upper right. 02 Still Moving · twin rounded bars · mountain trail summit Trail runner folded forward, hands on knees, chest heaving, freckled face lifted to the sky with wet strands of hair. Near foreground: sweat-lit forearm blurring across the lower left. Logo: two parallel rounded white bars slanting upward. 03 Deep Current · nested teardrop · open sea at the waterline Swimmer breaking the surface for air, goggles pushed up on a black cap, water streaming from nose and chin. Near foreground: wet hand gripping a dark boat edge. Logo: two nested white teardrop loops pointing up-right. 04 Raw Ascent · folded chevron · sunlit rock face Climber resting one beat after a hard move, cheek against warm stone, lips parted on an exhausted exhale. Near foreground: chalked hand on a hold, deep in soft focus. Logo: stacked white angular chevrons with a blunt cut end.

Visual concept

Visual concept

Ultra-realistic luxury product photography of a black glass reed diffuser bottle labeled “BLACK OUDH – Private Collection – RITUALS” in elegant gold serif typography. The bottle has a curved rectangular shape with soft edges, a glossy reflective surface, and a gold wax-seal style emblem centered near the top. Thin black diffuser reeds extend upward from the bottle neck. The bottle is covered in realistic water droplets and condensation, as if freshly misted after rain. It is placed among deep black roses and dark burgundy petals with visible water droplets, surrounded by rich green leaves. The scene is moody and dramatic with a dark botanical background, softly blurred (shallow depth of field, bokeh effect). Lighting is cinematic and low-key, with soft diffused highlights reflecting off the wet glass surface. Cool-toned lighting (deep greens and midnight blues) enhances the dark, luxurious atmosphere. The gold emblem and lettering subtly catch the light, creating a premium, high-end aesthetic. Composition: vertical portrait orientation (4:5 ratio), centered product placement, slightly angled bottle resting naturally among roses. Foreground roses partially frame the bottom of the bottle. Background is dark foliage fading into shadow. Texture emphasis: hyper-detailed water droplets, glossy glass reflections, velvety rose petals, matte black reeds. Style: high-end commercial fragrance advertising, macro lens, 85mm, f/2.0, shallow depth of field, photorealistic, 8K resolution, sharp focus on bottle, dramatic contrast, rich blacks, luxury perfume campaign aesthetic.

Visual concept

Visual concept

以上传人像作为唯一身份参考,生成一组高质感赛博暗黑婚纱剑姬写真。人物五官、发型和整体气质保持一致,但每张表情、眼神、动作与构图都要不同,包含冷静直视、低头沉思、闭眼克制、侧目疏离、温柔发呆等自然神态,避免僵硬、诡异和重复。 灰色极简摄影棚背景,柔和定向光,高级时尚杂志质感。人物穿黑色婚纱,融合薄纱、蕾丝、拖尾、头纱和不规则飘带,整体优雅、暗黑、神秘,但不过度暴露。 手持一把银黑色华丽长剑,剑柄带宝石、金属雕花和垂坠链条,剑身拥有细密赛博纹路、发光符文 and 蓝白色能量光效,周围环绕轻微剑气、粒子、光丝与能量轨迹,效果灵动但不过度夸张,不呈现攻击、伤口或暴力场面。 画面加入少量不规则赛博风英文排版作为点缀,例如: SILENT VOW I CARRY THE CODE I WRITE MY OWN LEGEND IN THE SILENCE I CHOOSE MY EDGE 文字采用细长未来感字体,错位、留白、分散排版,搭配少量线条、圆点、编号和HUD界面元素,不遮挡人物主体,不要水印和品牌Logo。 整体风格:暗黑婚纱、赛博剑姬、冷灰色调、蓝白剑气、时尚编辑大片、照片级写实、细腻皮肤、自然比例、电影感光影、干净高级、人物有灵性、单张独立输出、不拼图。

At a glance

Is this model right for you?

Google calls Nano Banana 2 Gemini 3.1 Flash Image and positions it as an efficient all-purpose image model. public source interface uses its own `nano-banana-2` identifier without publishing the public source Gemini version on the endpoint page. This page therefore uses Google material for model background and public source interface plus Kyeo configuration for the controls users can actually select.

What it does best
Among Kyeo's current Nano Banana options, this page is distinguished by up to 10 images, a 20,000-character prompt, 15 aspect-ratio choices, and 1K, 2K, or 4K output tiers; there is currently no web-search control.
Who it is for
It is a practical candidate for edits built from several clearly assigned references, or infographics and covers with detailed text and layout constraints. In-image text, subject details, and factual claims still need review, and the model cannot retrieve live web information.
Why use it on Kyeo AI
Aspect ratio, resolution, and output format are visible in one form, and Kyeo calculates credits from the chosen resolution. You can validate composition and instruction following at 1K before paying for 2K or 4K.

Key facts

Quickly evaluate whether this model fits your business use case.

Category
AI image generator and editor
Vendor
Google
Model family
Nano Banana
Integration
Current site integration
Platform model ID
nano-banana-2
Runtime
Asynchronous task
Prompt limit
20,000 characters
Upload limit
Up to 10 images

Other names

The same model may have different names in official documentation, community discussions, and API integrations. This section brings them together for you.

nano-banana-2
Gemini 3.1 Flash Image
gemini-3.1-flash-image
Google Nano Banana 2
Nano Banana 2 API

Common questions

These practical questions focus on the task, input conditions, and result requirements you should confirm before choosing.

How do I use Nano Banana 2 on Kyeo AI?
How many credits do the 1K, 2K, and 4K Nano Banana 2 tiers cost?
Why does Nano Banana 2 not have a web-search control?
How many images does Nano Banana 2 accept, and in which formats?
Is 20,000 characters the recommended Nano Banana 2 prompt length?
How should I choose a Nano Banana 2 resolution tier?
How should I choose between 3-credit Nano Banana and Nano Banana 2?
Which controls differ between Nano Banana 2 and Pro?
How do I edit with reference images in Nano Banana 2?
How should I fact-check an infographic made with Nano Banana 2?

Decision guide

Still deciding? Start with these key decision points.

1
Choose it when you need more references or resolution tiers

Nano Banana 2 is worth testing when the brief needs more references than the base route's recommended working set, extreme 4:1, 1:4, 8:1, or 1:8 ratios, or explicit 2K or 4K output. Obtain any recent facts from reliable sources first.

2
Compare other models by controls and test output

For basic generation or editing at a fixed 3 credits, compare standard Nano Banana. When 8 images are enough, run the same prompt and material through Pro. None of these current site options provides a web-search control.

3
Build a 1K baseline with a small reference set

Begin with 1 to 3 essential images and a 1K request. Raise resolution or add inputs after the source roles and composition are working. If the brief needs recent information, obtain and verify it from reliable sources before writing the prompt.

Popular comparisons

Compare common alternatives on the same task to clarify differences in inputs, controls, and cost.

What are the tradeoffs between fixed-price Nano Banana and tiered Nano Banana 2?
When are standard Nano Banana's current controls already enough?
Do Nano Banana 2 and Pro expose a web-search control?
What do 10-image and 8-image reference limits mean in practice?
How do Nano Banana 2 and GPT Image 1.5 compare on cost and input limits?
How should I test different image models with the same brief and source material?

Model comparison table

Not sure which model to choose? Compare the key differences between this model and its alternatives at a glance.

Current Kyeo controls
Nano Banana 2
10 images, 15 aspect-ratio choices, and three output tiers; no search control
Nano Banana
Fixed at 3 credits, with no resolution tier or search control
Nano Banana Pro
Three resolution tiers, up to 8 images, and no search control
Request structure
Nano Banana 2
One Nano Banana 2 workflow accepts text and optional reference images
Nano Banana
Kyeo switches model IDs based on whether images are attached
Nano Banana Pro
The same `nano-banana-pro` ID accepts text and images
Prompt and image limits
Nano Banana 2
20,000 characters and up to 10 input images
Nano Banana
5,000 characters; the editing route accepts up to 10 images
Nano Banana Pro
10,000 characters and up to 8 images
Current Kyeo price
Nano Banana 2
5 credits at 1K; 8 at 2K; 12 at 4K
Nano Banana
3 credits for either generation or editing
Nano Banana Pro
8 credits at 1K or 2K; 14 at 4K
Verifiable distinction
Nano Banana 2
Kyeo neither displays nor sends a web-search field; up to 10 images
Nano Banana
Fixed-price generation and editing with fewer controls
GPT Image 1.5
OpenAI image generation and editing, currently with up to 16 references

Real-world experience

Practical guidance based on public sources, current on-site limits, and representative tasks.

A shared product name does not disclose the public source service version

Google maps Nano Banana 2 to stable `gemini-3.1-flash-image`, while the public source interface publishes `nano-banana-2`.

Direct Gemini features and Kyeo controls are different scopes

Google's model also supports 0.5K, image-search grounding, PDF or video context, and Thinking, but Kyeo AI does not currently display those controls. This page promises only the features supported by both the Kyeo AI form and the public source interface.

Credit differences are not a quality ranking

Nano Banana 2 currently costs 12 credits at 4K and Pro costs 14 at 4K. That is a Kyeo pricing difference, not evidence about image quality, text accuracy, reference adherence, or editing stability; compare those with the same source material.

Capabilities

Text generation and reference-guided editing

Kyeo uses Nano Banana 2 for both text-only generation and reference-guided editing. You can upload up to 10 reference images, but the limit is not a recommendation to fill every slot.

Web search is currently unavailable

The current public source request schema has no `google_search`, so Kyeo neither displays nor sends a web-search parameter. Search capabilities of Google's direct model do not become Kyeo features; weather, sports, and recent events must be verified separately from reliable sources.

Aspect ratio, resolution, and output format

The form has 15 aspect-ratio choices, including auto, 4:1, 1:4, 8:1, and 1:8. Output options are 1K, 2K, or 4K and JPG or PNG; Google's 0.5K tier is not exposed on Kyeo.

Prompt and credit boundaries

Prompts allow 20,000 characters, but that is a ceiling rather than a target. A request currently costs 5 credits at 1K, 8 at 2K, or 12 at 4K, so it is sensible to validate instructions at the lower tier first.

Use cases

Drafts that need recent public information

Obtain weather, sports, or recent-event information from reliable sources first, then place the verified dates, numbers, and wording in the prompt. The current model cannot browse, and every map, chart, and piece of text still requires review.

Product or brand visuals with several references

Assign separate images to the subject, material, setting, and layout. When identity, product accuracy, or brand rules matter, inspect details that were not meant to change.

Infographics or covers with text and layout constraints

Break out the title, hierarchy, composition, palette, and protected elements. Google reports better multilingual text rendering for this model, but Kyeo output still requires line-by-line proofreading.

Prompt tips

Verify time-sensitive facts outside the model

There is currently no web-search control. When an image depends on recent public information, obtain and verify facts from reliable primary sources before writing the prompt; do not treat the generated image as evidence.

Start with a small, clearly assigned image set

Begin with 1 to 3 images and identify which one supplies the subject, material, pose, setting, or layout. Add images only when the result is controllable and information is genuinely missing, so the references do not conflict.

Turn a long prompt into testable sections

The 20,000-character allowance is a limit, not a goal. Separate subject, composition, copy, reference roles, protected details, and exclusions, then test at 1K before choosing a higher output tier.

Why choose it

Supports both text-to-image generation and reference-image editing on one page.
The current public source request schema has no web-search field, and Kyeo neither displays nor sends one.
The form offers 15 aspect-ratio choices and 1K, 2K, or 4K output.
A 20,000-character prompt and up to 10 images leave room for complex constraints.

What to know first

For routine generation or editing at a fixed 3 credits, the base Nano Banana workflow is lighter.
The current model cannot browse for live information, so time-sensitive facts must be verified outside the model.
Search capabilities of Google's direct model do not become features of the current Kyeo integration.
Kyeo does not expose the direct API's 0.5K tier, image-search grounding, PDF or video input, or Thinking controls.

Adjustable settings

Quickly evaluate whether this model fits your business use case.

Aspect ratio
Optional
Parameter type: Select
Default: auto
Auto
1:1
16:9
9:16
3:2
2:3
15 choices
Resolution
Optional
Parameter type: Select
Default: 1K
1K
2K
4K
Output format
Optional
Parameter type: Select
Default: jpg
JPG
PNG

Credit cost

5–12 credits per request

Current Kyeo AI pricing is 5 credits at 1K, 8 credits at 2K, and 12 credits at 4K.

Credit-saving tip

Before generating images or videos in bulk, run an A/B test with the same input on this model and similar alternatives. Confirm the result first to avoid wasting credits.

Frequently asked questions

Related models

Still deciding? Take a quick look at these similar alternatives.

Nano Banana

Nano Banana, also known as Gemini 2.5 Flash Image, provides text-to-image generation and natural-language editing on Kyeo AI. Requests without images use `Nano Banana`; requests with images use `Nano Banana`. Both paths cost 3 credits and accept prompts up to 5,000 characters.

AI image generator and editor
3 credits per request

Nano Banana Pro

Nano Banana Pro supports text-to-image generation and reference-image editing on Kyeo AI, with 1K, 2K, or 4K output. Each 1K or 2K request costs 8 credits, while 4K costs 14. Resolution is an output-size tier, not a guarantee of quality, accuracy, or detail.

AI image generation and editing model
8–14 credits per request

GPT Image 1.5

GPT Image 1.5 on Kyeo supports text-to-image and image-to-image with three aspect ratios and medium/high quality. Image editing accepts up to 16 JPG, PNG, or WebP references at 10 MB each. Medium costs 4 credits and high costs 22 credits. GPT Image 1.5 is OpenAI's deprecated previous image model. Kyeo retains generation and editing access, but that availability does not make it OpenAI's current default choice.

AI image model
4–22 credits per request

Sources

This page is based on vendor materials, model-family documentation, and Kyeo AI integration settings.

Source note

Generate or edit with Nano Banana 2 on Kyeo AI using 20,000-character prompts, up to 10 images, and 1K/2K/4K tiers priced at 5/8/12 credits; web search is currently unavailable. Current Kyeo AI pricing is 5 credits at 1K, 8 credits at 2K, and 12 credits at 4K.

Last updated: 2026-08-09
Google Blog: Nano Banana 2 launch
Official
Open original source
Google Blog: Build with Nano Banana 2
Official
Open original source
Google AI for Developers: Gemini 3.1 Flash Image
Official
Open original source
Google AI for Developers: Image generation with Gemini
Official
Open original source