Skip to main content

Nano Banana 2 Lite, Google's Gemini 3.1 Flash Lite Image, edits or combines one to ten source images into a 1K result, referenced as Image 1, Image 2 and so on, with an automatic aspect ratio option.

From $0.027/image

Workbench

Input

Image editing
182/20000

Reordering updates prompt references. Removing media also removes its references; review your prompt.

Explain the requested revision in up to 20,000 characters, referring to inputs as Image 1, Image 2 and onward; text length does not affect the fixed rate. at least 1 characters · at most 20000 characters
1/10

Drop files or media links, paste, or browse · Up to 10 files · Max 10 MB · JPG · PNG · WEBP · GIF

  • Image 1
1 / 10 files
Send 1–10 source image URLs to guide the revision; this workflow charges per image produced rather than by source count. at least 1 items · at most 10 items
Choose auto to follow the source, or 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, 1:4, 4:1, 1:8 or 8:1; selecting a shape does not alter Lite pricing.
Safety checkerOff

SpicyAPI does not run a safety checker on this model. Your prompt and media go to the model as written, and the model itself decides what comes back.

Checking your account before enabling submission and pricing.

Output

Ready for a new run
paris-suite-rainExample result

Missing the model you need?

1K IMAGES IN FOURTEEN SHAPES

Nano Banana 2 Lite API at a glance

Build a rainy train reading nook from text, or turn a greenhouse photo into a winter morning.

Output tier
1K
Images contain approximately one million pixels.
Composition choices
14
Shapes range from 1:8 vertical to 8:1 horizontal.
Editing source capacity
10
An edit accepts one to ten pictures.
Characters for direction
20,000
The prompt can describe a new scene or an edit.
Edit shape can follow
AUTO
The editing workflow adds auto to the fourteen fixed ratios.
Per-image charging
ONE RATE
Lite uses a fixed image rate for creation and revision.

Results

What you can make with Nano Banana 2 Lite

  • A four-frame black-and-white photo booth strip shows the same couple laughing, kissing, pulling a tie and touching foreheads.

    Four moments in one strip

    The same couple across changing poses

    Our 1:4 generation produced a black-and-white photo booth strip with four frames: laughing, kissing, a playful pull on a tie and foreheads touching. The couple stayed consistent across the sequence. Write the moments in their intended order and select the narrow ratio in the controls; the result is one composed image, with its four frames inside it. This sample demonstrates that particular sequence rather than a promise for every cast or layout.

    Generated 1:4 sample: four photo booth moments with the couple consistent across frames.

  • An open book and knitted blanket lie on a train window seat beside a warm lamp and rain-streaked glass.

    Interior from text

    A reading corner inside a carriage

    The train example begins with a place and a contrast in atmosphere: a cozy reading nook inside, rain outside. Our test produced the carriage reading corner. Use concrete furnishings and a lighting direction to explain the scene you want, then choose proportions that leave room for the window and seat. The 1K output is suited to reviewing that composition before deciding whether a larger version is needed.

    Text-to-image reading nook created in the 4:5 shape.

  • Frosted pale greenhouse glass surrounds green ferns and citrus trees under cold exterior light.

    A seasonal edit

    Winter light around living green plants

    A sunny greenhouse became a winter morning in our editing test. Frost appeared on the glass and the light turned cold, while the indoor plants remained green. That contrast makes the requested change easy to inspect: compare the glass and lighting, then check the plants separately. Name the greenhouse as Image 1 and state both the seasonal change and what should remain, rather than leaving preservation to an implied instruction.

    Seasonal greenhouse edit using auto aspect ratio.

Content test

Is Nano Banana 2 Lite uncensored? What we tested

Content levels tested on Nano Banana 2 Lite, by mode
LevelText to imageImage editing
Mild
RefusedTested Nov 11, 2026
Not tested yet
Moderate
RefusedTested Nov 11, 2026
RefusedTested Nov 11, 2026
Strong
RefusedTested Nov 11, 2026
RefusedTested Nov 11, 2026
Very strong
RefusedTested Nov 11, 2026
Not tested yet
Maximum
RefusedTested Nov 11, 2026
Not tested yet
How we test

How each mode behaves

All modes
Lite-generated files are stored for 14 days and then removed.
All modes
Nano Banana 2 Lite produces 1K images, approximately one million pixels each.
Image editing
Supply at least one and no more than ten editing images.
All modes
The Lite prompt accepts a maximum of 20,000 characters.

Use cases

What to build with the Nano Banana 2 Lite API

  • A photo-strip story

    Arrange a couple across four moments in a narrow 1:4 composition. Our black-and-white photo booth result kept the same couple recognizable while their poses changed between frames.

  • An interior mood study

    Explore warm light against rainy surroundings before developing a room concept. The train-carriage test brought a reading nook into that setting.

  • A seasonal location revision

    Ask for a winter atmosphere while naming the indoor details that should remain. Our greenhouse edit added frosted glass and cold light with the plants still green.

  • A canvas for an unusual placement

    Select 1:8, 8:1 or another supported ratio when a layout needs a narrow or panoramic image. These shapes change the composition without adding a larger resolution tier.

  • A brief with numbered references

    Use one to ten sources when an edit needs existing visual material. Explain the role of each image and review the returned details against those sources.

Prompts

Nano Banana 2 Lite prompt examples you can copy

  • Text to image

    Four moments after a night out

    A vintage black-and-white photo booth strip with four frames of the same couple: laughing, a stolen kiss, her pulling him close by his tie, foreheads touching. Film grain.

    Why it works. An ordered sequence names the cast, wardrobe and changing action. Pair it with 1:4; our displayed sample kept the couple consistent across four frames.

    Try this prompt
  • Text to image

    Reading between stations

    A cozy reading nook built into a train carriage window, rain outside, warm lamp, knitted blanket, film photo.

    Why it works. The prompt gives the interior specific objects and contrasts warm room light with rain outside. It develops the direction of our carriage reading-nook test.

    Try this prompt
  • Image editing

    A greenhouse in winter light

    Turn the greenhouse in Image 1 into a snowy winter morning: frost on the glass, snow on the roof outside, citrus trees still green inside.

    Why it works. The weather change and preservation goals are separate clauses. Our greenhouse sample supports the frosted-glass, cold-light and green-plant parts of this direction.

    Try this prompt
  • Text to image

    A quiet cafe portrait

    A woman in her forties wearing a burgundy silk blouse and a wool coat sits at a cafe window after the rain. She smiles down at a handwritten postcard beside her coffee. Warm pendant light, reflections on the street outside, relaxed evening mood, natural photographic color.

    Why it works. Age, wardrobe, action and light define a new portrait brief. This is a suggested prompt, without a measured result attached.

    Try this prompt
  • Text to image

    An observatory across a wide horizon

    A panoramic view of a small mountain observatory at blue hour, its white dome on the left and a long ridge stretching toward a faint warm horizon. A lit doorway anchors the scene, with sparse clouds overhead and no people. Restrained cinematic lighting and detailed stone textures.

    Why it works. A clear left-to-right arrangement gives a wide canvas a purpose. Try 8:1 for the composition; this proposed scene has not been included in our tests.

    Try this prompt
  • Image editing

    An evening light study from a portrait

    Using the authorized portrait of the woman in her forties in Image 1, change the lighting to a soft amber studio setup against a muted blue background. Preserve her face, navy jacket and seated pose. Keep the atmosphere calm and photographic.

    Why it works. The instruction names its source and separates lighting changes from identity, clothing and pose. Use an adult subject whose photo you have the right to edit, without impersonation; this is an untested suggestion.

    Try this prompt

Pricing

Nano Banana 2 Lite API pricing

One image starts at $0.027.

Get started

How to use the Nano Banana 2 Lite API in three steps

  1. Step 1

    Choose a starting point

    Open text to image for a scene described in words, or image to image for a picture you want to revise. For photos of people, use adults and images you have the right to use; do not impersonate anyone.

  2. Step 2

    Give the scene a clear direction

    Name the setting, light and visible action. In an edit, connect each input to Image 1, Image 2 and onward, then separate the requested changes from the details to retain.

  3. Step 3

    Choose the canvas proportions

    Select a fixed ratio for generation, such as 1:4 for a vertical photo strip. Editing also offers auto to follow source proportions; every selection stays at the 1K tier.

Parameter reference and code samples are in the API and Readme tabs at the top of this page.

FAQ

Nano Banana 2 Lite API FAQ

About Nano Banana 2 Lite

Start with the photo booth strip to see how a narrow 1:4 canvas can hold a sequence of changing poses. The carriage reading nook offers a different starting point for light and setting, while the greenhouse edit shows a seasonal change with green plants retained indoors. Choose Lite when a 1K result fits the job, and check Nano Banana 2.1 when you need 2K or 4K. Keep reference roles clear, inspect the returned details and save your accepted files within 14 days. The publisher's filter applies to both generation and editing.

Related models and next tasks