Skip to content
Grok image
English
English简体中文繁體中文DeutschEspañolPortuguês

Nano Banana 2

Nano Banana 2 is Google's general-purpose image model, published as Gemini 3.1 Flash Image. This page keeps three kinds of statement apart. The first is what Google published, quoted and attributed. The second is what this site's catalogue returns for the product, which is what the workspace actually obeys. The third is what the published artwork can and cannot support.

Updated:

Nano Banana 2

Choose a mode, write the prompt, then read the quoted cost before you generate.

AI Image0

Generated content will appear here

Publisher's artwork

Published artwork for Nano Banana 2

Ten images published by Google alongside the Nano Banana 2 announcement. Every one of them came with a prompt, published as a numbered footnote, and each prompt is reproduced here from that footnote. The site did not write any of them.

All ten images are Google's published artwork, retrieved on 19 September 2026. Rights remain with the publisher; they are shown with source attribution and no claim of ownership. Every image on this page came from the publisher's own announcement CDN, so any provenance marking it carries is Google's, and this site added none. Prompts stayed in English in every language version of this page, because a prompt is the model's input and translating it would change the output.

A flat lay on a light grey textured surface showing a hand-made infographic of the water cycle, with clouds, rain, a lake and a green hillside, connected by drawn black arrows and short handwritten labels Details and prompt ↗

01 / Published artwork with its published prompt

The water cycle as a flat lay

Google ↗

Use this prompt

High-quality flat lay photography creating a DIY infographic that simply explains how the water cycle works, arranged on a clean, light gray textured background. The visual story flows from left to right in clear steps. Simple, clean black arrows are hand-drawn onto the background to guide the viewer's eye. The overall mood is educational, modern, and easy to understand. The image is shot from a top-down, bird's-eye view with soft, even lighting that minimizes shadows and keeps the focus on the process.

Open this prompt in the workspace ↗

Copied from Google's own numbered footnote for this image. The only edit is the removal of the leading Prompt: label; the wording is otherwise unchanged, because a prompt is a model input and rewriting one changes what it produces.

A three-panel comic-style infographic labelled Cumulus, Stratus and Cirrus, each panel showing that cloud type in a dramatic sky over a green landscape with a block of descriptive text Details and prompt ↗

02 / Published artwork with its published prompt

Three cloud types, three panels

Google ↗

Use this prompt

Triptych infographic comparing three types of clouds: Cumulus, Stratus, and Cirrus. Each panel shows the cloud type in a dramatic sky with a bold label. High-contrast comic style. AR: 16:9

Open this prompt in the workspace ↗

Copied from Google's own numbered footnote for this image. The only edit is the removal of the leading Prompt: label; the wording is otherwise unchanged, because a prompt is a model input and rewriting one changes what it produces.

Two flat illustrations of the same chateau with towers and steep roofs, rendered side by side in bright synthetic cubist style with angular faceted planes Details and prompt ↗

03 / Published artwork with its published prompt

A chateau drawn twice, in cubism

Google ↗

Use this prompt

Create an image of Museum Clos Lucé. In the style of bright colored Synthetic Cubism. No text. Your plan is to first search for visual references, and generate after. Aspect ratio 16:9

Open this prompt in the workspace ↗

Copied from Google's own numbered footnote for this image. The only edit is the removal of the leading Prompt: label; the wording is otherwise unchanged, because a prompt is a model input and rewriting one changes what it produces.

Two images on white: an illustrated sign made of recycled material reading Native Wildlife, Please Observe from a Distance against green foliage, and the same sign reworked for an Indian setting with all text in Hindi Details and prompt ↗

04 / Published artwork with its published prompt

The same sign, localised in Hindi

Google ↗

Use this prompt

Prompt 1: An intimate, naturalistic cinematic close-up reveals a small, intricately illustrated sign made of recycled material, showing drawings of local birds and flowers. Delicate script below reads: "Native Wildlife: Please Observe from a Distance." Soft, diffused light filters through the leaves of a nearby fern, casting gentle shadows. The background is a soft blur of vibrant green foliage, emphasizing respect for the delicate ecosystem. Prompt 2: Take this concept and localize it to an Indian setting, including translation of all the text to Hindi

Open this prompt in the workspace ↗

Copied from Google's own numbered footnote for this image. The only edit is the removal of the leading Prompt: label; the wording is otherwise unchanged, because a prompt is a model input and rewriting one changes what it produces.

A wide illustrated farm scene with a red barn and many cartoon animals and objects arranged across the frame, alongside a grid of the same fourteen characters and items shown individually Details and prompt ↗

05 / Published artwork with its published prompt

Fourteen characters in one farm scene

Google ↗

Use this prompt

Create an image of these 14 characters and items having fun at the farm. The overall atmosphere is fun, silly and joyful. It is strictly important to keep identity consistent of all the 14 characters and items.

Open this prompt in the workspace ↗

Copied from Google's own numbered footnote for this image. The only edit is the removal of the leading Prompt: label; the wording is otherwise unchanged, because a prompt is a model input and rewriting one changes what it produces.

A grid of illustrated panels showing three cartoon animals building a treehouse, with their poses, expressions and viewing angles changing between panels Details and prompt ↗

06 / Published artwork with its published prompt

Three characters build a treehouse

Google ↗

Use this prompt

Create a funny 6 part story with these 3 fluffy friends building a tree house. The story is thrilling throughout with emotional highs and lows and is ending in a happy moment. Keep the attire and identity consistent of all 3 characters, but their expressions and angles should vary throughout all 6 images. Make sure to only have one of each character in each image. Generate 6 images one at a time. Each image should be a separate output in 16:9 format.

Open this prompt in the workspace ↗

Copied from Google's own numbered footnote for this image. The only edit is the removal of the leading Prompt: label; the wording is otherwise unchanged, because a prompt is a model input and rewriting one changes what it produces.

An aerial view looking down a valley of lush green hills, a road curving along the slope and a dark blue-grey body of water reflecting an overcast sky Details and prompt ↗

07 / Published artwork with its published prompt

A glen under heavy cloud

Google ↗

Use this prompt

This aerial shot captures a dramatic, misty landscape, likely a valley or glen, characterized by rolling, verdant hills and a winding river or loch. The photography style leans towards a moody and atmospheric aesthetic, emphasizing the grandeur and isolation of nature. The camera angle is high, looking down into the valley, providing a sweeping panoramic view that highlights the immense scale of the surroundings. The dominant colors are various shades of deep green, ranging from lush emerald in the foreground fields to darker, more muted tones on the distant mountains. The water, a central feature, appears as a serene, dark blue-grey, reflecting the overcast sky. The sky itself is a blend of grey and white, heavily laden with clouds and mist that cling to the mountain peaks, creating a soft, diffused lighting style. This natural, soft light minimizes harsh shadows and enhances the overall ethereal feel of the scene. The subject is a majestic natural landscape. In the foreground, a darker body of water curves around a patch of bright green fields, bordered by scattered trees and shrubs. A narrow, winding road snakes through the green hills on the right side of the frame, disappearing into the distance. Further into the valley, a larger, lighter blue-grey body of water stretches between towering, green-clad mountains. These mountains rise steeply on both sides, their peaks shrouded in the low-hanging mist, creating a sense of depth and mystery. The overall impression is one of serene, untamed wilderness, hinting at the rugged beauty of places like the Scottish Highlands or the Lake District.

Open this prompt in the workspace ↗

Copied from Google's own numbered footnote for this image. The only edit is the removal of the leading Prompt: label; the wording is otherwise unchanged, because a prompt is a model input and rewriting one changes what it produces.

A grid of pop-art portraits of a figure in a patterned blue and pink suit with heart-shaped sunglasses against a solid blue background, shown at several different aspect ratios Details and prompt ↗

08 / Published artwork with its published prompt

One figure, several shapes

Google ↗

Use this prompt

Cinematic still, evoking a vibrant, dreamlike quality often found in highly stylized musical dramas or whimsical comedies, with a composition style reminiscent of a master of bold, graphic imagery. The camera is positioned slightly low, looking up at the subject, emphasizing their commanding presence and the dramatic flair of their outfit. The color palette is exceptionally bold and high-contrast, dominated by electric blue and shocking pink, with a bright yellow accent. The background is a solid, uniform cerulean blue, providing a stark, graphic backdrop that makes the subject pop. The subject is a young, dark-skinned individual with tightly coiled hair, wearing an incredibly striking suit. The suit's fabric features an audacious pattern of swirling, wavy lines in electric blue, interspersed with large, concentric circles in hot pink, overlapping and radiating outwards. The tailored blazer has wide lapels and bell sleeves, worn over a sharply pressed yellow collared shirt. The matching trousers are wide-legged, dramatically flaring out towards the ground, with sharp creases down the front. The individual wears bright yellow, heart-shaped sunglasses and large, pink, circular earrings. Their hands are placed on their hips in a confident, almost defiant pose, and their gaze, though hidden behind the sunglasses, projects an aura of cool assurance. The ambiance is one of high fashion, playfulness, and unadulterated self-expression, imbued with an almost surreal, pop-art energy.

Open this prompt in the workspace ↗

Copied from Google's own numbered footnote for this image. The only edit is the removal of the leading Prompt: label; the wording is otherwise unchanged, because a prompt is a model input and rewriting one changes what it produces.

Two graphite pencil sketches side by side of a pufferfish nest, the left a textured shell-lined crater and the right a geometric scientific diagram in a notebook with handwritten annotations Details and prompt ↗

09 / Published artwork with its published prompt

A pufferfish nest, drawn by two models

Google ↗

Use this prompt

Create a pencil sketch of a pufferfish nest. Not a clean digital drawing but something with visible pencil strokes and that dusty graphite look

Open this prompt in the workspace ↗

Copied from Google's own numbered footnote for this image. The only edit is the removal of the leading Prompt: label; the wording is otherwise unchanged, because a prompt is a model input and rewriting one changes what it produces.

A four-panel collage showing a kangaroo steering a small boat at sea, drinking coffee at a cafe table, lying in a white bathrobe on a hotel bed and jumping inside a colourful bouncy castle Details and prompt ↗

10 / Published artwork with its published prompt

A kangaroo on holiday, four times

Google ↗

Use this prompt

Boat Prompt: 35mm soft blur, vibrant colors, soft light. Sailing at the ocean this baby kangaroo wearing a lilac raincoat sailing, motion blur, this hat is sitting messy on the boat. Cafe Prompt: 35mm soft blur, vibrant colors, soft light. Sitting on this seat of the café this baby kangaroo sipping coffee, a person sitting behind at the cafe blurred is wearing this hat. Hotel Prompt: 35mm soft blur, vibrant colors, soft light. Relaxing on the bed this baby kangaroo wearing a bathrobe relaxing, at the back there is a coat rack with this hat. Castle Prompt: 35mm soft blur, vibrant colors, soft light. Jumping inside the inflatable castle this baby kangaroo wearing this hat jumping, motion blur

Open this prompt in the workspace ↗

Copied from Google's own numbered footnote for this image. The only edit is the removal of the leading Prompt: label; the wording is otherwise unchanged, because a prompt is a model input and rewriting one changes what it produces.

What Google says Nano Banana 2 is

Google announced Nano Banana 2 on 26 February 2026 and gave it two names: the product name Nano Banana 2, and the model identifier Gemini 3.1 Flash Image. The announcement introduces it as combining the capabilities of Nano Banana Pro with Flash speed, and says it replaces Nano Banana Pro across the Fast, Thinking and Pro options in the Gemini app.

The developer documentation is where the two names are tied together, and it splits the family four ways. Gemini 3.1 Flash Image is published as the most versatile model, a generalist workhorse for all tasks, balancing speed against 4K generation, world knowledge and reliable text rendering, and excelling at multiple reference images and consistency. That sentence is the publisher's positioning, not a measurement.

The capability claims the announcement makes in its own words are narrow enough to repeat. Up to five characters and up to fourteen objects can keep their identity in a single workflow. Text renders legibly enough for infographics and marketing mockups, and text inside an image can be translated and localised. Aspect ratios and resolutions are described only as covering a range from 512px to 4K, with no ratio named. The announcement also promises stricter instruction following and a visual fidelity upgrade over the first Nano Banana.

Two of those claims are carried by the documentation rather than the announcement, and they are the ones worth holding separately. The documentation states that Gemini 3.1 Flash Image adds a 512px tier and that it adds Google Image Search grounding alongside web search. Neither claim appears in the announcement. Grounding with Google Search is documented as unsupported by the Lite model.

The documentation also describes a thinking stage, in which the model generates interim images that are visible in the backend and not charged, and it exposes a thinking level control whose default is minimal and whose only other supported value is high. That control is an API parameter. Nothing in the catalogue this site reads carries it.

This page is not an official product description and is not endorsed by Google. It records what the publisher published and what this site’s catalogue returns.

The Nano Banana family, split four ways

The Gemini API documentation lists four image models under the Nano Banana name, and the split matters because the product names do not sort into an obvious order. Two of the four sit on the same Gemini 3.1 Flash generation, and the one called Lite is the newer of the two.

Read that table as the publisher's own positioning rather than as a benchmark, because it is the former. The one ordering it does settle is that the Lite model is not simply a smaller version of this one. Google says Lite is not optimised for multiple reference inputs or multi-turn sequential edits, which is a scope statement rather than a quality statement, and this site exposes a reference-image control for Lite anyway. That discrepancy has its own page and is registered as an open question rather than settled here.

The price ladder is visible in this site’s catalogue instead, where the product is charged 3 points per image at 1K, 6 at 2K and 9 at 4K, with roughly 1 point added per reference image. That is a catalogue figure, not a Google figure, and Google publishes its own per-image API pricing separately.

Product namePublisher's model identifierWhat the publisher says it is for
Nano Banana 2 Litegemini-3.1-flash-lite-imageFastest and cheapest image model. Built for speed and scale. Not optimised for multiple reference inputs or multi-turn sequential edits.
Nano Banana 2gemini-3.1-flash-imageThe generalist workhorse. Balances speed against 4K generation, world knowledge and text rendering. Handles multiple reference images.
Nano Banana Progemini-3-pro-imageFor complex visual tasks. Highest world knowledge, advanced localisation, brand consistency and precise creative control.
Nano Bananagemini-2.5-flash-imageThe legacy first-generation model. Google recommends moving to Nano Banana 2 Lite instead.

The aspect-ratio list, and the value only this site’s fallback carries

Two lists exist for this product and they are not the same list. The service that this workspace actually talks to declares fourteen ratios. The local table kept in this site’s own source, used when that service publishes no ratio field, carries the same fourteen plus auto. Because the service does publish the field, the fourteen-win rule applies and auto never reaches the selector.

The four extreme shapes are the interesting part of the list, and they are specific to this generation on this site. Ratios of 4:1, 1:4, 8:1 and 1:8 appear in the catalogue for this product and in no other image model this site offers. Eight to one is a shape the service accepts as a generation target; whether a crop would have produced the same framing is not something this page can establish, and neither official source names these ratios.

The fallback table is worth knowing about precisely because it is invisible. It is what the workspace would build its selector from if the catalogue request failed, and it disagrees with the catalogue on both counts that matter, the list and the default. A reader who wants to know what happens on a working day should read the first row of that table. The second row is a contingency, and its auto value is not something the service declares.

This is an observation about two lists this project controls, not a defect claim about Google’s service. The catalogue entry was read from the live endpoint on 19 September 2026.

SourceWhat it listsDefault
Catalogue entry for this product14 ratios: 1:1, 1:4, 1:8, 2:3, 3:2, 3:4, 4:1, 4:3, 4:5, 5:4, 8:1, 9:16, 16:9, 21:9. No auto.1:1
This site’s local fallback tableThe same 14 plus auto, listed first. Used only if the catalogue stops publishing the field.auto

Three controls the publisher ships that this form does not carry

Google documents three controls on this model that have no counterpart in the workspace form. None of the three is hidden by the interface; each is absent because the catalogue entry does not publish it. That distinction matters, because it means the gap is in the service this site reads rather than in the page built from it.

  • The 512-pixel tier. The documentation states that Gemini 3.1 Flash Image adds the smaller 512px (0.5K) resolution on top of the built-in 1K, 2K and 4K, and that the Lite model is limited to 1K. This catalogue declares three tiers for the product: 1K, 2K and 4K. No selector value would send 512, so the cheapest tier the publisher ships is unreachable from this form.
  • The thinking level. The documentation exposes a control whose default is minimal and whose other supported level is high, and it describes interim images that the model generates to refine composition, which are visible in the backend and not charged. The catalogue form for this product carries a prompt, an optional reference-image field, an aspect ratio and a resolution tier. There is no reasoning field, so every task runs at whatever the service applies when none is sent.
  • Google Search grounding. The documentation describes the model using Google Search to verify facts and generate imagery from real-time data, and says this generation adds image search grounding alongside web search. The catalogue form has no field for it, and neither does this workspace. A task here therefore runs without the grounding the publisher documents, and no control on the page can turn it on.
  • The reference-image count, where the number is real but not the one this site chose. Google documents a ceiling of up to 14 reference images for the Gemini 3 image models, and publishes a per-model breakdown of how those slots may be used. The catalogue entry for this product publishes no ceiling at all, so the workspace applies its own setting of 14. The two numbers agree by coincidence of this schedule rather than because the site copied one from the other.

What this catalogue declares for the product

These are the fields the service returns for this product, and they are what the workspace obeys when it builds the form. A model mnemonic and a marketing name are not evidence of anything, so the useful question is always what a task can actually carry.

Two fields a reader might expect are simply not there. There is no quality or detail level published for this product, so the form does not offer one. There is no seed or step control either, which means a repeat of the same prompt at the same settings is not reproducible by any parameter this workspace can set.

The declaration is also the entire surface. Anything a page claims about this model that cannot be traced to one of those fields, to a dated Google announcement, or to the developer documentation is a claim this site has no basis for, and this page does not make any.

FieldValue declaredWhere the workspace uses it
Task typestext-to-image, image-to-imageThe mode tabs, and the task model sent with the request
Resolution tiers1K, 2K, 4KThe resolution selector, defaulting to 1K
Aspect ratios14 values, listed aboveThe aspect-ratio selector
Form fieldsprompt, image_urls, aspect_ratio, resolutionEvery control the form shows, and nothing else
Charges published for the product3 points per image at 1K, 6 at 2K, 9 at 4K, with roughly 1 point added per reference imageThe quote shown before a task is accepted

The consistency figure, and the source that disagrees with it

Two Google sources publish different limits for the same model. The announcement states that character resemblance holds for up to five characters and the fidelity of up to fourteen objects in a single workflow. The developer documentation publishes a table in which Gemini 3.1 Flash Image allows up to ten objects and up to four characters among its fourteen reference slots. Both are quoted above as published, and this page does not pick a winner.

The two numbers are not measuring the same thing, which is the most likely explanation and also the one that cannot be confirmed from outside. A workflow ceiling is the count a task may be built around; a reference-slot table is the count of attached inputs of a given kind. Fourteen objects with identity held, against ten object slots and four character slots, is a pair of statements about the shape of the claim rather than a contradiction anyone outside the publisher can resolve.

The announcement publishes an example that sits at the same figure, and it is worth reading as published rather than as evidence. Its farm prompt asks for fourteen characters and items in one scene, which is the announcement’s own ceiling used as a demonstration. The prompt was written by the same team that wrote the figure.

The treehouse example is the harder test in the set and the more useful one. Its published prompt asks for a six-part story in which three characters keep their identity while their expressions and angles change, and it asks for the images one at a time. Holding identity across separate generations is a different claim from holding it inside one frame, and it is the one more likely to break on a real task of yours.

What none of this establishes is how consistency holds up on a task of yours. Every example was chosen by the publisher from outputs that worked, and no failure rate accompanies any of them. Treat the figures as the shape of the claim and the images as illustrations of it.

Provenance: SynthID plus Content Credentials

Google states that all generated images carry a SynthID watermark, and that it couples that technology with interoperable C2PA Content Credentials. Both are metadata-level provenance mechanisms, which has a practical consequence for anyone reading a gallery of AI images.

  • SynthID is not a visible mark. It survives inside the file rather than across the picture, so an image carrying it looks untouched. Inspection tools are what detect it, not your eye.
  • Google says its SynthID verification feature in the Gemini app had been used more than 20 million times across various languages since a November launch, and that C2PA verification was coming to the app. Those are the publisher's own usage figures and are repeated here as claims.
  • Every image in the gallery on this page came from Google's own announcement, so the provenance mechanism attached to them is Google's, and any claim this page makes is limited to the absence of a watermark added by some other site.
  • This site does not strip, re-encode away or claim to detect provenance metadata. The images here are resized for delivery, which is a separate operation from the watermarking the publisher describes.

How a task runs here

The workspace pins the model when you arrive from this page, so nothing else has to be chosen by hand. Everything below happens before anything is charged, and the quote is the last thing you see rather than the first.

  1. Open this page in the workspace, which fixes the model and reads the current catalogue entry for it.
  2. Write the instruction. Google's own examples are one or two sentences of plain description naming the subject, the setting, the lighting and any text that must appear verbatim. Because there is no exclusion field, anything you want kept out has to be written into the same sentence as the thing it applies to.
  3. Attach reference images if the task needs them. The mode becomes image to image and the task model sent changes with it. The workspace allows up to 14 references, which is its own setting; the catalogue publishes no ceiling, although Google documents 14 as the model’s limit.
  4. Choose an aspect ratio deliberately. The list the service declares is what the selector shows, and extreme shapes such as eight to one are available here and unusual elsewhere, so a specific shape is worth choosing rather than leaving the default in place.
  5. Choose a resolution tier. The 512-pixel tier the publisher describes is not offered here, so the fastest and cheapest option Google ships is not reachable from this form.
  6. Read the quote, then submit. If the task fails, the failure is reported rather than silently retried, and the task appears in your history with the settings it actually used.

What the artwork shows, and what this page does not claim

The gallery and the case list on this page come from Google's own announcements, which is an unusually good provenance for this site. It comes with limits that are easier to state than to work around.

  • The images are presented by Google as artwork produced with this model, and the announcement does not label each image with the model that produced it. This page therefore attributes the artwork to the announcement as a set and not to a specific generation. Every image in the set carries a published prompt, so the prompt is not the weak link; the model attribution is.
  • Each prompt is reproduced from Google’s own numbered footnote for that image, with no rewriting and no summarising, because a prompt is a model input. The description shown alongside each image is the publisher’s own alternative text for it, translated for the language of the page.
  • The images demonstrate legible in-image text, in-image localisation across languages, subject consistency, and one portrait the publisher presents across several shapes. They do not demonstrate a latency figure, a cost figure, or a comparison against any other model, and this page uses them for nothing beyond the four things they show.
  • One downloaded candidate was rejected during review because it is a screenshot of the publisher's own application rather than a generated image. It is excluded from the gallery, and the rejection is recorded in the project evidence rather than quietly dropped.
  • This page carries no video, and the announcement provides none for this model: the media carousel behind it exposes empty video slots and no file addresses. There was therefore no video to embed and no frame to use as a poster, rather than a retrieval failure on this project’s side.
  • Nothing here is a statement of quality. Google's own positioning language, such as calling this the generalist workhorse, is quoted as positioning, and no Elo score, ranking or benchmark number from the publisher is restated as an independent result.

Examples

A flat lay infographic of the water cycle on a light grey surface, with drawn arrows and short labels linking evaporation, condensation and collection

The clearest evidence on this page that the model can hold a diagram together. The arrows connect in the right order, the labels sit next to the stages they name, and the whole thing reads as one object photographed from above rather than as a collage. The published prompt is a long paragraph about mood, viewpoint and lighting that never names a single label, which is the part worth noticing.

Google, Nano Banana 2 announcement, retrieved 19 September 2026. Prompt published by Google and reproduced unchanged. · Third-party material. Rights remain with the publisher; shown with source attribution and no claim of ownership.

A three-panel comic infographic comparing cumulus, stratus and cirrus clouds, each panel with a bold title and a block of descriptive text

Text at panel scale, in a 16:9 frame. Every word is legible and spelled correctly, including the paragraph inside each panel, and the three panels share one visual system without drifting. This is the failure mode most image models still show at this density, so it is worth looking at the actual pixels rather than trusting the sentence describing it.

Google, Nano Banana 2 announcement, retrieved 19 September 2026. Prompt published by Google and reproduced unchanged. · Third-party material. Rights remain with the publisher; shown with source attribution and no claim of ownership.

Two versions of an illustrated nature sign on white, the first in English reading Native Wildlife Please Observe from a Distance, the second reworked for an Indian setting with Hindi text

In-image localisation, which is the capability with the fewest public examples anywhere. The second image is not the first one with the words swapped: the illustration, the materials and the setting change with the language. Google describes this as translating text inside the image while localising the visuals at the same time, and this pair is what that claim looks like when it works.

Google, Nano Banana 2 announcement, retrieved 19 September 2026. Prompt published by Google and reproduced unchanged. · Third-party material. Rights remain with the publisher; shown with source attribution and no claim of ownership.

A busy illustrated farm scene with a red barn and many animals and objects, next to a grid showing each of the fourteen characters and items on its own

Fourteen characters and items in one frame. That is the announcement's own consistency figure used as a demonstration, and it is also above the ten object slots the developer documentation allows this model, so the two Google sources are worth reading side by side. Read the grid as the part that matters: each item keeps its own design while sharing the frame, so the useful question for your own task is how many distinct things must stay recognisable, not how large the scene is.

Google, Nano Banana 2 announcement, retrieved 19 September 2026. Prompt published by Google and reproduced unchanged. · Third-party material. Rights remain with the publisher; shown with source attribution and no claim of ownership.

A grid of illustrated panels in which three cartoon animals build a treehouse, their poses and expressions changing from panel to panel

A sequence rather than a picture, and the hardest consistency test in the set. The published prompt asks for a six-part story in which the three characters keep their identity while their expressions and angles change, and it explicitly asks for the images one at a time. Character identity holding across separate generations is a different claim from holding inside one frame, and it is the claim most likely to break on a real task of yours.

Google, Nano Banana 2 announcement, retrieved 19 September 2026. Prompt published by Google and reproduced unchanged. · Third-party material. Rights remain with the publisher; shown with source attribution and no claim of ownership.

An aerial view down a green valley with a curving road and a dark water body under a heavy overcast sky

The plain photographic case, and the one that is easiest to judge without knowing anything about the model. The published prompt describes a mood and a viewpoint rather than asking for a subject, and what comes back holds a single atmospheric read across the whole frame. Use it as a reference point for how the model handles light and distance, not as evidence about anything it was not asked to do.

Google, Nano Banana 2 announcement, retrieved 19 September 2026. Prompt published by Google and reproduced unchanged. · Third-party material. Rights remain with the publisher; shown with source attribution and no claim of ownership.

A pale blue composition with the words Nano Banana 2 at the centre, surrounded by small generated images including a red-dressed portrait, a dragonfly, a watercolour house and two robot dogs

The publisher's own title card for the announcement. Google published no prompt for this one, so the only statement about it is that it is the publisher's composited artwork introducing the model. It is included because it is the image a reader is most likely to have already seen, not because it demonstrates a capability.

Google, Nano Banana 2 announcement, retrieved 19 September 2026. No image-specific prompt was published for this artwork. · Third-party material. Rights remain with the publisher; shown with source attribution and no claim of ownership.

Several pop-art portraits of a figure in a patterned suit and heart-shaped sunglasses against a solid blue background, each at a different aspect ratio

One figure, several shapes, and the visual counterpart to the aspect-ratio list earlier on the page. The published prompt asks for a single portrait and the publisher presents the result across multiple frames, so the composition re-balances for each shape rather than leaving empty space at the edges. Whether the service generated each shape separately is not stated, and this page does not assume either way.

Google, Nano Banana 2 announcement, retrieved 19 September 2026. Prompt published by Google in the announcement footnote and reproduced unchanged. · Third-party material. Rights remain with the publisher; shown with source attribution and no claim of ownership.

Two graphite pencil sketches of a pufferfish nest side by side, one a loose textured crater and the other a tidy labelled scientific diagram in a notebook

The publisher's own side-by-side comparison, and the only one in the set. The published prompt asks for a pencil sketch with visible strokes rather than a clean digital drawing, and the image shows two interpretations of that instruction. Read it as a demonstration of a difference between two things, because that is what it is: there is no independent measurement here, and the pair was selected by the party with an interest in the result.

Google, Nano Banana 2 announcement, retrieved 19 September 2026. Prompt published by Google in the announcement footnote and reproduced unchanged. · Third-party material. Rights remain with the publisher; shown with source attribution and no claim of ownership.

Four panels showing the same kangaroo steering a boat, sitting at a cafe, lying on a hotel bed and jumping in a bouncy castle

The same character in four unrelated scenes, and the only example in the set whose footnote carries four separate prompts rather than one. That structure is the point: each scene is requested on its own while the character and the hat have to survive all four. Nothing in the frame tells you how many attempts this took, so treat it as an illustration of the pitch and take the character limit from the capability lists as the number to plan against.

Google, Nano Banana 2 announcement, retrieved 19 September 2026. Prompt published by Google in the announcement footnote and reproduced unchanged. · Third-party material. Rights remain with the publisher; shown with source attribution and no claim of ownership.

The same chateau illustrated twice in bright synthetic cubist style, with faceted angular planes and saturated colour

Style transfer with a named art movement and no reference image attached. The published prompt names Synthetic Cubism and a building and explicitly tells the model to search for visual references before generating, which is the clearest published example of the grounding claim being asked for rather than merely supported.

Google, Nano Banana 2 announcement, retrieved 19 September 2026. Prompt published by Google and reproduced unchanged. · Third-party material. Rights remain with the publisher; shown with source attribution and no claim of ownership.

Questions

Is Nano Banana 2 the same thing as Gemini 3.1 Flash Image?

Yes. Google announced the product under the name Nano Banana 2 and gives its identifier as gemini-3.1-flash-image. This site's catalogue calls it nano-banana-2, which is what the URL and the workspace model selector use.

Which aspect ratios does this model support?

The catalogue declares fourteen: 1:1, 1:4, 1:8, 2:3, 3:2, 3:4, 4:1, 4:3, 4:5, 5:4, 8:1, 9:16, 16:9 and 21:9. The service publishes that field itself, so those fourteen are what the selector shows and 1:1 is what it starts on. The site’s own source file carries the same fourteen plus auto, but that table is only a fallback for when the catalogue stops publishing the field, which is not the case for this product.

Can I ask for a 512-pixel image here?

No. The developer documentation states that Gemini 3.1 Flash Image adds the smaller 512px (0.5K) resolution alongside 1K, 2K and 4K, but the catalogue declares only 1K, 2K and 4K for the product, so no selector value would send it and no task placed from this page can request it.

Can I turn the model's thinking level up?

Not from this form. Google documents a thinking level control whose default is minimal and whose only other supported value is high, and describes interim images generated to refine composition, which are visible in the backend and not charged. The catalogue form for this product has no reasoning field, so every task runs at whatever the service applies when none is sent.

How many reference images can I attach?

The workspace allows up to 14, which is this site’s own setting. The catalogue returns no reference-image ceiling for this product, so there was nothing in the entry to copy. Google does document a real limit of up to 14 reference images for the Gemini 3 image models, and publishes a per-model breakdown of how those slots may be used, with ten object slots and four character slots for this model. The two numbers agree, but the site’s setting was not derived from the publisher’s.

How many characters can it keep consistent across images?

Google publishes two different figures. The announcement says five characters and fourteen objects can keep their identity in one workflow; the developer documentation allows ten object slots and four character slots among this model’s fourteen reference images. Both are quoted as published, and the difference looks like a workflow ceiling against an input-slot count rather than a correction of one by the other.

Is the image quality adjustable?

No. The catalogue publishes no quality or detail level for this product, and the form offers none. There is no seed or step control either, so the same prompt at the same settings is not reproducible by any parameter this workspace can set.

Do images from this model carry a watermark?

Google states that all generated images carry a SynthID watermark and that it couples SynthID with C2PA Content Credentials. Both are metadata-level mechanisms, so the image looks untouched and needs a verification tool to detect. This site adds no third-party watermark and does not claim to detect or remove provenance metadata.

Why is there no video on this page?

Because the announcement does not publish one for this model. The media carousel behind the announcement exposes empty video slots and no file addresses, so there was no video to embed and no frame that could honestly be presented as a poster. The page shows nothing rather than a substitute.

Is this an official Google page?

No. It records the fields this site's service catalogue returns for the product and quotes Google's published statements with attribution. It is not a statement by Google and is not endorsed by them.

Explore next