Skip to content

Nano Banana 2 Edit

Integrate

Model id nano-banana-2/edit
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/nano-banana-2/edit?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Turn this photo into a 1:7 scale collectible figurine of the dog on a round clear acrylic base, standing on a tidy wooden desk with soft studio light; keep the dog'\''s pose, fur colors and expression.",
    "images": [
      "https://content.doitong.com/dev-api/2026/10/21/req_3yckkmcr3dayonfhigdeaiia/0-pz7p4ydjvjJmL__s7lK6p_L0WSl1GK.png"
    ],
    "resolution": "1K"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

This request: $0.08 80 API credits Run it on this page

Get API key
Google Image Editing 4K outputup to 4K #editing#fast#multimodal

Fast instruction-based editing that can also read a video, audio clip or PDF as context.

Examples

Input
Output · ~21 s
Turn this photo into a 1:7 scale collectible figurine of the dog on a round clear acrylic base, standing on a tidy wo...

PromptTurn this photo into a 1:7 scale collectible figurine of the dog on a round clear acrylic base, standing on a tidy wooden desk with soft studio light; keep the dog's pose, fur colors and expression.

1K$0.08 · 80 API credits

Build a request

Controls are generated from the model schema. The code and the price update as you change them.

•required 198 / 50000

Text instructions for editing an image.

image_urls
Drop a file, or

Supply source images by URL for image editing or image-to-image generation, unless you provide at least one alternative input: `video_url`, `audio_url`, or `pdf_url`.

resolution

Resolution for the output image.

thinking_level

Select 'minimal' or 'high' to activate model thinking at that level and include its thoughts in the generation; leaving the level unset keeps thinking disabled.

default auto

Output image aspect ratio, including the extreme options 4:1, 1:4, 8:1, 1:8.

num_images default 1

Image count requested for generation.

Advanced system_prompt · video · audio · output_format · safety_tolerance · pdf_url · seed · limit_generations
0 / 50000

Optional request-wide persona and output-style guidance, delivered to Gemini as a system instruction or to OpenAI-compatible providers as a system message. Nothing is sent for this instruction when the value is blank.

video_url
Drop a file, or

Optional video context supplied as either a YouTube URL or an http(s)/data URL for a video file. YouTube links reach the model directly without downloading; video files are downloaded and sent inline, subject to a 15 MB maximum.

audio_url
Drop a file, or

Provide optional audio context through an http(s) or data URL pointing to a file no larger than 15 MB. The file is sent inline after downloading.

output_format default png

File format for the resulting image.

safety_tolerance default 4

Set content-moderation tolerance between the least restrictive level, 6, and the strictest level, 1, which blocks most content.

Provide optional PDF context through an http(s) or data URL pointing to a document no larger than 15 MB. The document is sent inline after downloading.

Seed value that initializes random-number generation.

POST /run/nano-banana-2/edit?wait=20 quote → $0.08
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/nano-banana-2/edit?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Turn this photo into a 1:7 scale collectible figurine of the dog on a round clear acrylic base, standing on a tidy wooden desk with soft studio light; keep the dog'\''s pose, fur colors and expression.",
    "images": [
      "https://content.doitong.com/dev-api/2026/10/21/req_3yckkmcr3dayonfhigdeaiia/0-pz7p4ydjvjJmL__s7lK6p_L0WSl1GK.png"
    ],
    "resolution": "1K"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Run this request

Your key stays in this browser: it is sent only to the Doitong API and saved (localStorage) only if you tick Remember. Get an API key

Made on Doitong

Public works made with Nano Banana 2 by the Doitong community. Reuse a prompt in one click.

Public works shown: 16
Strong rule: style --- 3D Pixar ---. Комната Макса, ночь. Свет только от экрана ноутбука освещает...

Strong rule: style --- 3D Pixar ---. Комната Макса, ночь. Свет только от экрана ноутбука освещает его уставшее лицо. Вокруг разбросаны учебники английского. На экране ноутбука открыта поисковая система. Стиль 3D Pixar, освещение создает ощущение безысходности. Character appearance reference (MUST...

Strong rule: style --- 3D Pixar ---. Комната Макса, ночь. Свет только от экрана ноутбука освещает...

Strong rule: style --- 3D Pixar ---. Комната Макса, ночь. Свет только от экрана ноутбука освещает его уставшее лицо. Вокруг разбросаны учебники английского. На экране ноутбука открыта поисковая система. Стиль 3D Pixar, освещение создает ощущение безысходности. Character appearance reference (MUST...

Strong rule: style --- 3D Pixar ---. Крупный план экрана ноутбука. Среди скучных ссылок на курсы ...

Strong rule: style --- 3D Pixar ---. Крупный план экрана ноутбука. Среди скучных ссылок на курсы виден яркий, мигающий баннер с изображением чашки чая, из которой вылетают английские буквы, и улыбающимся Михаилом Шестовым. Макс кликает по нему. Стиль 3D Pixar. Character appearance reference (MUST...

Strong rule: style --- 3D Pixar ---. Молодой парень, 20-25 лет, с взлохмаченными каштановыми воло...

Strong rule: style --- 3D Pixar ---. Молодой парень, 20-25 лет, с взлохмаченными каштановыми волосами и большими мечтательными глазами. Одет в простую домашнюю футболку с забавным принтом и спортивные штаны. Его лицо выражает смесь решимости и легкой растерянности.

Strong rule: style --- 3D Pixar ---. Мужчина 60-65 лет, с добрыми глазами за круглыми очками и ак...

Strong rule: style --- 3D Pixar ---. Мужчина 60-65 лет, с добрыми глазами за круглыми очками и аккуратной седой бородой. Одет в уютный твидовый пиджак. Выглядит как мудрый и немного эксцентричный профессор.

Strong rule: style --- 3D Pixar ---. Вход в темный, облицованный старым кирпичом железнодорожный ...

Strong rule: style --- 3D Pixar ---. Вход в темный, облицованный старым кирпичом железнодорожный туннель, поглощающий пути. Композиция: симметричный кадр прямо по курсу движения, камера установлена на крыше поезда. Освещение: резкий контраст между угасающим дневным светом снаружи и кромешной,...

Strong rule: style --- 3D Pixar ---. Оживленная центральная улица футуристического мегаполиса два...

Strong rule: style --- 3D Pixar ---. Оживленная центральная улица футуристического мегаполиса двадцать первого века, залитая холодным пронзительным светом гигантских рекламных голограмм и парящих светодиодных экранов. Недавний дождь оставил глубокие лужи на темном асфальте, идеально отражающие...

Яркая и радостная сцена в детской. Папа склонился над пеленальным столиком, развлекая Саю яркой п...

Яркая и радостная сцена в детской. Папа склонился над пеленальным столиком, развлекая Саю яркой погремушкой в форме солнца. Ракурс снизу, со стороны ребенка, подчеркивает масштаб и значимость фигуры отца. Освещение дневное, контрастное и веселое. Вокруг разбросаны мягкие кубики и яркие игрушки....

About Nano Banana 2 Edit

The editing mode of Nano Banana 2: pass images and describe the change, or skip images and give a video, an audio file or a PDF (each up to 15 MB) as context to illustrate. Output from 0.5K to 4K with aspect ratios from 1:8 to 8:1, optional web search and high thinking, up to four results per request.

Parameters

Send either the canonical name or the native name, not both. Canonical names

NameType DefaultAllowed Description
promptrequired
Typestring
≤ 50,000 characters≥ 3 characters
Text instructions for editing an image.
num_imagesoptional num_outputs
Typeinteger
Default1
1 – 4
Image count requested for generation.
seedoptional
Typeinteger | null
Seed value that initializes random-number generation.
aspect_ratiooptional
Typeenum
Defaultauto
auto21:916:93:24:35:41:14:53:42:39:164:11:48:11:8
Output image aspect ratio, including the extreme options 4:1, 1:4, 8:1, 1:8.
output_formatoptional
Typeenum
Defaultpng
jpegpngwebp
File format for the resulting image.
safety_toleranceoptional
Typeenum
Default4
123456
Set content-moderation tolerance between the least restrictive level, 6, and the strictest level, 1, which blocks most content.
image_urlsoptional images
Typeurl[] · image
Supply source images by URL for image editing or image-to-image generation, unless you provide at least one alternative input: `video_url`, `audio_url`, or `pdf_url`.
system_promptoptional
Typestring
Default
≤ 50,000 characters
Optional request-wide persona and output-style guidance, delivered to Gemini as a system instruction or to OpenAI-compatible providers as a system message. Nothing is sent for this instruction when the value is blank.
resolutionoptional
Typeenum
Default1K
0.5K1K2K4K
Resolution for the output image.
video_urloptional video
Typeurl · video
Optional video context supplied as either a YouTube URL or an http(s)/data URL for a video file. YouTube links reach the model directly without downloading; video files are downloaded and sent inline, subject to a 15 MB maximum.
audio_urloptional audio
Typeurl · audio
Provide optional audio context through an http(s) or data URL pointing to a file no larger than 15 MB. The file is sent inline after downloading.
pdf_urloptional
Typestring | null
Provide optional PDF context through an http(s) or data URL pointing to a document no larger than 15 MB. The document is sent inline after downloading.
limit_generationsoptional
Typeboolean
Defaulttrue
Experimental generation cap that may affect quality when enabled. With `True`, each prompting round is restricted to 1 generation, overriding image-count instructions in the prompt and ignoring model-generated intermediate images.
thinking_leveloptional
Typeenum
minimalhigh
Select 'minimal' or 'high' to activate model thinking at that level and include its thoughts in the generation; leaving the level unset keeps thinking disabled.
required Canonical name, also accepted

File parameters take a public https:// URL, a data: URI up to 10 MB, or the file_url of an upload. Files

Output

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "nano-banana-2/edit",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 80,
    "usd": "0.08",
    "charged": 80,
    "refunded": 0
  },
  "input": {
    "prompt": "Turn this night street scene into a sunny morning, keep the sneaker and the puddle reflections",
    "images": [
      "https://content.doitong.com/images/showcase/v3/gen_sneaker_ad.jpg"
    ],
    "resolution": "1K"
  },
  "output": {
    "images": [
      {
        "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
        "content_type": "image/jpeg",
        "file_name": "0-output.jpeg",
        "file_size": 1843200,
        "width": 1024,
        "height": 768
      }
    ],
    "description": "string"
  },
  "outputs": [
    {
      "type": "image",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "width": 1024,
      "height": 768,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
Your files, your choiceEvery outputs[].url is a copy on our storage: kept forever (paid per GB-month) or 7 days for free, by your account setting or ?storage=.
Same shape on every modeltype, url, content_type, width, height and duration, for images, video and audio alike. output is the model’s own result object.
Fields of output
images
array of object {url, content_type, file_name, file_size, width, height}Images resulting from editing.
description
stringDescription accompanying the generated images.

More models: Image Editing

For AI agents: this page as Markdown is at https://doitong.com/en-GB/developers/models/nano-banana-2/edit.md. All models and guides: https://doitong.com/developers/llms.txt