
No matches. Try “video”, “FLUX” or “webhooks”.
Loading models…
nano-banana-pro/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-pro/edit?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "Faithfully restore this image with high fidelity to modern photograph quality, in full color, upscale to 4K",
"images": [
"https://content.doitong.com/dev-api/2026/10/21/req_tlhvxyf27ektm9ozuzozz5fn/0-1h3kLymYuP3n6Z-kAnWa8_Nh4eqcOs.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 $DOITONG_API_KEY"
const API = "https://api.doitong.com/v1";
const headers = {
"Authorization": "Bearer " + process.env.DOITONG_API_KEY,
"Content-Type": "application/json",
};
// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/nano-banana-pro/edit?wait=20", {
method: "POST",
headers,
body: JSON.stringify({
"prompt": "Faithfully restore this image with high fidelity to modern photograph quality, in full color, upscale to 4K",
"images": [
"https://content.doitong.com/dev-api/2026/10/21/req_tlhvxyf27ektm9ozuzozz5fn/0-1h3kLymYuP3n6Z-kAnWa8_Nh4eqcOs.png"
],
"resolution": "1K"
}),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);
// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
import os
import requests
API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}
payload = {
"prompt": "Faithfully restore this image with high fidelity to modern photograph quality, in full color, upscale to 4K",
"images": [
"https://content.doitong.com/dev-api/2026/10/21/req_tlhvxyf27ektm9ozuzozz5fn/0-1h3kLymYuP3n6Z-kAnWa8_Nh4eqcOs.png",
],
"resolution": "1K",
}
# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/nano-banana-pro/edit", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])
# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
# 1. Connect once (Claude Code; Cursor, VS Code, Claude Desktop: https://doitong.com/developers/docs/mcp)
claude mcp add --transport http doitong-models https://api.doitong.com/v1/mcp \
--header "Authorization: Bearer $DOITONG_API_KEY"
# 2. Your agent calls the "run" tool with:
{
"model_id": "nano-banana-pro/edit",
"input": {
"prompt": "Faithfully restore this image with high fidelity to modern photograph quality, in full color, upscale to 4K",
"images": [
"https://content.doitong.com/dev-api/2026/10/21/req_tlhvxyf27ektm9ozuzozz5fn/0-1h3kLymYuP3n6Z-kAnWa8_Nh4eqcOs.png"
],
"resolution": "1K"
}
}
Call the Nano Banana Pro Edit model (nano-banana-pro/edit) through the Doitong API. Docs for agents: https://doitong.com/developers/models/nano-banana-pro/edit.md
POST https://api.doitong.com/v1/run/nano-banana-pro/edit?wait=20
Authorization: Bearer $DOITONG_API_KEY
Content-Type: application/json
{
"prompt": "Faithfully restore this image with high fidelity to modern photograph quality, in full color, upscale to 4K",
"images": [
"https://content.doitong.com/dev-api/2026/10/21/req_tlhvxyf27ektm9ozuzozz5fn/0-1h3kLymYuP3n6Z-kAnWa8_Nh4eqcOs.png"
],
"resolution": "1K"
}
If the response status is "queued" or "running", poll GET https://api.doitong.com/v1/requests/REQUEST_ID?wait=20 until it is "succeeded"; the files are in outputs[].url. POST https://api.doitong.com/v1/quote/nano-banana-pro/edit with the same body returns the exact price before the run.
This request: $0.15 150 API credits Run it on this page
Your new API key. It is shown only now and is already in the code and in the API key field below. Keep it secret: never put it in code that runs in a browser.
PromptFaithfully restore this image with high fidelity to modern photograph quality, in full color, upscale to 4K
Controls are generated from the model schema. The code and the price update as you change them.
/run/nano-banana-pro/edit?wait=20
quote → $0.15
# 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-pro/edit?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "Faithfully restore this image with high fidelity to modern photograph quality, in full color, upscale to 4K",
"images": [
"https://content.doitong.com/dev-api/2026/10/21/req_tlhvxyf27ektm9ozuzozz5fn/0-1h3kLymYuP3n6Z-kAnWa8_Nh4eqcOs.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 $DOITONG_API_KEY"
const API = "https://api.doitong.com/v1";
const headers = {
"Authorization": "Bearer " + process.env.DOITONG_API_KEY,
"Content-Type": "application/json",
};
// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/nano-banana-pro/edit?wait=20", {
method: "POST",
headers,
body: JSON.stringify({
"prompt": "Faithfully restore this image with high fidelity to modern photograph quality, in full color, upscale to 4K",
"images": [
"https://content.doitong.com/dev-api/2026/10/21/req_tlhvxyf27ektm9ozuzozz5fn/0-1h3kLymYuP3n6Z-kAnWa8_Nh4eqcOs.png"
],
"resolution": "1K"
}),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);
// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
import os
import requests
API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}
payload = {
"prompt": "Faithfully restore this image with high fidelity to modern photograph quality, in full color, upscale to 4K",
"images": [
"https://content.doitong.com/dev-api/2026/10/21/req_tlhvxyf27ektm9ozuzozz5fn/0-1h3kLymYuP3n6Z-kAnWa8_Nh4eqcOs.png",
],
"resolution": "1K",
}
# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/nano-banana-pro/edit", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])
# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "run",
"arguments": {
"model_id": "nano-banana-pro/edit",
"input": {
"prompt": "Faithfully restore this image with high fidelity to modern photograph quality, in full color, upscale to 4K",
"images": [
"https://content.doitong.com/dev-api/2026/10/21/req_tlhvxyf27ektm9ozuzozz5fn/0-1h3kLymYuP3n6Z-kAnWa8_Nh4eqcOs.png"
],
"resolution": "1K"
},
"wait_seconds": 20
}
}
}
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
Public works made with Nano Banana Pro by the Doitong community. Reuse a prompt in one click.
[Lighting: cinematic] Art style: Кинематографический, фотореалистичный. Крупный план экрана компьютера. По экрану бегут строки фейковых данных: IP-адрес, город, личная информация. Поверх изображения — красный 'сканирующий' луч и мигающие символы тревоги. В отражении экрана видны амогусы с ножами...
Recreate this exact cinematic film shot from the reference image as a brand-new photorealistic render. Match exactly: the composition and framing, the camera angle and lens, the lighting direction, the light rays and haze, the color grade, and the design of every object and character, including...
Strong rule: style --- Whimsical 3D Illustration ---. Strong rule: style --- Whimsical 3D Illustration ---. Strong rule: style --- Whimsical 3D Illustration ---. Милая антропоморфная овечка в полный рост, длинная длинная стройная фигура, фигура удлиненная, пушистая кремово-белая кудрявая шерсть,...
[Lighting: cinematic] Art style: Кинематографический, фотореалистичный. Крупный план руки парня, которая решительно нажимает кнопку 'Включить SILA VPN' на экране. В момент клика вся комната заливается мощным, чистым синим светом. Амогусы в ужасе отлетают от окон и дверей, их 2D-формы искажаются....
[Lighting: cinematic] Art style: Кинематографический, фотореалистичный. Та же комната, но теперь она залита спокойным синим светом от монитора. Парень расслабленно сидит в кресле и энергетик монстер. За окном видно, как побежденные амогусы с ножами грустно уходят. Стиль - полный реализм,...
Нужен кадр вот к этой секунде 00:08 без снега пусть будет лето, без текста Используй референс только при необходимости, если он есть в кадре по этому сценарию Вот подробный сценарий вирального музыкального клипа. **Стиль и эстетика:** Яркая, насыщенная цветовая палитра в духе колоризованного...
Нужен кадр вот к этой секунде 00:48 без снега пусть будет лето, без текста Используй референс только при необходимости, если он есть в кадре по этому сценарию Вот подробный сценарий вирального музыкального клипа. **Стиль и эстетика:** Яркая, насыщенная цветовая палитра в духе колоризованного...
Use the woman from the reference photo as the main character, preserve her facial identity, natural facial features, realistic skin texture, eyes, lips, eyebrows and face shape. Create a magical cinematic summer fantasy scene. The woman is sitting or lying on soft green grass in a beautiful...
Single isolated character reference image. EXACTLY ONE character, alone — no other people, no background scene, no story. Full or three-quarter body, centered on a clean plain neutral studio backdrop (soft solid color). Casting / character-sheet look. Character: Маленькая собака, пушистый...
Recreate this exact cinematic film shot from the reference image as a brand-new photorealistic render. Match exactly: the composition and framing, the camera angle and lens, the lighting direction, the light rays and haze, the color grade, and the design of every object and character, including...
Strong rule: style --- Кинематографичный, макро-съемка, меланхоличный ... ---. Обычная комнатная муха, но с большими, выразительными и грустными фасеточными глазами. Ее крылья имеют нежную, полупрозрачную текстуру. Акцент на том, чтобы она выглядела детализированной и трогательной, а не просто...
Strong rule: style --- 3D Pixar ---. Крупный план на лице Марка, который в ужасе смотрит, как на него с трёх сторон медленно надвигаются стилизованные гигантские фигуры: треснувшее пополам обручальное кольцо, разъярённый кассовый аппарат с зубами и стопка счетов, превратившаяся в монстра. Стиль —...
Art style: Кинематографичный, макро-съемка, меланхоличный .... Комната почти погрузилась во тьму. Муха — лишь крошечный темный силуэт на фоне последних отблесков заката в окне. Финальный кадр, полный одиночества. ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ FINAL STYLE ENFORCEMENT (this is the...
Art style: Кинематографичный, макро-съемка, меланхоличный .... Солнце начинает садиться. Муха сидит неподвижно на стекле. В стекле видно ее слабое отражение, наложенное на изображение угасающего сада. Настроение смирения и тихой грусти. ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ FINAL STYLE...
Art style: Кинематографичный, макро-съемка, меланхоличный .... Капля дождя медленно стекает по внешней стороне окна. Муха сидит на внутренней стороне и наблюдает за ней. Мир за окном искажается и переливается в этой капле. ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ FINAL STYLE ENFORCEMENT (this is...
Art style: Кинематографичный, макро-съемка, меланхоличный .... Крупный план: муха бьется о прозрачное стекло. Видны вибрации на ее крыльях и легкие искажения на стекле в месте удара. Свет от окна создает сильный контраст, почти силуэт. ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ FINAL STYLE...
The editing mode of Nano Banana Pro: give it one or more images and describe the change, such as swapping a background, merging a person and a product into one scene, restyling or fixing text on a sign. It keeps identities and details stable across edits. Output at 1K, 2K or 4K in any common aspect ratio, optional web grounding, up to four results per request.
Send either the canonical name or the native name, not both. Canonical names
promptrequired
num_imagesoptional
num_outputs
seedoptional
aspect_ratiooptional
output_formatoptional
safety_toleranceoptional
image_urlsrequired
images
system_promptoptional
resolutionoptional
limit_generationsoptional
enable_web_searchoptional
File parameters take a public https:// URL, a data: URI up to 10 MB, or the file_url of an upload. Files
{
"id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
"object": "request",
"model": "nano-banana-pro/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": 150,
"usd": "0.15",
"charged": 150,
"refunded": 0
},
"input": {
"prompt": "Put this white sneaker on a sunlit marble pedestal in a minimalist gallery, keep the shoe exactly as it is",
"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"
}
}
For AI agents: this page as Markdown is at https://doitong.com/developers/models/nano-banana-pro/edit.md. All models and guides: https://doitong.com/developers/llms.txt