

Aucun résultat. Essayez « vidéo », « FLUX » ou « webhooks ».
Chargement des modèles…
nano-banana-pro
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://vit.doitong.com/api/v1/run/nano-banana-pro?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "Cinematic portrait of a young woman with long, silky dark brown hair, sitting and resting her chin on her hand, gazing softly off to the side with a gentle smile. She wears a deep crimson red flowy dress with puffed sleeves and a textured, crinkled fabric. Small floral pearl-and-crystal stud earrings. Dramatic low-key lighting: a single warm window light casting geometric window-shadow patterns on a dark wall, soft glow on her face, deep black background. Rosy cheeks, soft natural makeup, dreamy and romantic mood. Shallow depth of field, 85mm lens, ultra-detailed skin texture, rich contrast, moody studio photography, vertical 9:16",
"aspect_ratio": "9:16",
"resolution": "1K"
}'
# Still "queued" or "running"? Poll with the id from the response:
curl "https://vit.doitong.com/api/v1/requests/REQUEST_ID?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY"
const API = "https://vit.doitong.com/api/v1";
const headers = {
"Authorization": "Bearer " + process.env.DOITONG_API_KEY,
"Content-Type": "application/json",
};
// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/nano-banana-pro?wait=20", {
method: "POST",
headers,
body: JSON.stringify({
"prompt": "Cinematic portrait of a young woman with long, silky dark brown hair, sitting and resting her chin on her hand, gazing softly off to the side with a gentle smile. She wears a deep crimson red flowy dress with puffed sleeves and a textured, crinkled fabric. Small floral pearl-and-crystal stud earrings. Dramatic low-key lighting: a single warm window light casting geometric window-shadow patterns on a dark wall, soft glow on her face, deep black background. Rosy cheeks, soft natural makeup, dreamy and romantic mood. Shallow depth of field, 85mm lens, ultra-detailed skin texture, rich contrast, moody studio photography, vertical 9:16",
"aspect_ratio": "9:16",
"resolution": "1K"
}),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);
// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
import os
import requests
API = "https://vit.doitong.com/api/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}
payload = {
"prompt": "Cinematic portrait of a young woman with long, silky dark brown hair, sitting and resting her chin on her hand, gazing softly off to the side with a gentle smile. She wears a deep crimson red flowy dress with puffed sleeves and a textured, crinkled fabric. Small floral pearl-and-crystal stud earrings. Dramatic low-key lighting: a single warm window light casting geometric window-shadow patterns on a dark wall, soft glow on her face, deep black background. Rosy cheeks, soft natural makeup, dreamy and romantic mood. Shallow depth of field, 85mm lens, ultra-detailed skin texture, rich contrast, moody studio photography, vertical 9:16",
"aspect_ratio": "9:16",
"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", 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/fr/developers/docs/mcp)
claude mcp add --transport http doitong-models https://vit.doitong.com/api/v1/mcp \
--header "Authorization: Bearer $DOITONG_API_KEY"
# 2. Your agent calls the "run" tool with:
{
"model_id": "nano-banana-pro",
"input": {
"prompt": "Cinematic portrait of a young woman with long, silky dark brown hair, sitting and resting her chin on her hand, gazing softly off to the side with a gentle smile. She wears a deep crimson red flowy dress with puffed sleeves and a textured, crinkled fabric. Small floral pearl-and-crystal stud earrings. Dramatic low-key lighting: a single warm window light casting geometric window-shadow patterns on a dark wall, soft glow on her face, deep black background. Rosy cheeks, soft natural makeup, dreamy and romantic mood. Shallow depth of field, 85mm lens, ultra-detailed skin texture, rich contrast, moody studio photography, vertical 9:16",
"aspect_ratio": "9:16",
"resolution": "1K"
}
}
Appelez le modèle Nano Banana Pro (nano-banana-pro) via la Doitong API. Documentation pour les agents : https://doitong.com/fr/developers/models/nano-banana-pro.md
POST https://vit.doitong.com/api/v1/run/nano-banana-pro?wait=20
Authorization: Bearer $DOITONG_API_KEY
Content-Type: application/json
{
"prompt": "Cinematic portrait of a young woman with long, silky dark brown hair, sitting and resting her chin on her hand, gazing softly off to the side with a gentle smile. She wears a deep crimson red flowy dress with puffed sleeves and a textured, crinkled fabric. Small floral pearl-and-crystal stud earrings. Dramatic low-key lighting: a single warm window light casting geometric window-shadow patterns on a dark wall, soft glow on her face, deep black background. Rosy cheeks, soft natural makeup, dreamy and romantic mood. Shallow depth of field, 85mm lens, ultra-detailed skin texture, rich contrast, moody studio photography, vertical 9:16",
"aspect_ratio": "9:16",
"resolution": "1K"
}
Si le statut de la réponse est "queued" ou "running", interrogez GET https://vit.doitong.com/api/v1/requests/REQUEST_ID?wait=20 jusqu’à ce qu’il soit "succeeded" ; les fichiers se trouvent dans outputs[].url. POST https://vit.doitong.com/api/v1/quote/nano-banana-pro avec le même corps renvoie le prix exact avant l’exécution.
Cette requête: 0,15 $ 150 crédits API L’exécuter sur cette page
Votre nouvelle clé API. Elle n’est affichée que maintenant et figure déjà dans le code et dans le champ de clé API ci-dessous. Gardez-la secrète : ne l’intégrez jamais dans du code exécuté dans un navigateur.
promptCinematic portrait of a young woman with long, silky dark brown hair, sitting and resting her chin on her hand, gazing softly off to the side with a gentle smile. She wears a deep crimson red flowy dress with puffed sleeves and a textured, crinkled fabric. Small floral pearl-and-crystal stud earrings. Dramatic low-key lighting: a single warm window light casting geometric window-shadow patterns on a dark wall, soft glow on her face, deep black background. Rosy cheeks, soft natural makeup, dreamy and romantic mood. Shallow depth of field, 85mm lens, ultra-detailed skin texture, rich contrast, moody studio photography, vertical 9:16
Les contrôles sont générés à partir du schéma du modèle. Le code et le prix se mettent à jour lorsque vous les modifiez.
/run/nano-banana-pro?wait=20
devis → 0,15 $
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://vit.doitong.com/api/v1/run/nano-banana-pro?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "Cinematic portrait of a young woman with long, silky dark brown hair, sitting and resting her chin on her hand, gazing softly off to the side with a gentle smile. She wears a deep crimson red flowy dress with puffed sleeves and a textured, crinkled fabric. Small floral pearl-and-crystal stud earrings. Dramatic low-key lighting: a single warm window light casting geometric window-shadow patterns on a dark wall, soft glow on her face, deep black background. Rosy cheeks, soft natural makeup, dreamy and romantic mood. Shallow depth of field, 85mm lens, ultra-detailed skin texture, rich contrast, moody studio photography, vertical 9:16",
"aspect_ratio": "9:16",
"resolution": "1K"
}'
# Still "queued" or "running"? Poll with the id from the response:
curl "https://vit.doitong.com/api/v1/requests/REQUEST_ID?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY"
const API = "https://vit.doitong.com/api/v1";
const headers = {
"Authorization": "Bearer " + process.env.DOITONG_API_KEY,
"Content-Type": "application/json",
};
// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/nano-banana-pro?wait=20", {
method: "POST",
headers,
body: JSON.stringify({
"prompt": "Cinematic portrait of a young woman with long, silky dark brown hair, sitting and resting her chin on her hand, gazing softly off to the side with a gentle smile. She wears a deep crimson red flowy dress with puffed sleeves and a textured, crinkled fabric. Small floral pearl-and-crystal stud earrings. Dramatic low-key lighting: a single warm window light casting geometric window-shadow patterns on a dark wall, soft glow on her face, deep black background. Rosy cheeks, soft natural makeup, dreamy and romantic mood. Shallow depth of field, 85mm lens, ultra-detailed skin texture, rich contrast, moody studio photography, vertical 9:16",
"aspect_ratio": "9:16",
"resolution": "1K"
}),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);
// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
import os
import requests
API = "https://vit.doitong.com/api/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}
payload = {
"prompt": "Cinematic portrait of a young woman with long, silky dark brown hair, sitting and resting her chin on her hand, gazing softly off to the side with a gentle smile. She wears a deep crimson red flowy dress with puffed sleeves and a textured, crinkled fabric. Small floral pearl-and-crystal stud earrings. Dramatic low-key lighting: a single warm window light casting geometric window-shadow patterns on a dark wall, soft glow on her face, deep black background. Rosy cheeks, soft natural makeup, dreamy and romantic mood. Shallow depth of field, 85mm lens, ultra-detailed skin texture, rich contrast, moody studio photography, vertical 9:16",
"aspect_ratio": "9:16",
"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", 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",
"input": {
"prompt": "Cinematic portrait of a young woman with long, silky dark brown hair, sitting and resting her chin on her hand, gazing softly off to the side with a gentle smile. She wears a deep crimson red flowy dress with puffed sleeves and a textured, crinkled fabric. Small floral pearl-and-crystal stud earrings. Dramatic low-key lighting: a single warm window light casting geometric window-shadow patterns on a dark wall, soft glow on her face, deep black background. Rosy cheeks, soft natural makeup, dreamy and romantic mood. Shallow depth of field, 85mm lens, ultra-detailed skin texture, rich contrast, moody studio photography, vertical 9:16",
"aspect_ratio": "9:16",
"resolution": "1K"
},
"wait_seconds": 20
}
}
}
Votre clé reste dans ce navigateur : elle est envoyée uniquement à la Doitong API et enregistrée dans localStorage uniquement si vous cochez Mémoriser. Obtenir une clé API
Modèle d’image basé sur Gemini qui raisonne sur le prompt avant de dessiner ; les affiches, infographies, menus et photos de produits avec texte lisible sont donc bien plus souvent réussis qu’avec les seuls modèles de diffusion. Choisissez une sortie 1K, 2K ou 4K et n’importe quel format courant, et autorisez éventuellement une recherche web pour ancrer l’image dans des faits actuels. Jusqu’à quatre images par requête.
Envoyez soit le nom canonique, soit le nom natif, mais pas les deux. Noms canoniques
promptrequis
num_imagesfacultatif
num_outputs
seedfacultatif
aspect_ratiofacultatif
output_formatfacultatif
safety_tolerancefacultatif
system_promptfacultatif
resolutionfacultatif
limit_generationsfacultatif
enable_web_searchfacultatif
{
"id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
"object": "request",
"model": "nano-banana-pro",
"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": "A minimalist poster for a jazz night called \"Blue Hour\", a saxophone silhouette against a deep blue sky, bold sans-serif title",
"aspect_ratio": "3:4",
"resolution": "2K"
},
"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://vit.doitong.com/api/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
"cancel": "https://vit.doitong.com/api/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
}
}
Pour les agents IA : cette page au format Markdown est disponible à https://doitong.com/fr/developers/models/nano-banana-pro.md. Tous les modèles et guides : https://doitong.com/developers/llms.txt