New: Nano Banana 2.1Try the model
API Stock

Imagen

Edición de imágenes

Editar imágenes con referencias: fondos, productos, estilo y acciones de Midjourney.

1 min de lectura2 secciones

Una edición es una instrucción: diga qué cambia y qué no puede cambiar. Las referencias comunican el aspecto deseado mejor que muchos adjetivos.

Principios prácticos

Elija el modelo según la prioridad — rapidez, fidelidad, resolución o control — y guarde parámetros y versión de cada resultado. nano-banana-*, gpt-image-2, wan2.7-image and midjourney — Image editing.

Cambie una sola cosa por intento. Las salidas buenas se convierten en referencias y en el punto de partida más fiable para la siguiente iteración.

Trate finished y failed como estados finales. Use polling o webhooks, conserve errores sin procesar en el servidor y muestre mensajes seguros al usuario.

Prompts y ejemplos de API

text
Replace the overcast sky with a clear blue one. Keep the building, the
lighting on the facade and the framing exactly as they are.
The original living-room input supplied with the Google editing example; its generation prompt is not published.
The original living-room input supplied with the Google editing example; its generation prompt is not published.

Source: Google AI for Developers, used under CC BY 4.0; format and dimensions adapted.

text
Using the provided image of a living room, change only the blue sofa to be a
vintage, brown leather chesterfield sofa. Keep the rest of the room, including
the pillows on the sofa and the lighting, unchanged.
Nano Banana 2.1 changes only the sofa while retaining the room, pillows and lighting from the source.
Nano Banana 2.1 changes only the sofa while retaining the room, pillows and lighting from the source.

Source: Google AI for Developers, used under CC BY 4.0; format and dimensions adapted.

text
Put the chair from image 1 into the room from image 2. Match the window light
and cast a soft shadow on the floor. Do not change the room's furniture or
the chair's upholstery.
text
The person from the reference, now standing on a train platform at night,
three-quarter view, rain, sodium lighting. Keep their face, hair and jacket
identical to the reference.
text
Redraw image 1 in the visual style of image 2 — same palette, line weight and
grain. Keep the composition and subject of image 1 unchanged.
text
A ceramic mug in the masked area, same lighting and perspective as the rest of
the frame

About these samples. Ready-made examples are copied to our own storage only when their source permits reuse. The exact prompt appears above each result, and the original source and license are linked below the media.

json
{
"model": "z-image",
"input": {
"prompt": "Replace the overcast sky with a clear blue one, keep the lighting on the building consistent",
"urls": ["https://example.com/facade.jpg"]
}
}
json
{
"model": "wan2.7-image",
"input": {
"prompt": "Put the chair from image 1 into the room from image 2, matching the window light",
"urls": ["https://example.com/chair.png", "https://example.com/room.jpg"],
"size": "3:2"
}
}
sh
curl -X POST https://api.api-stock.com/api/v1/generation/create \
-H "Authorization: Bearer sk-your-key" \
-H "Content-Type: application/json" \
-d '{
"model": "midjourney",
"input": {
"action": "imagine",
"prompt": "A weathered brass diving helmet on a workshop bench, volumetric dust",
"size": "1:1",
"version": "7",
"stylize": 300
}
}'
json
{
"code": 200,
"data": {
"taskId": "019ca8c4-3e17-7b55-9f10-cc2b6de0a8f4",
"status": "not_started",
"createdAt": "2026-02-28T13:07:45.000Z"
}
}
json
{
"code": 200,
"data": {
"taskId": "019ca8c4-3e17-7b55-9f10-cc2b6de0a8f4",
"status": "finished",
"files": [
{
"fileUrl": "https://storage.api-stock.com/generated/mj-grid-4c81.png",
"fileType": "image"
}
],
"createdTime": "2026-02-28T13:07:45.000Z"
}
}
sh
curl -X POST https://api.api-stock.com/api/v1/generation/create \
-H "Authorization: Bearer sk-your-key" \
-H "Content-Type: application/json" \
-d '{
"model": "midjourney",
"input": {
"action": "upscale",
"parentTaskId": "019ca8c4-3e17-7b55-9f10-cc2b6de0a8f4",
"index": 2
}
}'
ts
const BASE = "https://api.api-stock.com/api/v1";
const KEY = process.env.API_STOCK_KEY!;
async function submit(input: Record<string, unknown>): Promise<string> {
const res = await fetch(`${BASE}/generation/create`, {
method: "POST",
headers: {
Authorization: `Bearer ${KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({ model: "midjourney", input }),
});
const body = await res.json();
if (!res.ok) throw new Error(`${body.error.code}: ${body.error.message}`);
return body.data.taskId;
}
async function wait(taskId: string) {
for (;;) {
await new Promise((r) => setTimeout(r, 5_000));
const res = await fetch(`${BASE}/task/status/${taskId}`, {
headers: { Authorization: `Bearer ${KEY}` },
});
const body = await res.json().catch(() => null);
if (!res.ok) {
const message = body?.error?.message ?? `${res.status} ${res.statusText}`;
throw new Error(message);
}
const { data } = body;
if (data.status === "finished") return data;
if (data.status === "failed") throw new Error(data.errorMessage);
}
}
const gridId = await submit({
action: "imagine",
prompt:
"A weathered brass diving helmet on a workshop bench, volumetric dust",
size: "1:1",
version: "7",
stylize: 300,
});
await wait(gridId);
const upscaleId = await submit({
action: "upscale",
parentTaskId: gridId,
index: 2,
});
const upscaled = await wait(upscaleId);
console.log(upscaled.files[0].fileUrl); // → https://storage.api-stock.com/...
json
{
"model": "midjourney",
"input": {
"action": "pan",
"parentTaskId": "019ca8c4-3e17-7b55-9f10-cc2b6de0a8f4",
"index": 2,
"direction": "left"
}
}
json
{
"model": "midjourney",
"input": {
"action": "zoom",
"parentTaskId": "019ca8c4-3e17-7b55-9f10-cc2b6de0a8f4",
"index": 2,
"zoomRatio": 1.5
}
}
json
{
"model": "midjourney",
"input": {
"action": "modal",
"parentTaskId": "019ca8c4-3e17-7b55-9f10-cc2b6de0a8f4",
"index": 2,
"prompt": "Replace the bench with a slab of sea-worn granite",
"maskUrl": "https://example.com/mask.png"
}
}
json
{
"model": "midjourney",
"input": {
"action": "describe",
"imageUrls": ["https://example.com/reference.jpg"]
}
}
json
{
"model": "midjourney",
"input": {
"action": "blend",
"imageUrls": [
"https://example.com/texture-a.jpg",
"https://example.com/texture-b.jpg",
"https://example.com/texture-c.jpg"
],
"dimensions": "LANDSCAPE"
}
}
json
{
"code": 400,
"error": {
"message": "action \"variation\" requires index or customId",
"type": "BadRequest",
"code": "invalid_input"
}
}

Ejecútalo con tu propia clave

Elija un modelo en el catálogo de API Stock, consulte su precio y pruébelo en el navegador o por API.

Seguir leyendo