alibaba/wan-2.7/editDa 5 crediti per immagine· Modifica immagine

L’image-to-image Wan 2.7 di Alibaba unisce o modifica da una a nove immagini di riferimento in una nuova immagine con un’unica istruzione.

Lo chiami con il nome di modello alibaba/wan-2.7/edit su POST /jobs/createTask, da 5 crediti per immagine (0,05 USD). I nuovi account ricevono 30 crediti gratuiti per provarlo prima nel Playground.

  • Crea immagine
  • Modifica immagine
  • Fino a 2K
  • Fino a 9 immagini di riferimento
  • 7 formati
  • Fino a 4 per generazione
Nome del modelloalibaba/wan-2.7/edit
EndpointPOST https://api.popnow.ai/api/v1/jobs/createTask
# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -d '{
  "model": "alibaba/wan-2.7/edit",
  "input": {
    "prompt": "A ceramic teapot on a linen cloth, soft window light, muted palette",
    "image_urls": [
      "https://media.popnow.ai/influencer/examples/marco.webp"
    ],
    "num_outputs": 1,
    "resolution": "1k"
  }
}'

# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

L’input è costruito dallo schema qui sotto, quindi supera la verifica così com’è. Sostituisci prompt e link con i tuoi.

Prezzo

OpzioneCrediti per immagine≈ USD
Standard4,50,045 USD

1 credito = 0,01 $ · Tutte le opzioni e i prezzi: GET /models/alibaba/wan-2.7/edit

Ogni attività è arrotondata per eccesso ai crediti interi, quindi un'esecuzione al livello più basso costa 5 crediti per immagine (0,05 USD).

Limiti

Risoluzioni
1K · 2K
Proporzioni
1:1 · 4:3 · 3:4 · 16:9 · 9:16 · 3:2 · 2:3
Risultati per chiamata
1–4
Immagini di riferimento
9
Lunghezza del prompt (caratteri)
5,000

Parametri

Questi campi vengono dallo stesso schema con cui verifichiamo ogni richiesta. I campi non elencati vengono rifiutati.

  • promptstringObbligatorio

    Describe the image to produce from the source: subject, composition, style, and lighting.

    Intervallo
    1 – 5000 chars
  • image_urlsarray<string>Obbligatorio

    Foto da modificare o combinare. Spiega nel prompt cosa aggiunge ciascuna.

    Intervallo
    1 – 9 items · image/jpeg, image/png, image/webp, image/gif
  • bounding_boxesarray<object>Facoltativo

    Rectangles marking the areas to edit, in pixels from the top-left corner of the reference image each one belongs to. Up to 2 per image.

    Intervallo
    0 – 18 items
    Campi interni
    • bounding_boxes[].image_indexintegerObbligatorio

      Which reference image the box is on, counting from 1 in upload order.

      Intervallo
      1 – 9
    • bounding_boxes[].x1integerObbligatorio

      Left edge of the box, in pixels.

      Intervallo
      0 – …
    • bounding_boxes[].y1integerObbligatorio

      Top edge of the box, in pixels.

      Intervallo
      0 – …
    • bounding_boxes[].x2integerObbligatorio

      Right edge of the box, in pixels.

      Intervallo
      0 – …
    • bounding_boxes[].y2integerObbligatorio

      Bottom edge of the box, in pixels.

      Intervallo
      0 – …
  • aspect_ratiostringFacoltativo

    La forma dell'inquadratura: larga, quadrata o verticale.

    Valori ammessi
    "1:1""4:3""3:4""16:9""9:16""3:2""2:3"
  • num_outputsintegerFacoltativoCambia il prezzo

    Quanti risultati creare in una volta.

    Predefinito
    1
    Intervallo
    1 – 4
  • resolutionstringFacoltativo

    Dimensione dell'output. Più grande è più nitido e costa di più.

    Predefinito
    "1k"
    Valori ammessi
    "1k""2k"
  • color_palettearray<object>Facoltativo

    Custom colour theme: 3 to 10 colours, each with an optional share of the image in percent. Leave the shares empty to split them evenly.

    Intervallo
    3 – 10 items
    Campi interni
    • color_palette[].hexstringObbligatorio

      The colour as a six-digit hex code, for example #C2D1E6.

    • color_palette[].rationumberFacoltativo

      How much of the image this colour should cover, in percent. Leave it empty to share the remainder evenly with the other empty rows.

      Intervallo
      0.01 – 100
  • seedintegerFacoltativo

    Lo stesso numero dà un risultato ripetibile.

    Intervallo
    0 – 2147483647
JSON Schema grezzo
{
  "additionalProperties": false,
  "properties": {
    "aspect_ratio": {
      "description": "Aspect ratio of the generated image. Omit it to follow the proportions of the last source image.",
      "enum": [
        "1:1",
        "4:3",
        "3:4",
        "16:9",
        "9:16",
        "3:2",
        "2:3"
      ],
      "type": "string"
    },
    "bounding_boxes": {
      "description": "Rectangles marking the areas to edit, in pixels from the top-left corner of the reference image each one belongs to. Up to 2 per image.",
      "items": {
        "additionalProperties": false,
        "properties": {
          "image_index": {
            "description": "Which reference image the box is on, counting from 1 in upload order.",
            "maximum": 9,
            "minimum": 1,
            "type": "integer"
          },
          "x1": {
            "description": "Left edge of the box, in pixels.",
            "minimum": 0,
            "type": "integer"
          },
          "x2": {
            "description": "Right edge of the box, in pixels.",
            "minimum": 0,
            "type": "integer"
          },
          "y1": {
            "description": "Top edge of the box, in pixels.",
            "minimum": 0,
            "type": "integer"
          },
          "y2": {
            "description": "Bottom edge of the box, in pixels.",
            "minimum": 0,
            "type": "integer"
          }
        },
        "required": [
          "image_index",
          "x1",
          "y1",
          "x2",
          "y2"
        ],
        "type": "object"
      },
      "maxItems": 18,
      "type": "array"
    },
    "color_palette": {
      "description": "Custom colour theme: 3 to 10 colours, each with an optional share of the image in percent. Leave the shares empty to split them evenly.",
      "items": {
        "additionalProperties": false,
        "properties": {
          "hex": {
            "description": "The colour as a six-digit hex code, for example #C2D1E6.",
            "pattern": "^#[0-9A-Fa-f]{6}$",
            "type": "string"
          },
          "ratio": {
            "description": "How much of the image this colour should cover, in percent. Leave it empty to share the remainder evenly with the other empty rows.",
            "maximum": 100,
            "minimum": 0.01,
            "type": "number"
          }
        },
        "required": [
          "hex"
        ],
        "type": "object"
      },
      "maxItems": 10,
      "minItems": 3,
      "type": "array"
    },
    "image_urls": {
      "description": "Source images that you are authorised to process.",
      "items": {
        "contentMediaType": [
          "image/jpeg",
          "image/png",
          "image/webp",
          "image/gif"
        ],
        "format": "uri",
        "type": "string"
      },
      "maxItems": 9,
      "minItems": 1,
      "type": "array"
    },
    "num_outputs": {
      "default": 1,
      "description": "How many images to generate in one run.",
      "maximum": 4,
      "minimum": 1,
      "type": "integer"
    },
    "prompt": {
      "description": "Describe the image to produce from the source: subject, composition, style, and lighting.",
      "maxLength": 5000,
      "minLength": 1,
      "type": "string"
    },
    "resolution": {
      "default": "1k",
      "description": "Output resolution tier. With aspect_ratio omitted, the output follows the last source image's proportions at this tier.",
      "enum": [
        "1k",
        "2k"
      ],
      "type": "string"
    },
    "seed": {
      "description": "Random seed. Omit to let the model pick one.",
      "maximum": 2147483647,
      "minimum": 0,
      "type": "integer"
    }
  },
  "required": [
    "prompt",
    "image_urls"
  ],
  "type": "object"
}

Un risultato reale di Wan 2.7

A woman in a cream cable-knit sweater, black tights and a red scarf stands on cracked black ice at blue hour, bare birch trees behind her.
PromptKeep the woman's face, body proportions and exact pose unchanged. Replace the white studio with a frozen lake at blue hour: cracked black ice underfoot, bare birch trees and a low band of pale winter light on the horizon, snow drifting sideways. Change her clothing to a heavy cream cable-knit sweater slipping off one shoulder over black opaque tights, with a scarlet wool scarf loose around her neck and scarlet mittens in one hand. Add wind-blown hair, frost on her eyelashes and faint breath vapour. Relight the whole image with cold pale blue ambient light and a weak amber sun grazing her shoulder from behind. Everything desaturated except the scarlet scarf. No text, no logos.
La stessa richiesta tramite API
{
  "model": "alibaba/wan-2.7/edit",
  "input": {
    "prompt": "Keep the woman's face, body proportions and exact pose unchanged. Replace the white studio with a frozen lake at blue hour: cracked black ice underfoot, bare birch trees and a low band of pale winter light on the horizon, snow drifting sideways. Change her clothing to a heavy cream cable-knit sweater slipping off one shoulder over black opaque tights, with a scarlet wool scarf loose around her neck and scarlet mittens in one hand. Add wind-blown hair, frost on her eyelashes and faint breath vapour. Relight the whole image with cold pale blue ambient light and a weak amber sun grazing her shoulder from behind. Everything desaturated except the scarlet scarf. No text, no logos.",
    "image_urls": [
      "https://media.popnow.ai/influencer/examples/marco.webp"
    ],
    "num_outputs": 1,
    "resolution": "1k"
  }
}

Questo risultato parte da un file caricato: metti il tuo link al posto di quello d’esempio.

Risposte, polling e callback

Tutti i modelli funzionano allo stesso modo: crei un task, poi lo interroghi o aspetti la callback.

Prima il prezzo

cURL
curl -X POST https://api.popnow.ai/api/v1/jobs/quote \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "alibaba/wan-2.7/edit",
  "input": {
    "prompt": "A ceramic teapot on a linen cloth, soft window light, muted palette",
    "image_urls": [
      "https://media.popnow.ai/influencer/examples/marco.webp"
    ],
    "num_outputs": 1,
    "resolution": "1k"
  }
}'

Stesso corpo di createTask. Restituisce l’addebito previsto e quello massimo possibile, senza eseguire nulla.

Accettata

HTTP
HTTP/1.1 202 Accepted

{
  "code": 200,
  "msg": "success",
  "data": {
    "taskId": "task_01k3m8x9q2z4v7n5p6r8s0t1w3",
    "state": "queued"
  },
  "request_id": "req_example_create"
}

HTTP 202 significa che il task è stato accettato e i crediti sono riservati, non ancora addebitati. L’addebito finale non supera mai la riserva.

Controlla lo stato

cURL
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

Controlla ogni pochi secondi allungando via via l’intervallo e fermati quando state è succeeded, failed, canceled o expired.

Task completato

JSON
{
  "code": 200,
  "msg": "success",
  "data": {
    "taskId": "task_01k3m8x9q2z4v7n5p6r8s0t1w3",
    "model": "alibaba/wan-2.7/edit",
    "state": "succeeded",
    "output": {
      "assets": [
        {
          "url": "https://cdn.popnow.ai/tasks/task_01k3m8x9q2z4v7n5p6r8s0t1w3/output.png?signature=FROM_RESPONSE",
          "expiresAt": "2026-10-17T12:20:00Z",
          "mime": "image/png",
          "width": 1024,
          "height": 1024
        }
      ]
    },
    "settled": true
  },
  "request_id": "req_example_record"
}

Scarica dall’url prima di expiresAt. Ti serve un link nuovo più tardi? Chiedilo con POST /common/download-url.

Verifica una callback

Node.js
import { createHash, createHmac, timingSafeEqual } from "node:crypto";
import express from "express";

const app = express();
// express.raw keeps the exact bytes that were signed; express.json would not match.
app.post("/hooks/popnow", express.raw({ type: "application/json" }), (req, res) => {
  const timestamp = req.header("X-Webhook-Timestamp");
  const signature = req.header("X-Webhook-Signature") ?? "";
  const body = JSON.parse(req.body.toString("utf8"));
  const taskId = body.data?.taskId ?? body.task_id;
  const digest = createHash("sha256").update(req.body).digest("hex");
  const expected = createHmac("sha256", process.env.POPNOW_WEBHOOK_SECRET)
    .update(`${taskId}.${timestamp}.${digest}`)
    .digest("base64");
  const ok = expected.length === signature.length && timingSafeEqual(Buffer.from(expected), Buffer.from(signature));
  // Check the signature first, then reject anything older than five minutes.
  if (!ok || Math.abs(Date.now() / 1000 - Number(timestamp)) > 300) return res.status(401).end();
  res.status(200).end(); // answer fast, then fetch the task and store its files
});

Con callBackUrl impostata ti inviamo il task completato. Verifica la firma sul corpo grezzo prima di fidarti.

Invia un file locale

cURL
curl -X POST https://api.popnow.ai/api/v1/common/upload-url \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"contentType": "image/png", "bytes": 482113}'

# PUT the file bytes to data.uploadUrl with every header in data.headers, then commit it:
curl -X POST https://api.popnow.ai/api/v1/files/$FILE_ID/commit \
  -H "Authorization: Bearer $POPNOW_API_KEY"
# The commit returns a popnow://f/... reference. Put it in any image, video or
# audio field of the task input instead of a public https URL.

I link https pubblici funzionano così come sono. I file locali passano prima da upload-url e commit.