alibaba/qwen-image-2.1/edit6 點數起 /張· 編輯圖片

Qwen Image 2.1 是阿里巴巴的開源權重圖像模型,既能生成也能編輯。提示詞最長 5000 字元,15 種比例都按比例本身來構圖,包括全景長條和直式手機比例,改圖時最多可用十張參考照片。還能在照片上圈出一塊區域,只改那一部分。

在 POST /jobs/createTask 把模型名稱填成 alibaba/qwen-image-2.1/edit 就能呼叫,6 點數/張起(US$0.06)。新帳戶送 30 點數,可以先在 Playground 免費試用。

  • 生成圖片
  • 編輯圖片
  • 最高 2K
  • 最多 10 張參考圖
  • 15 種畫面比例
模型名稱alibaba/qwen-image-2.1/edit
端點POST 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/qwen-image-2.1/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"
    ],
    "aspect_ratio": "1:1",
    "resolution": "1k",
    "background": "opaque",
    "output_format": "jpeg"
  }
}'

# 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"

input 依下方的 Schema 產生,原樣就能通過驗證。把提示詞和連結換成你自己的即可。

價格

選項點數 /張≈ 美元
resolution 1K5.4US$0.054
resolution 2K7.2US$0.072
resolution 1.5K10.8US$0.11

1 點數 = $0.01 · 全部選項及價格:GET /models/alibaba/qwen-image-2.1/edit

每個任務會無條件進位到整數點數,所以最低檔跑一次是 6 點數/張(US$0.06)。

限制

解析度
1K · 1.5K · 2K
畫面比例
1:1 · 16:9 · 9:16 · 4:3 · 3:4 · 3:2 +9
參考圖
10
提示詞長度(字元)
5,000
單一上傳上限
10 MB

參數

這些欄位來自我們驗證每個請求所用的同一份 Schema。沒列出的欄位會被拒絕。

  • promptstring必填

    Describe the subject, composition, lighting, and any wording to render.

    範圍
    1 – 5000 chars
  • image_urlsarray<string>必填影響價格

    要編輯或合成的照片。在提示詞裡說明每張的用途。

    範圍
    1 – 10 items · image/jpeg, image/png, image/webp, image/gif · ≤ 10 MB
  • mask_urlstring選填

    塗出需要改動的區域。

    範圍
    image/jpeg, image/png, image/webp, image/gif · ≤ 10 MB
  • aspect_ratiostring選填

    畫面形狀:橫式、方形或直式。

    預設值
    "1:1"
    可用值
    "1:1""16:9""9:16""4:3""3:4""3:2""2:3""21:9""9:21""2:1""1:2""3:1""1:3""5:4""4:5"
  • resolutionstring選填影響價格

    輸出尺寸。越大越清晰,價格也越高。

    預設值
    "1k"
    可用值
    "1k""1.5k""2k"
  • enable_prompt_expansionboolean選填

    讓模型替簡短的提示詞補上細節。

    預設值
    true
  • backgroundstring選填

    保留、移除或替換背景。

    預設值
    "opaque"
    可用值
    "opaque""transparent"
  • output_formatstring選填

    結果的檔案格式。

    預設值
    "jpeg"
    可用值
    "jpeg""png""webp"
  • seedinteger選填

    用同一個數字,結果就能重現。

    範圍
    0 – 2147483647
原始 JSON Schema
{
  "additionalProperties": false,
  "properties": {
    "aspect_ratio": {
      "default": "1:1",
      "description": "Output aspect ratio.",
      "enum": [
        "1:1",
        "16:9",
        "9:16",
        "4:3",
        "3:4",
        "3:2",
        "2:3",
        "21:9",
        "9:21",
        "2:1",
        "1:2",
        "3:1",
        "1:3",
        "5:4",
        "4:5"
      ],
      "type": "string"
    },
    "background": {
      "default": "opaque",
      "description": "opaque keeps a normal background; transparent returns the subject alone on a real alpha channel (needs output_format png or webp).",
      "enum": [
        "opaque",
        "transparent"
      ],
      "type": "string"
    },
    "enable_prompt_expansion": {
      "default": true,
      "description": "Rewrite the prompt into a fuller scene description before generating. On by default; turn it off to have the prompt followed word for word.",
      "type": "boolean"
    },
    "image_urls": {
      "description": "One to ten reference images. Each one you add raises the quote.",
      "items": {
        "contentMediaType": [
          "image/jpeg",
          "image/png",
          "image/webp",
          "image/gif"
        ],
        "format": "uri",
        "minLength": 1,
        "type": "string"
      },
      "maxItems": 10,
      "minItems": 1,
      "type": "array"
    },
    "mask_url": {
      "contentMediaType": [
        "image/jpeg",
        "image/png",
        "image/webp",
        "image/gif"
      ],
      "description": "Optional black-and-white mask for local editing: white is the area to repaint, black is kept. Use it with exactly one reference image.",
      "format": "uri",
      "type": "string"
    },
    "output_format": {
      "default": "jpeg",
      "description": "Container of the returned image.",
      "enum": [
        "jpeg",
        "png",
        "webp"
      ],
      "type": "string"
    },
    "prompt": {
      "description": "Describe the subject, composition, lighting, and any wording to render.",
      "maxLength": 5000,
      "minLength": 1,
      "type": "string"
    },
    "resolution": {
      "default": "1k",
      "description": "Output resolution tier.",
      "enum": [
        "1k",
        "1.5k",
        "2k"
      ],
      "type": "string"
    },
    "seed": {
      "description": "Random seed for controlled comparisons.",
      "maximum": 2147483647,
      "minimum": 0,
      "type": "integer"
    }
  },
  "required": [
    "prompt",
    "image_urls"
  ],
  "type": "object"
}

Qwen Image 2.1 的真實成品

Gold gown rooftop
提示詞Dress the woman from Image 1 in the molten-gold satin gown from Image 2 - the same deep cowl back, the same thin gold chain straps, the same floor-length bias-cut drape. Keep her face, her black bob and her calm expression. Put her on a rooftop terrace at night, glancing back over her shoulder so the open cowl back faces the camera, city lights blurred behind her, a single warm lamp raking across the satin. Fashion editorial, 35mm film grain.
透過 API 送出的同一個請求
{
  "model": "alibaba/qwen-image-2.1/edit",
  "input": {
    "prompt": "Dress the woman from Image 1 in the molten-gold satin gown from Image 2 - the same deep cowl back, the same thin gold chain straps, the same floor-length bias-cut drape. Keep her face, her black bob and her calm expression. Put her on a rooftop terrace at night, glancing back over her shoulder so the open cowl back faces the camera, city lights blurred behind her, a single warm lamp raking across the satin. Fashion editorial, 35mm film grain.",
    "image_urls": [
      "https://media.popnow.ai/influencer/examples/marco.webp"
    ],
    "aspect_ratio": "3:4",
    "resolution": "1k",
    "background": "opaque",
    "output_format": "jpeg"
  }
}

這則是從上傳的檔案開始的:把範例連結換成你自己的檔案連結。

回應、輪詢與回呼

所有模型的用法都一樣:先建立任務,再輪詢,或等待回呼。

先報價

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/qwen-image-2.1/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"
    ],
    "aspect_ratio": "1:1",
    "resolution": "1k",
    "background": "opaque",
    "output_format": "jpeg"
  }
}'

請求內容和 createTask 相同。它回傳預估扣款和最高可能扣款,不會真的執行。

已受理

HTTP
HTTP/1.1 202 Accepted

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

HTTP 202 代表任務已受理,點數先凍結、尚未扣除。最終扣款不會超過凍結額。

查詢狀態

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

每隔幾秒查詢一次並逐步拉長間隔,state 變成 succeeded、failed、canceled 或 expired 時停止。

完成的任務

JSON
{
  "code": 200,
  "msg": "success",
  "data": {
    "taskId": "task_01k3m8x9q2z4v7n5p6r8s0t1w3",
    "model": "alibaba/qwen-image-2.1/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"
}

請在 expiresAt 之前從 url 下載。之後需要新連結,請呼叫 POST /common/download-url。

驗證回呼

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
});

設定 callBackUrl 後,我們會把完成的任務送給你。先用原始請求內容驗證簽名,再信任它。

上傳本機檔案

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.

公開的 https 連結可以直接用。本機檔案要先經過 upload-url 和 commit。