Qwen Image 2.1 Pro 图片编辑
alibaba/qwen-image-2.1-pro/edit
使用提示词和 1~10 张参考图编辑图片,单次生成 1~6 张。
示例
参数
| 名称 | 类型 | 默认 | 约束 | 说明 |
|---|---|---|---|---|
| prompt *提示词 | textarea | — | ≤ 5000 chars | 描述所需编辑效果的文本提示词,支持中文和英文,建议不超过 4500 Token。本模型不支持反向提示词,不希望出现的内容请直接写在提示词中(如“不要出现文字”)。要求抠图或透明背景时,模型会自动输出带透明通道的 PNG |
| images *参考图片 | image_upload | — | image/jpeg,image/jpg,image/png,image/bmp,image/tiff,image/webp,image/gif · 1–10 items | 用于编辑的参考图片,1-10 张。单张不超过 10MB,宽高 1-8000 像素(建议 384-2048 像素),长短边比不超过 10:1。多图时按顺序对应提示词中的图1、图2……图10。 |
| n生成张数 | number | 1 | 1 ~ 6 · step 1 | 单次生成 1-6 张图片,按成功生成的张数计费 |
| size尺寸 | text | — | ≤ 16 chars | 输出图片尺寸,格式为宽*高,总像素 512*512 至 2048*2048,宽高比 1:8 至 8:1。推荐:2048*2048(1:1)、2688*1536(16:9)、1536*2688(9:16)、2368*1728(4:3)、1728*2368(3:4)。留空时由模型自动推荐分辨率。 |
| prompt_extend智能改写 | boolean | true | — | 自动扩写优化提示词,官方建议开启,对短提示词效果提升明显 |
| enable_thinking思考模式 | boolean | true | — | 开启后增强推理以提升出图质量,但会增加生成耗时。仅在开启智能改写时生效 |
| seed随机种子 | number | — | 0 ~ 2147483647 · step 1 | 用于结果复现,取值 0-2147483647,留空表示随机 |
输出字段
| 字段 | 类型 | 说明 |
|---|---|---|
| images | array<string> |
API
通过统一 REST API 调用本模型;在 API Keys 页获取密钥。
cURL
# 1) Submit — returns { "task_uuid": "..." }
curl -X POST "https://www.namifusion.com/api/v1/marketplace/run/alibaba/qwen-image-2.1-pro/edit" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"prompt": "Using image 1 as the main product reference and image 2 as the lifestyle scene reference, create a clean premium e-commerce hero image of the same leather handbag placed on a light beige stone pedestal in soft natural studio lighting. Keep the bag'\''s exact shape, color, stitching, hardware, and proportions consistent with the reference. Replace the background with a minimal warm neutral setting, add a subtle soft shadow under the bag, and remove any distracting props. No text, no watermark, no extra bags, no people, no logo changes.",
"images": [
"https://d1s3annbwribom.cloudfront.net/marketplace/examples/261013/default/254gkbbtuykh.jpeg",
"https://d1s3annbwribom.cloudfront.net/marketplace/examples/261013/default/5f4s804daar9.jpeg"
],
"n": 1,
"size": "2048*2048",
"prompt_extend": true,
"enable_thinking": true,
"seed": 12345
}
}'
# 2) Poll until status is "completed", then read the output URLs
curl "https://www.namifusion.com/api/v1/marketplace/run/tasks/TASK_UUID" \
-H "Authorization: Bearer YOUR_API_KEY"Python
import time, requests
API_KEY = "YOUR_API_KEY"
HEADERS = {"Authorization": f"Bearer {API_KEY}"}
# 1) Submit
resp = requests.post(
"https://www.namifusion.com/api/v1/marketplace/run/alibaba/qwen-image-2.1-pro/edit",
headers=HEADERS,
json={
"input": {
"prompt": "Using image 1 as the main product reference and image 2 as the lifestyle scene reference, create a clean premium e-commerce hero image of the same leather handbag placed on a light beige stone pedestal in soft natural studio lighting. Keep the bag's exact shape, color, stitching, hardware, and proportions consistent with the reference. Replace the background with a minimal warm neutral setting, add a subtle soft shadow under the bag, and remove any distracting props. No text, no watermark, no extra bags, no people, no logo changes.",
"images": [
"https://d1s3annbwribom.cloudfront.net/marketplace/examples/261013/default/254gkbbtuykh.jpeg",
"https://d1s3annbwribom.cloudfront.net/marketplace/examples/261013/default/5f4s804daar9.jpeg"
],
"n": 1,
"size": "2048*2048",
"prompt_extend": True,
"enable_thinking": True,
"seed": 12345
}
},
)
resp.raise_for_status() # 401/402/429/5xx stop here instead of polling a bad task
task = resp.json()
# 2) Poll until a terminal state (completed / failed / cancelled).
# This model is allowed up to 1800s server-side.
deadline = time.time() + 1860
while task.get("status") not in ("completed", "failed", "cancelled"):
if time.time() > deadline:
raise TimeoutError(f"still {task.get('status')} — keep the task_uuid and poll later")
time.sleep(3)
poll = requests.get(f"https://www.namifusion.com/api/v1/marketplace/run/tasks/{task['task_uuid']}", headers=HEADERS)
poll.raise_for_status()
task = poll.json()
print(task["status"], task.get("output"))JavaScript
const API_KEY = "YOUR_API_KEY";
const HEADERS = { Authorization: `Bearer ${API_KEY}` };
// 1) Submit
const resp = await fetch("https://www.namifusion.com/api/v1/marketplace/run/alibaba/qwen-image-2.1-pro/edit", {
method: "POST",
headers: { ...HEADERS, "Content-Type": "application/json" },
body: JSON.stringify({
"input": {
"prompt": "Using image 1 as the main product reference and image 2 as the lifestyle scene reference, create a clean premium e-commerce hero image of the same leather handbag placed on a light beige stone pedestal in soft natural studio lighting. Keep the bag's exact shape, color, stitching, hardware, and proportions consistent with the reference. Replace the background with a minimal warm neutral setting, add a subtle soft shadow under the bag, and remove any distracting props. No text, no watermark, no extra bags, no people, no logo changes.",
"images": [
"https://d1s3annbwribom.cloudfront.net/marketplace/examples/261013/default/254gkbbtuykh.jpeg",
"https://d1s3annbwribom.cloudfront.net/marketplace/examples/261013/default/5f4s804daar9.jpeg"
],
"n": 1,
"size": "2048*2048",
"prompt_extend": true,
"enable_thinking": true,
"seed": 12345
}
}),
});
if (!resp.ok) throw new Error(`submit failed: ${resp.status} ${await resp.text()}`);
let task = await resp.json();
// 2) Poll until a terminal state (completed / failed / cancelled).
// This model is allowed up to 1800s server-side.
const deadline = Date.now() + 1860 * 1000;
while (!["completed", "failed", "cancelled"].includes(task.status)) {
if (Date.now() > deadline) throw new Error(`still ${task.status} — keep the task_uuid and poll later`);
await new Promise((r) => setTimeout(r, 3000));
const poll = await fetch(`https://www.namifusion.com/api/v1/marketplace/run/tasks/${task.task_uuid}`, { headers: HEADERS });
if (!poll.ok) throw new Error(`poll failed: ${poll.status}`);
task = await poll.json();
}
console.log(task.status, task.output);文档
Qwen Image 2.1 Pro 图片编辑
alibaba/qwen-image-2.1-pro/edit
使用提示词和 1~10 张参考图编辑图片,单次生成 1~6 张。
参数
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
prompt | string | true | — | 描述所需编辑效果的文本提示词,支持中文和英文,建议不超过 4500 Token。本模型不支持反向提示词,不希望出现的内容请直接写在提示词中(如“不要出现文字”)。要求抠图或透明背景时,模型会自动输出带透明通道的 PNG; max 5000 characters |
images | array | true | — | 用于编辑的参考图片,1-10 张。单张不超过 10MB,宽高 1-8000 像素(建议 384-2048 像素),长短边比不超过 10:1。多图时按顺序对应提示词中的图1、图2……图10。; 1–10 URLs |
n | integer | false | 1 | 单次生成 1-6 张图片,按成功生成的张数计费 [1, 6] |
size | string | false | — | 输出图片尺寸,格式为宽高,总像素 512512 至 20482048,宽高比 1:8 至 8:1。推荐:20482048(1:1)、26881536(16:9)、15362688(9:16)、23681728(4:3)、17282368(3:4)。留空时由模型自动推荐分辨率。; max 16 characters |
prompt_extend | boolean | false | true | 自动扩写优化提示词,官方建议开启,对短提示词效果提升明显 |
enable_thinking | boolean | false | true | 开启后增强推理以提升出图质量,但会增加生成耗时。仅在开启智能改写时生效 |
seed | integer | false | — | 用于结果复现,取值 0-2147483647,留空表示随机 [0, 2.14748e+09] |
价格
每张成功生成的图片 $0.04(4 积分)。按请求 n 预扣,按实际成功输出张数结算。参考图片、输出尺寸、提示词扩展均不额外收费。默认 n=1。
size 使用宽*高格式,总像素为 512²~2048²,宽高比 1:8~8:1;省略时自动选择。省略 seed 使用随机种子。enable_thinking 仅在 prompt_extend=true 时生效。
采用 Alibaba International 国际部署标准美元标价。1 美元=100 积分,账户折扣另行计算。
API
curl -X POST https://www.namifusion.com/api/v1/marketplace/run/alibaba/qwen-image-2.1-pro/edit \
-H "Authorization: Bearer $API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"input": {
"n": 1,
"seed": 12345,
"size": "2048*2048",
"images": [
"https://d1s3annbwribom.cloudfront.net/marketplace/examples/261013/default/254gkbbtuykh.jpeg",
"https://d1s3annbwribom.cloudfront.net/marketplace/examples/261013/default/5f4s804daar9.jpeg"
],
"prompt": "Using image 1 as the main product reference and image 2 as the lifestyle scene reference, create a clean premium e-commerce hero image of the same leather handbag placed on a light beige stone pedestal in soft natural studio lighting. Keep the bag'"'"'s exact shape, color, stitching, hardware, and proportions consistent with the reference. Replace the background with a minimal warm neutral setting, add a subtle soft shadow under the bag, and remove any distracting props. No text, no watermark, no extra bags, no people, no logo changes.",
"prompt_extend": true,
"enable_thinking": true
}
}'
curl 'https://www.namifusion.com/api/v1/marketplace/run/tasks/TASK_UUID' \
-H "Authorization: Bearer $API_KEY"
使用 task_uuid 轮询至 completed 或 failed。成功时 output.images 为输出 URL 字符串数组。
相关模型
xAI Grok Imagine Image v2.0 图片编辑
xAI Grok Imagine Image V2.0 Edit 可根据文本提示词对输入图片进行编辑,并支持可配置的分辨率和质量,适用于精细图片编辑、视觉优化、创意变体、社交内容、营销素材和生产工作流。提供开箱即用的 REST 推理 API,性能出色,无冷启动,价格实惠。
qwen-image-edit-spicy
通过文本指令精确编辑图片,可添加、移除或修改画面元素,也支持风格迁移和背景替换,适合照片修饰与视觉设计。
Qwen Image 3.0 Pro Edit|快速图片编辑
Qwen Image 3.0 Pro Edit 是一款专业级图片编辑模型,具备出色的画质和高级指令理解能力。最高支持 2k。提供开箱即用的 REST inference API,性能优异,无冷启动,价格实惠。
OpenAI GPT Image 2.5 Sunburst 图像编辑
使用最多 16 张参考图片完成高保真、精确的图像编辑。
OpenAI GPT Image 2.5 Flare 图像编辑
使用自然语言指令和最多 16 张参考图片进行快速、均衡的图像编辑。
图片换头
将照片中的人物头部替换为参考图中的头部。先上传目标照片,再上传头部参考图。
Nano Banana 图像编辑
高性价比智能修图。 无需蒙版即可实现物体替换与风格迁移,极速响应,成本低廉。
Nano Banana Pro 图像编辑
4K 语义级修图。基于自然语言修改现有图像,支持智能光影融合与图像内多语言文字编辑。