Qwen Image 2.1 Turbo Edit
alibaba/qwen-image-2.1-turbo/edit
alibaba/qwen-image-2.1-turbo/edit. 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。
相關模型
完整參數參考、輸出結構與即時價格
| AI 模型 API 市集 | 一個平台,全部完成 | 最受歡迎 | 服務條款 | 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。 |
|---|---|---|---|---|
| prompt *Prompt | textarea | — | ≤ 5000 chars | |
| images *Reference Images | image_upload | — | image/jpeg,image/jpg,image/png,image/bmp,image/tiff,image/webp,image/gif · 1–10 items | |
| nNumber of Images | number | 1 | 1 ~ 6 · step 1 | |
| sizeSize | text | — | ≤ 16 chars | |
| prompt_extendPrompt Extend | boolean | true | — | |
| enable_thinkingThinking Mode | boolean | true | — | |
| seedSeed | number | — | 0 ~ 2147483647 · step 1 |
完整參數參考、輸出結構與即時價格
| 深入了解 | 一個平台,全部完成 | 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。 |
|---|---|---|
| images | array<string> |
API
瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。
cURL
# 1) Submit — returns { "task_uuid": "..." }
curl -X POST "https://www.namifusion.com/api/v1/marketplace/run/alibaba/qwen-image-2.1-turbo/edit" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"prompt": "Use image 1 as the base photo. Replace the background with a clean, bright modern kitchen interior lit by soft natural morning light. Keep the person exactly recognizable with the same face, hairstyle, pose, and clothing, preserving realistic skin texture and proportions. Improve overall sharpness and color balance, add subtle depth of field, and keep the result photorealistic. Remove any distracting objects from the original background, no text, no watermark, no logo.",
"images": [
"https://d1s3annbwribom.cloudfront.net/marketplace/examples/261013/default/905tpxijklp9.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-turbo/edit",
headers=HEADERS,
json={
"input": {
"prompt": "Use image 1 as the base photo. Replace the background with a clean, bright modern kitchen interior lit by soft natural morning light. Keep the person exactly recognizable with the same face, hairstyle, pose, and clothing, preserving realistic skin texture and proportions. Improve overall sharpness and color balance, add subtle depth of field, and keep the result photorealistic. Remove any distracting objects from the original background, no text, no watermark, no logo.",
"images": [
"https://d1s3annbwribom.cloudfront.net/marketplace/examples/261013/default/905tpxijklp9.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-turbo/edit", {
method: "POST",
headers: { ...HEADERS, "Content-Type": "application/json" },
body: JSON.stringify({
"input": {
"prompt": "Use image 1 as the base photo. Replace the background with a clean, bright modern kitchen interior lit by soft natural morning light. Keep the person exactly recognizable with the same face, hairstyle, pose, and clothing, preserving realistic skin texture and proportions. Improve overall sharpness and color balance, add subtle depth of field, and keep the result photorealistic. Remove any distracting objects from the original background, no text, no watermark, no logo.",
"images": [
"https://d1s3annbwribom.cloudfront.net/marketplace/examples/261013/default/905tpxijklp9.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);API 文件
Qwen Image 2.1 Turbo Edit
alibaba/qwen-image-2.1-turbo/edit
Edit images with a prompt and 1–10 reference images; generate 1–6 output images.
Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
prompt | string | true | — | Text prompt describing the desired edit, supports Chinese and English; up to about 4500 tokens is recommended. Negative prompts are not supported, so state anything to avoid directly in the prompt (e.g. "no text"). Ask for a cutout or transparent background and the model outputs a PNG with an alpha channel.; max 5000 characters |
images | array | true | — | Reference images for editing, 1-10 images. Up to 10MB each, 1-8000px per side (384-2048px recommended), aspect ratio up to 10:1. Order defines image 1, image 2 ... image 10 in the prompt.; 1–10 URLs |
n | integer | false | 1 | Generate 1-6 images per request, billed per successfully generated image [1, 6] |
size | string | false | — | Output size in widthheight format. Total pixels from 512512 to 20482048, aspect ratio between 1:8 and 8:1. Recommended: 20482048 (1:1), 26881536 (16:9), 15362688 (9:16), 23681728 (4:3), 17282368 (3:4). Leave empty to let the model auto-select.; max 16 characters |
prompt_extend | boolean | false | true | Automatically expands and optimizes the prompt. Recommended; most useful for short prompts. |
enable_thinking | boolean | false | true | Enhances reasoning to improve image quality at the cost of longer generation time. Only takes effect when Prompt Extend is on. |
seed | integer | false | — | For reproducibility, 0-2147483647. Leave empty for random. [0, 2.14748e+09] |
Pricing
$0.016 per successfully generated image (1.6 credits). Precharge = unit price × requested n; settlement uses the actual successful output image count. Input reference images, output size and prompt expansion add no charge. Default n=1.
size uses width*height; total pixels 512²–2048², aspect ratio 1:8–8:1. Omit size for automatic selection. Omit seed for random generation. enable_thinking only applies when prompt_extend=true.
Alibaba International standard USD list prices. USD 1 = 100 credits. Account discounts are applied separately.
API
curl -X POST https://www.namifusion.com/api/v1/marketplace/run/alibaba/qwen-image-2.1-turbo/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/905tpxijklp9.jpeg"
],
"prompt": "Use image 1 as the base photo. Replace the background with a clean, bright modern kitchen interior lit by soft natural morning light. Keep the person exactly recognizable with the same face, hairstyle, pose, and clothing, preserving realistic skin texture and proportions. Improve overall sharpness and color balance, add subtle depth of field, and keep the result photorealistic. Remove any distracting objects from the original background, no text, no watermark, no logo.",
"prompt_extend": true,
"enable_thinking": true
}
}'
curl 'https://www.namifusion.com/api/v1/marketplace/run/tasks/TASK_UUID' \
-H "Authorization: Bearer $API_KEY"
Poll task_uuid until completed or failed. On success, output.images contains output URL strings.
相關模型
xAI Grok Imagine Image v2.0 Edit
x-ai/grok-imagine-image-v2.0/edit. 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。
qwen-image-edit-spicy
qwen-image-edit-spicy. 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。
Qwen Image 3.0 Pro Edit | Fast Image Editing
qwen-image-3.0-pro/edit. 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。
OpenAI GPT Image 2.5 Sunburst Edit
openai/gpt-image-2.5-sunburst/edit. 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。
OpenAI GPT Image 2.5 Flare Edit
openai/gpt-image-2.5-flare/edit. 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。
Head Swap (Image)
namifusion/head-swap/image-edit. 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。
Nano Banana Image Edit
google/nano-banana/edit. 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。
Nano Banana Pro Image Edit
google/nano-banana-pro/edit. 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。