qwen-image-edit-spicy
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。
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。 |
|---|---|---|---|---|
| image *Input Image | image_upload | — | image/* · 0–1 items | |
| prompt *Edit Instruction | textarea | — | ≤ 5000 chars | |
| seedSeed | number | — | ≥ 0 · 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/qwen-image-edit-spicy" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"image": [
"https://assets-public.namifusion.com/marketplace/images/2026-06-12/638e1ee18ac7.jpeg"
],
"prompt": "Replace the background with a clean modern studio, add soft directional lighting, and preserve the subject identity and fine details."
}
}'
# 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/qwen-image-edit-spicy",
headers=HEADERS,
json={
"input": {
"image": [
"https://assets-public.namifusion.com/marketplace/images/2026-06-12/638e1ee18ac7.jpeg"
],
"prompt": "Replace the background with a clean modern studio, add soft directional lighting, and preserve the subject identity and fine details."
}
},
)
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 180s server-side.
deadline = time.time() + 240
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/qwen-image-edit-spicy", {
method: "POST",
headers: { ...HEADERS, "Content-Type": "application/json" },
body: JSON.stringify({
"input": {
"image": [
"https://assets-public.namifusion.com/marketplace/images/2026-06-12/638e1ee18ac7.jpeg"
],
"prompt": "Replace the background with a clean modern studio, add soft directional lighting, and preserve the subject identity and fine details."
}
}),
});
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 180s server-side.
const deadline = Date.now() + 240 * 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-edit-spicy
Apply precise prompt-driven edits to a source image while preserving the details that should remain unchanged.
qwen-image-edit-spicy is a focused image-editing model for transforming one input image with a natural-language instruction. It is suited to background replacement, visual restyling, lighting changes, object-level adjustments, and polished creative variants. The compact parameter set keeps the workflow direct: provide an image, explain the intended edit, and optionally specify a seed for comparable iterations.
Key Features
- Instruction-led editing: Uses a written edit request to determine what should change in the source image.
- Strong preservation workflow: Prompts can explicitly retain identity, composition, branding, materials, or other important details.
- Flexible creative changes: Supports background, lighting, color, atmosphere, and style transformations in one request.
- Simple input contract: Requires only one image and one prompt, making it easy to test and integrate.
- URL and base64 image input: The Marketplace uploader accepts a hosted image or base64 image data.
- Seed control: An optional seed helps produce comparable variations during prompt refinement.
Technical Specifications
| Item | Details |
|---|---|
| Task | Image editing / image-to-image |
| Required input | image, prompt |
| Image input | One image URL or base64 payload |
| Prompt length | Up to 5,000 characters |
| Optional input | seed, integer value starting at 0 |
| Output | Generated image URL |
| Typical workflow | Source image plus a concrete edit instruction |
Sample Prompts
Replace the background with a clean modern studio, add soft directional lighting, and preserve the subject identity, pose, and clothing.Keep the product shape, logo, and material unchanged; place it on a dark reflective surface with premium commercial lighting.Convert the scene to a rainy evening with cool cinematic color grading while retaining every person and the original composition.
Pricing
| Item | Price |
|---|---|
| One edited image | 4 credits |
This value reproduces the existing Marketplace pricing configuration; this documentation update does not alter pricing.
Best Use Cases
- E-commerce background cleanup and product presentation.
- Advertising and social creative variants from an approved source image.
- Portrait relighting, atmosphere changes, and controlled restyling.
- Rapid design iteration that must preserve selected visual elements.
Best Practices
State both what should change and what must remain unchanged. Refer to concrete attributes such as subject identity, pose, logo, material, camera angle, and background. Avoid combining unrelated transformations in one instruction; a short sequence of focused edits generally gives more predictable results than one overloaded prompt.
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 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。
Nano Banana 2 Image Edit
google/nano-banana-2/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。