qwen-image-edit-spicy
qwen-image-edit-spicy
Precisely edit images with text instructions. Add, remove, or modify visual elements, transfer styles, and replace backgrounds for photo retouching and visual design.
Examples
Parameters
| Name | Type | Default | Constraints | Description |
|---|---|---|---|---|
| image *Input Image | image_upload | — | image/* · 0–1 items | Image to edit; accepts a URL or base64 data. |
| prompt *Edit Instruction | textarea | — | ≤ 5000 chars | Describe the edit to apply to the image. |
| seedSeed | number | — | ≥ 0 · step 1 | Optional random seed for reproducible results; leave empty to use a random seed. |
Output fields
| Field | Type | Description |
|---|---|---|
| images | array<string> | Generated image URL(s). |
API
Call this model through one unified REST API. Get a key on the API Keys page.
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);Documentation
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.
Related models
xAI Grok Imagine Image v2.0 Edit
xAI Grok Imagine Image V2.0 Edit transforms input images with text prompts, with configurable resolution and quality for precise image editing, visual refinements, creative variations, social content, marketing assets, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Qwen Image 3.0 Pro Edit | Fast Image Editing
Qwen Image 3.0 Pro Edit is a professional-grade image editing model with superior quality and advanced instruction understanding. Up to 2k. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
OpenAI GPT Image 2.5 Sunburst Edit
High-fidelity image editing for precise transformations using up to 16 reference images.
OpenAI GPT Image 2.5 Flare Edit
Fast, balanced image editing from natural-language instructions and up to 16 reference images.
Head Swap (Image)
Swap the head in a photo with the head from a reference image. Upload the target photo first, then the head reference.
Nano Banana Image Edit
Fast & Affordable Editing. Intuitive object replacement and style transfer without manual masking.
Nano Banana Pro Image Edit
4K Semantic Editing.Modifies existing images via natural language with context awareness and multilingual text editing.
Nano Banana 2 Image Edit
4K Semantic Editing.Modifies existing images via natural language with context awareness and multilingual text editing.