Qwen Image 3.0 Pro Edit | Fast Image Editing
qwen-image-3.0-pro/edit
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.
Examples
Parameters
| Name | Type | Default | Constraints | Description |
|---|---|---|---|---|
| prompt *Prompt | textarea | — | ≤ 5000 chars | Text prompt describing the desired edit, supports Chinese and English |
| images *Reference Images | image_upload | — | image/jpeg,image/jpg,image/png,image/bmp,image/tiff,image/webp,image/gif · 1–3 items | Reference images for editing, 1-3 images. 384-2048px per side recommended, up to 10MB each. Order defines image 1/2/3 in the prompt. |
| nNumber of Images | number | 1 | 1 ~ 6 · step 1 | Generate 1-6 images per request |
| sizeSize | text | — | ≤ 16 chars | Output size in width*height format, from 512*512 to 2048*2048 (e.g., 1024*1024, 1280*720). Leave empty to let the model auto-select. |
| negative_promptNegative Prompt | textarea | — | — | Describe what should not appear in the image |
| prompt_extendPrompt Extend | boolean | true | — | Automatically expands and optimizes the prompt. Recommended; most useful for short prompts. |
| seedSeed | number | — | 0 ~ 2147483647 · step 1 | For reproducibility, 0-2147483647. Leave empty for random. |
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-3.0-pro/edit" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"prompt": "Preserve the subject and composition, replace the background with a clean modern studio, add soft cinematic lighting, and retain natural textures.",
"images": [
"https://assets-public.namifusion.com/marketplace/images/2026-06-12/638e1ee18ac7.jpeg"
],
"n": 1,
"prompt_extend": true
}
}'
# 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-3.0-pro/edit",
headers=HEADERS,
json={
"input": {
"prompt": "Preserve the subject and composition, replace the background with a clean modern studio, add soft cinematic lighting, and retain natural textures.",
"images": [
"https://assets-public.namifusion.com/marketplace/images/2026-06-12/638e1ee18ac7.jpeg"
],
"n": 1,
"prompt_extend": True
}
},
)
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 300s server-side.
deadline = time.time() + 360
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-3.0-pro/edit", {
method: "POST",
headers: { ...HEADERS, "Content-Type": "application/json" },
body: JSON.stringify({
"input": {
"prompt": "Preserve the subject and composition, replace the background with a clean modern studio, add soft cinematic lighting, and retain natural textures.",
"images": [
"https://assets-public.namifusion.com/marketplace/images/2026-06-12/638e1ee18ac7.jpeg"
],
"n": 1,
"prompt_extend": true
}
}),
});
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 300s server-side.
const deadline = Date.now() + 360 * 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 3.0 Pro Edit
Professional image editing with strong instruction following, fast inference, and up to 2K output.
Qwen Image 3.0 Pro Edit is a production-ready image editing model designed for high-quality visual transformation based on reference images. It combines superior edit quality, advanced prompt understanding, and fast, no-cold-start performance, making it a strong choice for teams that need reliable results at an affordable price.
🚀 Key Features
- Professional-grade editing quality: Optimized for high-fidelity edits that preserve subject identity while enabling replacement, enhancement, stylization, and scene changes.
- Advanced prompt understanding: Handles detailed editing instructions more accurately, enabling finer control over composition, style, and visual attributes.
- Multi-image reference editing: Accepts 1-3 reference images; their order defines image 1/2/3 in the prompt — useful for consistency, style transfer, and multi-element composition.
- Batch generation: Produces up to 6 edited images in a single request for faster comparison and selection.
- Bilingual prompt support: Supports both Chinese and English prompts for flexible multilingual workflows.
- Up to 2K output: Delivers images up to 2048×2048 suitable for commercial content, design review, and downstream creative pipelines.
- No cold start: Built for responsive production usage with stable latency and faster turnaround.
🛠️ Technical Specifications
| Item | Details |
|---|---|
| Model architecture | Professional image editing model |
| Task type | Image editing (image-to-image) |
| Input format | Prompt + reference images |
| Prompt | Chinese and English supported |
| Prompt rewriting | Automatic prompt optimization (enabled by default) |
| Image input | 1-3 images; order defines image 1/2/3 in the prompt |
| Image formats | JPG, JPEG, PNG, BMP, TIFF, WEBP, GIF |
| Per-image requirement | 384-2048 px per side recommended, up to 10MB each |
| Output Format | Image, 1-6 per request |
| Output resolution | 512512 to 20482048, specified as width*height (e.g. 1024*1024, 1280*720); auto-selected by the model when unspecified |
| Seed | Optional; 0-2147483647 for reproducibility, random when unspecified |
| Latency | Optimized for fast inference with no cold start |
| Supported languages | Chinese, English |
Sample Prompts
- Keep the character pose and composition unchanged, replace the background with a modern minimalist living room, and improve lighting realism and fine details.
- Keep the product shape unchanged, replace the background with a premium studio setup, add soft reflections and clean commercial lighting.
- Transform this illustration into a cinematic style, enhance volumetric lighting and color depth, while preserving facial identity consistency.
💰 Pricing
| Item | Price |
|---|---|
| 1K resolutions (e.g. 1024×1024, 1280×720, 768×1152) | $0.04 / image |
| 2K resolutions (e.g. 1536×1536, 1920×1080, 1080×1920) | $0.075 / image |
| Unspecified size (smart resolution) | Billed at the 2K rate ($0.075 / image) |
| Input reference images | $0.003 / image |
Total = applicable resolution price × generated images (n) + $0.003 × input reference images. Unspecified size uses the 2K rate.
💡 Best Use Cases
- E-commerce image enhancement: Replace backgrounds, unify lighting, and improve product presentation for listings and ads.
- Marketing and social media creative: Generate polished visual variants for campaigns, brand content, and paid media.
- Design iteration and concept exploration: Rapidly revise existing visuals, mockups, or references to accelerate creative decision-making.
- Consistency-focused editing workflows: Maintain character, apparel, or brand consistency across multiple assets using reference images.
🔗 Related Models
- Qwen Image 3.0 Pro Text to Image: Better suited for high-quality image generation workflows.
- Qwen Image 3.0 Pro Edit: Focused on professional reference-based image editing and refinement.
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-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.
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.