# Qwen Image 3.0

> Generate and edit legible text-in-image posters, infographics, and UI mockups in 12 languages at up to 2K.


## Overview

- **Endpoint**: `https://api.segmind.com/v1/qwen-image-3`
- **Model ID**: `qwen-image-3`
- **Category**: Text-to-Image Generation
- **Type**: Synchronous (Direct response)

- **Average Cost**: $0.04900000000000001


## Pricing

- **Cost**: $0.049 per generation

## API Information

This model uses a **synchronous response pattern**:
1. Make a POST request with your parameters
2. Receive the output directly in the response (binary for images/videos/audio, JSON for text)
3. No polling required - response is immediate


### Input Schema

The API accepts the following input parameters:

- **`prompt`** (`string`, _required_):
  Prompt
  Describe the image to generate, or the edit to apply to the reference image(s).

- **`image`** (`File (URL)`, _optional_):
  Reference Image
  Optional. Supply an image to edit it instead of generating from scratch.

- **`image2`** (`File (URL)`, _optional_):
  Reference Image 2
  Optional second reference image.

- **`image3`** (`File (URL)`, _optional_):
  Reference Image 3
  Optional third reference image. Up to 3 references are supported.

- **`size`** (`string`, _optional_):
  Size
  Output resolution. Editing supports up to 1440 x 1440; 2048 x 2048 is text-to-image only.
  - Default: `"1024*1024"`
  - Options: "1024*1024" (1024 x 1024 (square)), "1328*1328" (1328 x 1328 (square, large)), "768*1024" (768 x 1024 (portrait 3:4)), "1024*768" (1024 x 768 (landscape 4:3)), "1080*1440" (1080 x 1440 (portrait 3:4, large)), "1440*1080" (1440 x 1080 (landscape 4:3, large)), "2048*2048" (2048 x 2048 (text-to-image only))

- **`negative_prompt`** (`string`, _optional_):
  Negative Prompt
  Elements to exclude from the image.

- **`prompt_extend`** (`boolean`, _optional_):
  Prompt Extend
  Let the model automatically rewrite and enrich short prompts.
  - Default: `true`

- **`prompt_extend_mode`** (`string`, _optional_):
  Prompt Extend Mode
  How the prompt is rewritten when Prompt Extend is on.
  - Default: `"direct"`
  - Options: "direct" (Direct - light touch-up), "agent" (Agent - fuller rewrite)

- **`seed`** (`integer`, _optional_):
  Seed
  Seed for reproducible results.
  - Range: 0 to 2147483647

- **`watermark`** (`boolean`, _optional_):
  Watermark
  Add the Qwen watermark to the output.
  - Default: `false`


**Required Parameters Example**:

```json
{
  "prompt": "A cozy independent bookstore cafe on a rainy autumn evening, warm golden light glowing through the large front windows onto a wet cobblestone street, a hand-painted wooden sign above the entrance that reads \"Qwen Books & Coffee\", reflections shimmering in the puddles, a person under a red umbrella walking past, cinematic photorealistic detail, shallow depth of field, 35mm"
}
```


**Full Example**:

```json
{
  "prompt": "A cozy independent bookstore cafe on a rainy autumn evening, warm golden light glowing through the large front windows onto a wet cobblestone street, a hand-painted wooden sign above the entrance that reads \"Qwen Books & Coffee\", reflections shimmering in the puddles, a person under a red umbrella walking past, cinematic photorealistic detail, shallow depth of field, 35mm",
  "size": "1328*1328",
  "negative_prompt": "blurry, watermark, low quality, distorted text, deformed, extra limbs, jpeg artifacts",
  "prompt_extend": true,
  "prompt_extend_mode": "direct",
  "seed": 12345,
  "watermark": false
}
```


### Output Schema

The API returns a synchronous response based on the model type:

**For Image/Video/Audio Models**:
- Response contains binary data (image/png, video/mp4, audio/mp3)
- Content-Type header indicates the media type
- Save the response body directly to a file

**For Text Models**:
- Response is JSON with the generated text
- Structure varies by model

**HTTP Response Codes**:
- **200 - OK**: Request successful, output in response body
- **400 - Bad Request**: Invalid parameters
- **401 - Unauthorized**: Invalid or missing API key
- **404 - Not Found**: Model not found
- **406 - Not Acceptable**: Insufficient credits
- **429 - Too Many Requests**: Rate limit exceeded
- **500 - Server Error**: Internal server error


## Usage Examples

### cURL

```bash
curl -X POST "https://api.segmind.com/v1/qwen-image-3" \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "prompt": "A cozy independent bookstore cafe on a rainy autumn evening, warm golden light glowing through the large front windows onto a wet cobblestone street, a hand-painted wooden sign above the entrance that reads \"Qwen Books & Coffee\", reflections shimmering in the puddles, a person under a red umbrella walking past, cinematic photorealistic detail, shallow depth of field, 35mm",
  "size": "1328*1328",
  "negative_prompt": "blurry, watermark, low quality, distorted text, deformed, extra limbs, jpeg artifacts",
  "prompt_extend": true,
  "prompt_extend_mode": "direct",
  "seed": 12345,
  "watermark": false
}'
```

### Python

```python
import requests
import json

api_key = "YOUR_API_KEY"
url = "https://api.segmind.com/v1/qwen-image-3"

data = {
  "prompt": "A cozy independent bookstore cafe on a rainy autumn evening, warm golden light glowing through the large front windows onto a wet cobblestone street, a hand-painted wooden sign above the entrance that reads \"Qwen Books & Coffee\", reflections shimmering in the puddles, a person under a red umbrella walking past, cinematic photorealistic detail, shallow depth of field, 35mm",
  "size": "1328*1328",
  "negative_prompt": "blurry, watermark, low quality, distorted text, deformed, extra limbs, jpeg artifacts",
  "prompt_extend": true,
  "prompt_extend_mode": "direct",
  "seed": 12345,
  "watermark": false
}

response = requests.post(
    url,
    json=data,
    headers={
        'x-api-key': api_key,
        'Content-Type': 'application/json'
    }
)

if response.status_code == 200:
    # For image/video/audio models, response.content contains the binary data
    with open('output.png', 'wb') as f:
        f.write(response.content)
    print('Generation complete, saved to output.png')
else:
    print(f"Error: {response.status_code}")
    print(response.text)
```

### JavaScript

```javascript
const apiKey = 'YOUR_API_KEY';
const url = 'https://api.segmind.com/v1/qwen-image-3';

const data = {
  "prompt": "A cozy independent bookstore cafe on a rainy autumn evening, warm golden light glowing through the large front windows onto a wet cobblestone street, a hand-painted wooden sign above the entrance that reads \"Qwen Books & Coffee\", reflections shimmering in the puddles, a person under a red umbrella walking past, cinematic photorealistic detail, shallow depth of field, 35mm",
  "size": "1328*1328",
  "negative_prompt": "blurry, watermark, low quality, distorted text, deformed, extra limbs, jpeg artifacts",
  "prompt_extend": true,
  "prompt_extend_mode": "direct",
  "seed": 12345,
  "watermark": false
};

const response = await fetch(url, {
  method: 'POST',
  headers: {
    'x-api-key': apiKey,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify(data),
});

if (response.ok) {
  // For image/video/audio models, response contains binary data
  const blob = await response.blob();
  const downloadUrl = URL.createObjectURL(blob);

  // Create download link
  const a = document.createElement('a');
  a.href = downloadUrl;
  a.download = 'output.png';
  a.click();

  console.log('Generation complete');
}
```


## Additional Resources

### Documentation

- [Model Playground](https://www.segmind.com/models/qwen-image-3)
- [API Documentation](https://www.segmind.com/models/qwen-image-3/api)
- [Pricing Details](https://www.segmind.com/models/qwen-image-3/pricing)
- [Platform Documentation](https://docs.segmind.com/)

### Tags

No tags available