Skip to content

Qwen Image Format (Image)

Official Documentation

Alibaba Cloud Models Usage (Image and Video Generation)

📝 Introduction

Given a text prompt, the model will generate new images. Qwen/Alibaba Cloud provides powerful image generation and editing models that can create images based on natural language descriptions or edit existing images.

🤖 Supported Models

Currently supported models include:

Model Description
qwen-image-plus Qwen image generation model that supports generating high-quality images based on text prompts
wan2.5-t2i-preview Wan 2.5 text-to-image preview model
qwen-image-edit-plus Qwen image editing model that supports editing images based on input images and text prompts
qwen-image-edit Qwen image editing model
wan2.5-i2i-preview Wan 2.5 image-to-image preview model

💡 Request Examples

Create Image ✅

# Basic image generation
curl "https://computevault.unodetech.xyz/v1/images/generations" \
  -H 'Content-Type: application/json' \
  -H "Authorization: Bearer $API_KEY" \
  -X POST \
  -d '{
    "model": "qwen-image-plus",
    "prompt": "Give me an image of a cat",
    "n": 1,
    "size": "1328*1328"
  }'

Response Example:

{
  "created": 1234567890,
  "data": [
    {
      "url": "https://example.com/image.png",
      "b64_json": "..."
    }
  ]
}

Edit Image ✅

# Image editing (using multipart form)
curl -X POST "https://computevault.unodetech.xyz/v1/images/edits" \
  -H "Authorization: Bearer $API_KEY" \
  -F "image=@hand-statue.png" \
  -F "model=qwen-image-edit" \
  -F "prompt=The broken remains of the hand-shaped statue, with all parts above the wrist missing. These broken pieces are jutting out of the water surrounding the statue."

Response Example:

{
  "created": 1234567890,
  "data": [
    {
      "url": "https://example.com/edited-image.png",
      "b64_json": "..."
    }
  ]
}

📮 Request

Endpoint

Create Image

POST /v1/images/generations

Create an image based on a text prompt. Supports qwen-image-plus and wan2.5-t2i-preview models.

Edit Image

POST /v1/images/edits

Edit or generate new images based on input images and text prompts. Supports qwen-image-edit-plus, qwen-image-edit, and wan2.5-i2i-preview models. Image data is provided via multipart form request.

Authentication Method

Include the API key in the request header:

Authorization: Bearer $API_KEY

Where $API_KEY is your API key.

Request Body Parameters

Text-to-Image Generation (/v1/images/generations)

Parameter Type Required Description
model string Yes Model name, e.g., "qwen-image-plus" or "wan2.5-t2i-preview"
prompt string Yes Text description of the desired image
n integer No Number of images to generate, fixed at 1
size string No The resolution of the output image, in the format of width*height. The default resolution is 1328*1328. Available options and their corresponding aspect ratios:
- "1664*928" (16:9)
- "1472*1140" (4:3)
- "1328*1328" (1:1, default)
- "1140*1472" (3:4)
- "928*1664" (9:16)
response_format string No Response format, "url" or "b64_json"
prompt
  • Type: String
  • Required: Yes
  • Description: Text description of the desired image.
  • Tips:
  • Use specific and detailed descriptions
  • Include key visual elements
  • Specify the desired artistic style
  • Describe composition and perspective

Image Editing (/v1/images/edits)

Image editing uses multipart form request format.

Parameter Type Required Description
model string Yes Model name, e.g., "qwen-image-edit-plus", "qwen-image-edit", or "wan2.5-i2i-preview"
image file Yes Input image file to be edited
prompt string Yes Text prompt describing how to modify the input image
image
  • Type: File (multipart form)
  • Required: Yes
  • Description: Input image file to be edited.
prompt
  • Type: String
  • Required: Yes
  • Description: Text prompt describing how you want to modify the input image.
  • Tips:
  • Clearly describe elements to add, remove, or replace
  • Use specific and detailed descriptions
  • Describe the desired modification effect

📥 Response

Success Response

Text-to-Image Generation Response

{
  "created": 1234567890,
  "data": [
    {
      "url": "https://example.com/image.png",
      "b64_json": "..."
    }
  ]
}

Response Field Descriptions:

Field Type Description
created integer Creation timestamp
data array Array of generated images
data[].url string Image URL (if response_format is "url")
data[].b64_json string Base64-encoded image data (if response_format is "b64_json")

Image Editing Response

{
  "created": 1234567890,
  "data": [
    {
      "url": "https://example.com/edited-image.png",
      "b64_json": "..."
    }
  ]
}

The response format is the same as text-to-image generation.

Error Response

If the request fails, an error response will be returned:

{
  "error": {
    "message": "Error description",
    "type": "invalid_request_error",
    "code": "error_code"
  }
}

🌟 Best Practices

Prompt Writing Suggestions

  1. Use clear and specific descriptions
  2. Specify important visual details
  3. Describe the desired artistic style and atmosphere
  4. Pay attention to composition and perspective descriptions
  5. Can include details such as color, lighting, mood, etc.

Parameter Selection Suggestions

  1. Model Selection

    • qwen-image-plus: Qwen image generation model, suitable for quickly generating high-quality images
    • wan2.5-t2i-preview: Wan 2.5 text-to-image preview model
    • qwen-image-edit-plus: Qwen image editing model that supports editing images based on input images and text prompts
    • qwen-image-edit: Qwen image editing model
    • wan2.5-i2i-preview: Wan 2.5 image-to-image preview model

  2. Prompt Optimization

    • Use detailed and descriptive text
    • Include specific visual elements and style requirements
    • Avoid vague or overly brief descriptions
    • When editing images, clearly describe how you want to modify the input image (add, remove, replace elements, etc.)

  3. Image Editing Notes

    • Ensure the input image format is correct
    • Use multipart form format to upload images
    • Provide clear editing instructions

Common Issues

  1. Image Generation Failure

    • Check if the prompt complies with content policies
    • Verify API key permissions
    • Confirm the request format is correct
    • Check if the model name is correct

  2. Results Don't Match Expectations

    • Optimize prompt descriptions to be more specific and detailed
    • Add more visual details and style descriptions
    • Try different description approaches

  3. Image Editing Failure

    • Confirm the image file format is correct
    • Check if multipart form format is used
    • Verify the prompt clearly describes the editing requirements