Qwen Image Edit Plus

qwen_image_edit_plus

Qwen Image Edit Plus supports multi-image input and output. It can precisely edit text in images, add, remove, or move objects, change subject actions, transfer image styles, and enhance image details.

Эндпоинты

POST /v1/queue/qwen_image_edit_plus # Создать задачу

GET /v1/queue/qwen_image_edit_plus/requests/{request_id}/status # Проверить статус

GET /v1/queue/qwen_image_edit_plus/requests/{request_id}/response # Получить результат

PUT /v1/queue/qwen_image_edit_plus/requests/{request_id}/cancel # Отменить задачу

Параметры запроса

curl --location "https://odirouter.ai/model/v1/queue/qwen_image_edit_plus" \
  --header "Authorization: Bearer YOUR_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "prompt": "A red apple on a white table, clean studio lighting, simple background.",
    "images": [
      "https://example.com/reference-image.webp"
    ]
  }'

prompt string обязательно

Positive prompt describing the desired image content, style, and composition. Chinese and English are supported. The length must not exceed 800 tokens, and content beyond the limit is truncated automatically.

images string[] обязательно

Input image URL or Base64 encoded data list. Pass 1-3 images. For multi-image input, array order defines image order, and the output aspect ratio follows the last image.

Supported image formats: JPG, JPEG, PNG, BMP, TIFF, WEBP, GIF

Animated GIFs only process the first frame. Recommended image width and height are between 384 and 3072 pixels, and file size must not exceed 10MB.

negative_prompt string

Negative prompt describing content that should not appear in the image. Chinese and English are supported. The maximum length is 500 characters, and content beyond the limit is truncated automatically.

size string

Output image resolution in width*height format, for example 1024*1536. If omitted, the output image keeps an aspect ratio similar to the input image, or the last input image for multi-image input, with total pixels close to 1024*1024.

Range: width and height are both 512 - 2048 pixels. The specified value is adjusted to the nearest multiple of 16.

n int

Number of output images.

Range: 1 - 6

Default: 1

prompt_extend bool

Whether to enable intelligent prompt rewriting. When enabled, the model optimizes the positive prompt, which can noticeably improve simple prompts.

Default: true

watermark bool

Whether to add a Qwen-Image watermark in the lower-right corner of the image.

Default: false

seed int

Random seed used to improve reproducibility. Generation is probabilistic, so using the same seed does not guarantee identical results every time.

Range: 0 - 2147483647

Параметры ответа

{
  "request_id": "mmsu_01hxyz...",
  "response_url": "https://odirouter.ai/model/v1/queue/qwen_image_edit_plus/requests/mmsu_01hxyz.../response",
  "status_url": "https://odirouter.ai/model/v1/queue/qwen_image_edit_plus/requests/mmsu_01hxyz.../status",
  "cancel_url": "https://odirouter.ai/model/v1/queue/qwen_image_edit_plus/requests/mmsu_01hxyz.../cancel",
  "queue_position": 0
}

Поле	Тип	Описание
`request_id`	string	Идентификатор задачи, используемый во всех последующих операциях.
`response_url`	string	URL для получения итогового результата.
`status_url`	string	URL для проверки статуса задачи.
`cancel_url`	string	URL для отмены задачи.
`queue_position`	int	Текущая позиция в очереди.

Следующие операции