Wan 2.6 - Image to Video

wan26_i2v

Alibaba Wanx 2.6 Image to Video converts static images into dynamic video content.

Эндпоинты

POST /v1/queue/wan26_i2v # Создать задачу

GET /v1/queue/wan26_i2v/requests/{request_id}/status # Проверить статус

GET /v1/queue/wan26_i2v/requests/{request_id}/response # Получить результат

PUT /v1/queue/wan26_i2v/requests/{request_id}/cancel # Отменить задачу

Параметры запроса

curl --location "https://odirouter.ai/model/v1/queue/wan26_i2v" \
  --header "Authorization: Bearer YOUR_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "prompt": "A red apple slowly rotating on a white table, clean studio lighting, static camera.",
    "img_url": "https://example.com/input.webp",
    "duration": 3,
    "resolution": "720P",
    "prompt_extend": true,
    "watermark": false,
    "seed": 12345
  }'

prompt string обязательно

Text prompt describing expected elements, motion, and visual characteristics in the generated video. Chinese and English are supported, and content beyond the model limit is truncated automatically.

Maximum length: 1500 characters

negative_prompt string

Negative prompt describing content that should not appear in the generated video. Chinese and English are supported.

img_url string обязательно

First-frame image URL or Base64-encoded data.

Supported formats: JPEG, JPG, PNG, BMP, WEBP. PNG images do not support transparent channels.

Image width and height follow the official constraints.

Maximum file size: 10MB

audio_url string

Optional audio URL used to guide video generation when supported by the model workflow.

duration int

Generated video duration in seconds. This parameter affects cost.

Range: 3 - 30

Default: 5

resolution string

Video resolution tier. The model scales to a nearby total-pixel target and tries to match the input image aspect ratio.

Options: 720P, 1080P

Default: 1080P

shot_type string

Shot type used to control video narrative structure.

Options: single, multi

template string

Motion template used by supported image-to-video workflows.

prompt_extend bool

Whether to enable prompt rewriting. When enabled, a large model rewrites the input prompt, often improving short prompts but increasing latency.

Options: true, false

Default: true

seed int

Random seed. When omitted, the system generates a random seed automatically. A fixed seed can improve reproducibility, but identical results are not guaranteed.

Range: 0 - 2147483647

watermark bool

Whether to add a watermark in the lower-right corner of the video.

Options: false, true

Default: false

Параметры ответа

{
  "request_id": "mmsu_01hxyz...",
  "response_url": "https://odirouter.ai/model/v1/queue/wan26_i2v/requests/mmsu_01hxyz.../response",
  "status_url": "https://odirouter.ai/model/v1/queue/wan26_i2v/requests/mmsu_01hxyz.../status",
  "cancel_url": "https://odirouter.ai/model/v1/queue/wan26_i2v/requests/mmsu_01hxyz.../cancel",
  "queue_position": 0
}

Поле	Тип	Описание
`request_id`	string	Идентификатор задачи для последующей проверки статуса, получения результата и отмены
`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