Vidu 2.0 - Image to Video

vidu2.0-img2video

Vidu 2.0 I2V offers enhanced image-to-video generation with improved motion quality, better detail preservation, and extended duration support.

Endpoints

POST /v1/queue/vidu2.0-img2video # Create task

GET /v1/queue/vidu2.0-img2video/requests/{request_id}/status # Check status

GET /v1/queue/vidu2.0-img2video/requests/{request_id}/response # Get result

PUT /v1/queue/vidu2.0-img2video/requests/{request_id}/cancel # Cancel task

Request parameters

curl --request 'POST' 'https://odirouter.ai/model/v1/queue/vidu2.0-img2video' \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --location \
  --data-raw '{
  "images": [
    "https://www.gstatic.com/webp/gallery/1.jpg"
  ],
  "prompt": "A cat slowly turns its head and blinks",
  "duration": 4,
  "resolution": "720p",
  "off_peak": false
}'

images array required

The image that will be used as the starting frame for the generated video.

Format Requirements:

Only accepts 1 image

Supports public URL or Base64 format

Supported formats: png, jpeg, jpg, webp

The aspect ratio of the image must be less than 1:4 or 4:1

All image sizes are limited to 50MB

HTTP request POST body must not exceed 20MB and must include the appropriate content type string. Example: data:image/png;base64,{base64_encode}

prompt string

Text description for video generation, maximum 2000 characters

Note: If the is_rec parameter is used in the recommended prompt, the model will ignore the manually entered prompt content for this parameter

duration integer

Video duration in seconds

Options: 4, 8

Default: 4

resolution string

Resolution based on model and duration.

vidu2.0 (4 seconds): optional settings 360p, 720p, 1080p

vidu2.0 (8 seconds): fixed at 720p

Default: 360p (for 4 seconds), 720p (for 8 seconds)

seed integer

Random seed. Default value is a random seed number. Manually set values will override the default random seed

Default: 0

movement_amplitude string

Movement amplitude of objects in the scene

Options: auto, small, medium, large

Default: auto

payload string

Pass-through parameter. No processing required, only data transmission, maximum transmission length is 1048576 characters

audio boolean

Whether to use direct audio-video output capability. When true, outputs video with dialogue and background sound; when false, outputs silent video

The voice_id parameter only takes effect when this parameter is true, and off-peak mode is not supported when this parameter is true

Options: true, false

Default: false

voice_id string

Voice ID to determine the voice timbre in the video

When empty, the system will automatically recommend. Refer to the list for available options

is_rec boolean

Whether to use recommended prompts. When true, the system automatically recommends prompts and generates videos using the prompt content, with the number of recommended prompts equal to 1; when false, generates video based on the input prompt

Enabling recommended prompts will consume additional points for each task

Options: true, false

bgm boolean

Whether to add background music to the generated video. When true, the system will automatically select and add suitable music from the preset BGM library; when not provided or false, no BGM will be added

BGM duration is unlimited, the system automatically adapts to the video duration

Options: true, false

Default: false

watermark boolean

Whether to add watermark. When true, adds watermark; when false, does not add watermark

Currently the watermark content is fixed, generated by AI, not added by default

Options: true, false

wm_position integer

Watermark position, indicating where the watermark appears in the image. 1 for top left, 2 for top right, 3 for bottom right, 4 for bottom left

Options: 1, 2, 3, 4

Default: 3

wm_url string

Watermark content, image URL here

When not provided, the default watermark is used: content generated by AI

callback_url string

Callback URL

off_peak boolean

Note: Temporarily unavailable

Off-peak mode. Off-peak mode consumes fewer points, please refer to detailed pricing information. Tasks submitted during off-peak hours will be generated within 48 hours. Unfinished tasks will be automatically cancelled and their points refunded. We also support canceling off-peak tasks. Except for q3, other direct audio-video generation functions do not support off-peak mode.

Options: true, false

Default: false

Response parameters

{
  "request_id": "task_01hxyz...",
  "response_url": "https://odirouter.ai/model/v1/queue/vidu2.0-img2video/requests/task_01hxyz.../response",
  "status_url": "https://odirouter.ai/model/v1/queue/vidu2.0-img2video/requests/task_01hxyz.../status",
  "cancel_url": "https://odirouter.ai/model/v1/queue/vidu2.0-img2video/requests/task_01hxyz.../cancel",
  "queue_position": 0
}

Field	Type	Description
`request_id`	string	Task ID used for all follow-up operations.
`response_url`	string	URL to fetch the final result.
`status_url`	string	URL to query task status.
`cancel_url`	string	URL to cancel the task.
`queue_position`	int	Current queue position.

Follow-up operations

Check status

Get result

Cancel task

Error handling