Skip to main content
POST
/
v3
/
async
/
seedance-v1-pro-i2v
Seedance V1 Pro Image to Video
curl --request POST \
  --url https://api.novita.ai/v3/async/seedance-v1-pro-i2v \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "prompt": "<string>",
  "image": "<string>",
  "last_image": "<string>",
  "resolution": "<string>",
  "aspect_ratio": "<string>",
  "camera_fixed": true,
  "seed": 123,
  "duration": 123
}
'
{
  "task_id": "<string>"
}

Documentation Index

Fetch the complete documentation index at: https://novita.ai/docs/llms.txt

Use this file to discover all available pages before exploring further.

Seedance V1 Pro is an AI video model designed for coherent multi-shot video generation, offering smooth motion and precise adherence to detailed prompts. It supports resolutions of 480p, 720p, and 1080p.
This is an asynchronous API; only the task_id will be returned. You should use the task_id to request the Task Result API to retrieve the video generation results.

ā€‹
Request Headers

ā€‹
Content-Type
string
required
Supports: application/json
ā€‹
Authorization
string
required
Bearer authentication format, for example: Bearer {{API Key}}.

ā€‹
Request Body

ā€‹
prompt
string
Text prompt for video generation; Positive text prompt; Cannot exceed 2000 characters.
ā€‹
image
string
required
Input image supports both URL and Base64 format.
  • Supported image formats include jpeg, png, webp, bmp, tiff, gif.
  • The image file size cannot exceed 30MB.
  • Its shorter side must be greater than 300 pixels, and its longer side must be less than 6,000 pixels.
  • Its aspect ratio must be in the range of 0.4 to 2.5.
ā€‹
last_image
string
End image, supports both URL and Base64 format.
  • Supported image formats include jpeg, png, webp, bmp, tiff, gif.
  • The image file size cannot exceed 30MB.
  • Its shorter side must be greater than 300 pixels, and its longer side must be less than 6,000 pixels.
  • Its aspect ratio must be in the range of 0.4 to 2.5.
The first and last frame images provided can be the same. If the aspect ratios of the first and last frame images differ, the first frame image will be used as the reference, and the last frame image will be automatically cropped to match.
ā€‹
resolution
string
required
Video quality. Accepted values: 480p, 720p, 1080p
ā€‹
aspect_ratio
string
default:"16:9"
The aspect ratio of the generated video. Accepted values: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16
ā€‹
camera_fixed
boolean
default:false
Determines if the camera position should remain fixed.
ā€‹
seed
integer
The random seed to use for the generation. -1 means a random seed will be used.
ā€‹
duration
integer
default:5
Specifies the length of the generated video in seconds. Available options: 5, 10

ā€‹
Response

ā€‹
task_id
string
required
Use the task_id to request the Task Result API to retrieve the generated outputs.