POST
/
v3
/
async
/
pixverse-v4.5-i2v
PixVerse V4.5 Image to Video
curl --request POST \
  --url https://api.novita.ai/v3/async/pixverse-v4.5-i2v \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '{
  "prompt": "<string>",
  "image": "<string>",
  "resolution": "<string>",
  "negative_prompt": "<string>",
  "fast_mode": true,
  "style": "<string>",
  "seed": 123
}'
{
  "task_id": "<string>"
}
Generate high-quality videos from text descriptions and image using PixVerse’s latest v4.5 model. Supports multiple resolutions, aspect ratios, and motion modes for versatile video creation.
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.

​
Request Headers

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

​
Request Body

​
prompt
string
required
Text prompt for video generation.
  • Maximum length: 2048 characters
  • Clear description of desired scene and motion
​
image
string
required
First frame of the video.
  • Supported image formats include .jpg/.jpeg/.png
  • The image file size cannot exceed 10MB
  • The image resolution should not be less than 300*300px
  • The aspect ratio of the image should be between 1:2.5 ~ 2.5:1
​
resolution
string
Video quality. Default: 540p
Accepted values:
  • fast_mode is false: 360p, 540p, 720p, 1080p
  • fast_mode is true: 360p, 540p, 720p
​
negative_prompt
string
Negative prompt for generation.
  • Maximum length: 2048 characters
​
fast_mode
boolean
Whether to enable fast mode, which will generate videos more quickly but may reduce quality and lower the price.Default: false.
​
style
string
Style preset (v3.5 only).
Accepted values: anime, 3d_animation, clay, comic, cyberpunk
​
seed
integer
The random seed to use for the generation.

​
Response

​
task_id
string
required
Use the task_id to request the Task Result API to retrieve the generated outputs.