Skip to main content
POST
/
v3
/
async
/
pixverse-v6-i2v
PixVerse V6 Image-to-Video
curl --request POST \
  --url https://api.highwayapi.ai/v3/async/pixverse-v6-i2v \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "seed": 123,
  "image": "<string>",
  "prompt": "<string>",
  "duration": 123,
  "cfg_scale": 123,
  "resolution": "<string>",
  "thinking_type": "<string>",
  "negative_prompt": "<string>",
  "generate_audio_switch": true
}
'
{
  "task_id": "<string>"
}
PixVerse V6 image-to-video model. It supports converting static images into dynamic videos, with support for multiple resolutions and audio generation.
This is an asynchronous API and only returns the asynchronous task’s task_id. You should use this task_id to request the Get Task Result API to retrieve the generated result.

​
Request Headers

​
Content-Type
string
required
Enum value: application/json
​
Authorization
string
required
Bearer authentication format: Bearer {{API key}}.

​
Request Body

​
seed
integer
Random seed, used to reproduce generation results.
​
image
string
required
Input image URL; supports .jpg, .jpeg, and .png formats. The image file size must not exceed 10 MB; both width and height must be >= 300 px; the aspect ratio must be between 1:2.5 and 2.5:1.
​
prompt
string
required
Positive prompt text for generating the video; must not exceed 2500 characters.Length limit: 0 - 2500
​
duration
integer
default:5
Duration of the generated video (seconds), range 1-15.Value range: [1, 15]
​
cfg_scale
number
Guidance strength, controlling how closely the video generation follows the prompt. Lower values produce more natural motion, while higher values follow the prompt more closely.Value range: [0, 1]
​
resolution
string
default:"720p"
Output video resolution.Available values: 360p, 540p, 720p, 1080p
​
thinking_type
string
default:"auto"
Inference mode, controlling the thinking approach during generation.
​
negative_prompt
string
Negative prompt, describing elements to avoid; length must not exceed 2500 characters.Length limit: 0 - 2500
​
generate_audio_switch
boolean
default:false
Whether to generate audio at the same time when generating the video.

​
Response

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