You're looking at a specific version of this model. Jump to the model overview.

prunaai /p-video-avatar:863ac422

Input schema

The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.

Field Type Default value Description
image
string
Input image (first frame). Supports jpg, jpeg, png, webp.
resolution
None
720p
Resolution of the video.
audio
string
Optional uploaded audio to condition video generation. If both audio and script are provided, uploaded audio is used.
voice
None
Zephyr (Female)
Voice for generated speech.
voice_script
string
Script for the person to say when no audio is uploaded.
voice_prompt
string
Say the following.
Optional speaking style, tone, pacing, emotion.
voice_language
None
English (US)
Output language.
seed
integer
Random seed. Set for reproducible generation.
video_prompt
string
The person is talking.
Optional prompt for the video.
disable_safety_filter
boolean
True
Disable safety filter for prompts and input image. When disabled, prompts are not checked for unsafe content before generation.
disable_prompt_upsampling
boolean
False
When true, skip the OpenRouter multimodal prompt upsampler and pass the raw user prompt to the video model.
no_op
boolean
False
Health check mode - returns status without inference.

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{'format': 'uri', 'title': 'Output', 'type': 'string'}