Skip to content
Pruna AI logo

P-Video

Text-to-VideoPruna AI

Pruna's P-Video is a premium video generation model supporting text-to-video, image-to-video, and audio-conditioned generation up to 1080p at 24 or 48 fps, with configurable duration up to 20 seconds.

Model Info
More informationlink
PricingView pricing in the Cloudflare dashboard

Usage

TypeScript
const response = await env.AI.run(
'pruna/p-video',
{
prompt: 'A sports car drifting through a neon-lit city at night, cinematic aerial shot',
duration: 5,
resolution: '720p',
aspect_ratio: '16:9',
draft: true,
},
)
console.log(response)

Parameters

prompt
stringrequiredText prompt for video generation.
image
stringInput image to generate video from (image-to-video). HTTP(S) URL or data URI. Supports jpg, jpeg, png, webp. When provided, aspect_ratio is ignored.
audio
stringInput audio to condition video generation. HTTP(S) URL or data URI. Supports flac, mp3, wav. When provided, duration is ignored.
duration
integerrequireddefault: 5minimum: 1maximum: 20Duration of the video in seconds (1-20). Ignored when audio is provided.
resolution
stringrequireddefault: 720penum: 720p, 1080pVideo resolution.
aspect_ratio
stringrequireddefault: 16:9enum: 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 1:1Aspect ratio of the video. Ignored when an input image is provided.
seed
integerminimum: -9007199254740991maximum: 9007199254740991Random seed for reproducible generation.
draft
booleanrequireddefault: falseDraft mode. Generates a lower-quality preview of the video.
save_audio
booleanrequireddefault: trueSave the video with audio.
last_frame_image
stringReference image for the last frame of the video. HTTP(S) URL or data URI.
prompt_upsampling
booleanrequireddefault: trueUse prompt upsampling to enhance the prompt.
disable_safety_filter
booleanrequireddefault: trueDisable safety filter for prompts and input images.

API Schemas (Raw)

Input
Output