P-Video
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.
Quick start
# Inspect the price — a plain request returns the 402 challenge:
curl -i https://api.glianalabs.com/v1/infer \
-H "content-type: application/json" \
-d '{
"model": "pruna/p-video",
"audio": <string>,
"image": <string>,
"prompt": <string>
}'
# Pay + run in one step with the mppx CLI (create a wallet: npx mppx account create):
npx mppx https://api.glianalabs.com/v1/infer \
-J '{"model": "pruna/p-video", "audio": "<string>", "image": "<string>", "prompt": "<string>"}'Examples
Parameters
Aspect ratio of the video. Ignored when an input image is provided.
Input audio to condition video generation. HTTP(S) URL or data URI. Supports flac, mp3, wav. When provided, duration is ignored. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
Disable safety filter for prompts and input images.
Draft mode. Generates a lower-quality preview of the video.
Duration of the video in seconds (1-20). Ignored when audio is provided.
Frames per second: 24 or 48.
Input 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. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
Reference image for the last frame of the video. HTTP(S) URL or data URI. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
Text prompt for video generation.
Use prompt upsampling to enhance the prompt.
Video resolution.
Save the video with audio.
Random seed for reproducible generation.