All models

P-Video

pruna/p-video
Pruna Video GenerationText-to-VideoImage-to-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

Input
aspect_ratio string required

Aspect ratio of the video. Ignored when an input image is provided.

audio string

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 boolean required

Disable safety filter for prompts and input images.

draft boolean required

Draft mode. Generates a lower-quality preview of the video.

duration integer required

Duration of the video in seconds (1-20). Ignored when audio is provided.

fps number required

Frames per second: 24 or 48.

image string

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.

last_frame_image string

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.

prompt string required

Text prompt for video generation.

prompt_upsampling boolean required

Use prompt upsampling to enhance the prompt.

resolution string required

Video resolution.

save_audio boolean required

Save the video with audio.

seed integer

Random seed for reproducible generation.

Output
video: model output URL