P-Video
Pruna AI · AI videoP-Video is Pruna AI's performance video model built for speed and creative iteration. It supports text-to-video, image-to-video, and audio-conditioned generation in a single endpoint, with optional draft mode for faster previews and native audio generation when no custom track is supplied.
The model is strong at close-up subjects, product animation, and short-form social clips. Hosted APIs typically expose 720p and 1080p tiers, multi-aspect ratios, and clip lengths on the order of several seconds per generation.
On VidMachine, scene generation uses image-to-video at 720p via Replicate at 4 credits per second. For AI Influencer talking-head segments, use P-Video Avatar instead.
Key features and benefits
Image-to-video with optional audio
Animate a starting frame from a motion prompt. Attach soundtrack audio to condition timing; when audio is provided, output length follows the audio instead of a separate duration parameter.
Fast iteration
P-Video is tuned for quick turnaround on short clips. Provider draft mode can speed previews further; VidMachine always runs full-quality (non-draft) renders at 720p.
Product and character motion
Strong identity consistency from a still plate makes it a fit for product hero animation and social ads where the opening frame already defines the look.
Native or custom audio
Generate with built-in dialogue and sound, or import your own audio for music videos and voiceovers.
Technical specifications
ProviderPruna AI (P-Video)
Primary inputsText prompt; start image for image-to-video; optional last-frame image; optional audio (flac, mp3, wav)
Resolutions720p or 1080p (VidMachine: 720p only)
Aspect ratio16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 1:1 when no input image; with an image, framing follows the source
DurationTypically 1–10 seconds when no audio is set; with audio, length follows the track
Use cases and applications
Animate scene start frames into short motion clips for AI Video projects—camera moves, subtle ambience, and product or character motion from a strong still.
Iterate quickly on social ads and short-form creatives where turnaround and cost matter as much as polish.
Why this model
Choose P-Video when you want a fast, affordable Replicate-backed model for general scene motion in AI Video projects.
For lip-synced AI Influencer talking heads, use P-Video Avatar. Pair P-Video with higher-cost models in your priority list when you need a quality fallback.
How VidMachine uses it
VidMachine generates scene clips via image-to-video at 720p (24 fps, full quality—not draft mode) using each scene's starting frame and motion prompt. Optional last-frame conditioning is passed when available. Duration is clamped to 1–10 seconds for standard AI Video scenes.
Generation runs on Replicate (prunaai/p-video). Billing is 4 credits per second of output video at 720p.
What you should know
What resolution does VidMachine use?
Always 720p. The Replicate API also supports 1080p, but VidMachine locks resolution to 720p for consistent cost and pipeline behavior.
Can I use P-Video for AI Influencer projects?
No. Influencer talking-head segments use P-Video Avatar (p-video-avatar) on influencer_video_model_priority. P-Video remains available for AI Video scenes.
Does VidMachine use draft mode?
No. Scene generation always runs with draft disabled for production-quality output.
How is P-Video billed?
4 credits per second of generated scene video duration.