Pruna AI · Clips · standard
P-Video Animate
Takes a still and a driving video, and moves the still the way the video moves.
What it costs
| 5s · 720p | 12.5 credits |
| 5s · 1080p | 25 credits |
What it takes
| Aspect ratios | 16:9 4:3 1:1 3:4 9:16 21:9 |
| Resolutions | 720p 1080p |
| Duration | 1–15 seconds |
| Reference images | 1 |
| Reference videos | 1 |
| Audio | Always generated |
| Required inputs | image, video |
When to reach for it
Motion transfer: you supply an image and a video, and the subject in the image performs the motion in the video. It is the tool for putting a character you have designed into a movement you have already captured or found, without needing the model to invent either.
Both inputs are required, and the duration follows the driving video up to fifteen seconds rather than being chosen. Audio is always generated. Seven aspect ratios and a choice of 720p or 1080p.
The quality of the result depends far more on the driving video than on the prompt. A clean, well-lit, single-subject clip with unambiguous motion transfers well, and a busy handheld one does not. That is worth knowing before blaming the model. Its siblings split the neighbouring jobs: Avatar drives a still from audio rather than video, and Replace swaps a subject inside existing footage rather than animating a new one.
Guides that cover it
- P-Video: the complete guide to Pruna's four models
Four models, one family: a cheap generator and three performance rigs. What each one takes, what a take really costs, and the failures worth knowing first.
P-Video Animate is one pick in the composer.
Every model in this catalog runs from the same prompt bar, priced in the same credits. New accounts start with some to spend.
Start picturing