Pruna P Video 2 Pro Replace

Swap the person in any video for the one in your photo, keeping the motion, camera and soundtrack, with lips that follow the original audio.

Coming Soon

Image To Video

Pruna P Video 2 Pro Replace is coming to Segmind

The playground and serverless API for this model aren't live yet. Here's what we know so far — launch details, pricing, and full API docs will appear on this page.

About

P Video 2 Pro Replace is Pruna AI's person-swap model on the P-Video-2-Pro line. Send a video and one or two photos, and get the same video back with the new person in it. Motion, camera and soundtrack are kept, and the lips follow the original audio.

What to expect

The new identity comes from the photo; expressions, pose and lip movement come from the source video.
Two people: one photo per person, matched left to right, or say who is who in the instruction.
Processing runs at roughly 10 seconds per second of video at 480p and 12 at 768p.

Specifications

Input: one video (mp4, mov or webm, 1 to 120 s) and 1 or 2 photos.
Output: MP4 at 24 fps, as long as the source, at 480p or 768p, aspect ratio kept.
Price: per second of returned video; 768p costs twice 480p.