P-Video-Edit

Video·P-video·by Pruna AI

P-Video-Edit transforms source videos with prompt-guided edits, preserving motion and structure with optional reference images for style or identity.

Runtime (p50)
1m
Estimated price
$0.025–$0.045 per second, depending on draft
Call the API
prediction.sh
sh
curl -X POST \
  -H "Authorization: Bearer $EACHLABS_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
    "model": "p-video-edit",
    "version": "0.0.1",
    "input": {
        "draft": true,
        "video": "https://cdn-us.eachlabs.ai/defaults/fa53c3dfd83f4dea9ecbd5573e507f5a.mp4",
        "prompt": "Change only the SUV body paint to deep metallic red. Preserve the vehicle geometry, glass, trim, headlights, tires, reflections and shadows. Keep the environment, lighting and camera movement unchanged.",
        "save_audio": true,
        "prompt_upsampling": true
    },
    "webhook_url": ""
}' \
  https://api.eachlabs.ai/v1/prediction/

Related models

4 models
* FAQ

About P-Video-Edit

01 / 03

What is P-Video-Edit video editing?

P-Video-Edit video editing turns an existing clip into a newly edited video from a text instruction. Pruna's model is designed for short source videos where the original motion and structure should stay recognizable while the visual change follows the prompt.