P Video Edit.

P Video Edit Overview

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

This entry transforms an existing video with a text instruction and optional image references.

P Video Edit from Pruna is available through each::labs in the P-video family. Required fields are video, prompt.

images: Optional reference image URLs for reference-guided edits. prompt_upsampling: Enhance the edit prompt before generation.

Use the P Video Edit API when you need this transformation or analysis as a repeatable step in an application or creative pipeline. The sections below distinguish the required material, adjustable controls and checks that matter before delivery.

Capabilities

• This entry transforms an existing video with a text instruction and optional image references.
• images: Optional reference image URLs for reference-guided edits.
• prompt_upsampling: Enhance the edit prompt before generation.
• draft: Draft mode generates a faster, lower-quality preview at lower cost.
• video: Source video to edit.

Use Cases for P Video Edit

P Video Edit is useful when this specific operation fits between source preparation and delivery. These scenarios show how it can support different parts of a working pipeline.

Creators

Revise a short product scene. Use a representative source or a concise brief, then inspect the result before preparing a larger set of assets.

Design and marketing teams

Restyle an existing clip. Compare the result with the intended message, composition and destination. Keep reviewable versions of the source and output.

Developers

Explore a reference-guided identity or appearance change. Inspect the actual returned value before connecting it to another step, and keep the chosen request settings with the result.

Start with a clear definition of the desired result and use the exposed controls to reach it. Keep any additional generation, editing or application logic in separate steps so that the effect of this operation remains easy to review.

Tips and Tricks

Describe one coherent shot before adding complex action. State the subject, movement, camera behavior and setting separately. For reference-guided requests, choose source images with clear subjects and compatible framing.

• prompt_upsampling: Enhance the edit prompt before generation.
• draft: Draft mode generates a faster, lower-quality preview at lower cost.

• Example direction: “Replace the background with a softly lit studio; keep the subject, colors and framing unchanged.”
• Example direction: “Make the lighting warmer while preserving the main subject and its visible details.”

Compare one deliberate adjustment at a time. Inspect the part of the result affected by that change, then check the rest of the asset or response for unwanted side effects before reusing the settings.

Technical Specifications

• Result type: video.
• Required fields: video, prompt.
• prompt: string.
• images: array or null.
• prompt_upsampling: boolean or null; default true.
• draft: boolean or null; default false.

video: Source video to edit.

Values must use the types and accepted options listed in the parameter reference. A displayed default does not remove a required-field requirement. Choose a supported output setting for this entry rather than borrowing a preset from a related model.

Things to Be Aware Of

Watch the entire clip rather than reviewing only a thumbnail. Check subject identity, object boundaries, motion continuity, camera changes and the ending; review the audio as well when the entry includes it.

Optional settings are not necessarily interchangeable with those on another entry in the same family. Use the accepted names, types and values shown for this operation.

For media-based inputs, supply a directly retrievable file URL rather than a page containing the asset. Keep the source available while processing. Check the final content in the destination player, editor or application, not only the request status.

Key Considerations

The source-video limit is 15 seconds, references are limited to four, and draft mode is a lower-quality preview rather than a final-quality guarantee.

Public estimate: $0.025–$0.045 per second.

Prepare video, prompt before starting. Optional settings include images, prompt_upsampling, draft. Keep these settings aligned with the intended delivery, especially when a later step expects a particular type or format.

Run a representative request before scaling to a larger collection. Judge the result against the source and the brief, and account for all generated outputs or usage-sensitive options when estimating a batch.

Limitations

• prompt: maximum characters: 4000.
• images: minimum items: 0; maximum items: 4; item string; item format: uri.

Unsupported parameters do not establish additional capabilities. A generated result can differ from the intended brief, so review detail and consistency before publication.