Video Generation

P-Video Edit API

Pruna P-Video Edit: prompted edits on a clip up to 15 seconds, with up to 4 reference images. Keeps the original audio; draft mode for quick previews. Integrate this model via REST with endpoint docs, parameters, and code examples.

Prompting guide Compare video models Use cases

Img2Vid

Audio

Credit Cost

2 credits/sec

Type

Video

Get API Key

Create auth keys for apps and agents

See Usage

Track requests, credits, and logs

Buy Credits

Top up prepaid API capacity

API Endpoint

POST

/api/v1/models/p-video-edit/run

Test This Model

Run a real request through the API pipeline and inspect the exact input and output your integration will handle. Uses your credits like any API call; failed runs are refunded automatically.

LLM.txt

AI-Ready

For AI assistants

Copy this model's documentation into Claude, GPT, or any AI for instant integration help.

/llm/p-video-edit.txt

OpenAPI Spec

Swagger compatible

Import into Postman, Swagger UI, or generate client SDKs in any language.

/api/openapi

Parameters

Input parameters accepted by this model

Parameter	Type	Description	Default
`video` required	url	Clip to edit. Maximum 15 seconds. The output keeps the same duration.	-
`prompt` required	string	What to change in the clip, in plain language.	-
`video_duration` required	integer	Duration of the source clip in whole seconds. Used for credit calculation and refund accounting. min: 1 \| max: 15	-
`images`	array	Up to 4 reference image URLs to guide the edit (subject, style, or object references).	-
`prompt_upsampling`	boolean	Let the model expand your prompt with extra detail before generating.	`true`
`draft`	boolean	Faster, cheaper preview pass. 1 credit/second instead of 2.	`false`
`save_audio`	boolean	Preserve the source clip's audio in the output. Turn off for a silent clip.	`true`
`seed`	integer	Optional integer seed for reproducible output.	-

Use saved characters (@Name)

Write @Name in the prompt to use a character, product, outfit, location, prop or style saved in the account's Character Studio, for example "@Mara on a beach at sunset". Its photos are added to images automatically, after any images you send yourself, so your own image numbering is unchanged. List saved names with GET /api/v1/characters and save new ones with POST /api/v1/characters. An @word that names nothing saved stays plain text.

Code Examples

Edit a clip with a reference image: copy and paste to get started

bash

curl -X POST "https://pixeldojo.ai/api/v1/models/p-video-edit/run" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "video": "https://example.com/clip.mp4",
    "prompt": "Give the character a red leather jacket",
    "video_duration": 5,
    "images": [
      "https://example.com/jacket.jpg"
    ]
  }'

Response Format

Submit Response (202 Accepted)

json

{
  "jobId": "job_abc123...",
  "status": "pending",
  "statusUrl": "https://pixeldojo.ai/api/v1/jobs/job_abc123...",
  "creditCost": 10,
  "creditsRemaining": 95,
  "expiresAt": "2026-11-16T17:22:20Z"
}

Completed Response

json

{
  "jobId": "job_abc123...",
  "status": "completed",
  "output": {
    "video": "https://temp.pixeldojo.ai/pixeldojotemp/1705930123-456789.mp4"
  },
  "creditCost": 10,
  "expiresAt": "2026-11-16T17:22:20Z"
}

LLM Documentation Try in Web UI Get API Key Usage Dashboard Buy Credits