prunaai/p-video-edit | API reference

Edit videos with a text prompt and optional reference images.

Public

5 runs

Run prunaai/p-video-edit with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

Input schema

The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.

Field	Type	Default value	Description
video	string		Input video to edit. Maximum length: 15 seconds.
prompt	string		Text prompt describing the edit.
images	array	[]	Optional reference image(s) for reference-guided editing. Up to 4 images. Supports jpg, jpeg, png, webp.
task	None	auto	Editing task. Use auto to choose from the prompt, or pick a specific task. Reference tasks require at least one image.
prompt_upsampling	boolean	True	Use prompt upsampling to enhance the edit prompt.
draft	boolean	False	Draft mode. Generates a faster, lower-quality preview of the edit.
save_audio	boolean	True	Save the video with audio.
seed	integer	Max: 2147483647	Random seed. Set for reproducible generation.

{
  "type": "object",
  "title": "Input",
  "required": [
    "video",
    "prompt"
  ],
  "properties": {
    "seed": {
      "type": "integer",
      "title": "Seed",
      "maximum": 2147483647,
      "minimum": 0,
      "x-order": 7,
      "nullable": true,
      "description": "Random seed. Set for reproducible generation."
    },
    "task": {
      "enum": [
        "Reference + Video Editing",
        "Reference + Video Editing: (high movement)",
        "Video Editing",
        "Camera Editing",
        "Subject Movement Editing",
        "style editing",
        "auto"
      ],
      "type": "string",
      "title": "task",
      "description": "Editing task. Use auto to choose from the prompt, or pick a specific task. Reference tasks require at least one image.",
      "default": "auto",
      "x-order": 3
    },
    "draft": {
      "type": "boolean",
      "title": "Draft",
      "default": false,
      "x-order": 5,
      "description": "Draft mode. Generates a faster, lower-quality preview of the edit."
    },
    "video": {
      "type": "string",
      "title": "Video",
      "format": "uri",
      "x-order": 0,
      "description": "Input video to edit. Maximum length: 15 seconds."
    },
    "images": {
      "type": "array",
      "items": {
        "type": "string",
        "format": "uri"
      },
      "title": "Images",
      "default": [],
      "x-order": 2,
      "description": "Optional reference image(s) for reference-guided editing. Up to 4 images. Supports jpg, jpeg, png, webp."
    },
    "prompt": {
      "type": "string",
      "title": "Prompt",
      "x-order": 1,
      "description": "Text prompt describing the edit."
    },
    "save_audio": {
      "type": "boolean",
      "title": "Save Audio",
      "default": true,
      "x-order": 6,
      "description": "Save the video with audio."
    },
    "prompt_upsampling": {
      "type": "boolean",
      "title": "Prompt Upsampling",
      "default": true,
      "x-order": 4,
      "description": "Use prompt upsampling to enhance the edit prompt."
    }
  }
}

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema

{
  "type": "string",
  "title": "Output",
  "format": "uri"
}