Video Generation

P-Video 2 Pro Reference API

Pruna P-Video 2 Pro Reference: reference-to-video built on MiniMax H3. Up to 9 images, 3 video and 3 audio references, plus optional start and end frames, 480p or 768p, 5 to 15 seconds with native audio. keep_audio lip-syncs to your own song or line. Integrate this model via REST with endpoint docs, parameters, and code examples.

Prompting guide Compare video models Use cases

Img2Vid

Audio

Credit Cost

1.25 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-2-pro-reference/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-2-pro-reference.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
`prompt` required	string	Describe the video. Refer to references by what they show.	-
`reference_images`	array	Up to 9 image URLs (identity, product, style), start/end frames included in that count. The first 5 are included, each one past that adds 0.25 credits.	-
`reference_videos`	array	Up to 3 video URLs (2-15s each, 15s combined, max 1080p) for motion and camera. Each clip bills 1.5 credits per second up to the output length + 0.5s, 15s total.	-
`reference_audios`	array	Up to 3 audio URLs (15s combined) for voice and sound.	-
`keep_audio`	boolean	Use the single reference audio as the soundtrack, as is (lip sync to a song or line). Requires exactly one reference audio.	`false`
`image_url`	url	Optional opening frame. Counts as an image and can be combined with references.	-
`end_image_url`	url	Optional closing frame. Counts as an image.	-
`duration`	integer	Seconds (5-15). 1.25 credits per second. min: 5 \| max: 15	`5`
`resolution`	enum	Output resolution. `480p768p`	`768p`
`mode`	enum	speed (default) or cost (slower queue). Same price. `speedcost`	`speed`
`aspect_ratio`	enum	Output aspect ratio. adaptive follows the references. `adaptive16:99:164:33:4`+3 more	`16:9`
`prompt_upsampler`	enum	How much the model expands your prompt. A start or end frame forces turbo. `offturbomax`	`turbo`
`seed`	integer	Optional integer seed.	-

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 reference_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.

Supported Aspect Ratios

adaptive

16:9

9:16

4:3

3:4

3:2

2:3

1:1

Code Examples

Character reference — copy and paste to get started

bash

curl -X POST "https://pixeldojo.ai/api/v1/models/p-video-2-pro-reference/run" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "The person in the reference walks through a sunlit market",
    "reference_images": [
      "https://example.com/person.jpg"
    ],
    "duration": 5,
    "resolution": "768p",
    "aspect_ratio": "adaptive"
  }'

Response Format

Submit Response (202 Accepted)

json

{
  "jobId": "job_abc123...",
  "status": "pending",
  "statusUrl": "https://pixeldojo.ai/api/v1/jobs/job_abc123...",
  "creditCost": 5,
  "creditsRemaining": 95,
  "expiresAt": "2026-10-20T12:52:32Z"
}

Completed Response