--- title: "P-Video" description: "Premium AI video generation from text, images, and audio" url: "https://docs.api.pruna.ai/guides/models/p-video" image: "https://docs.api.pruna.ai/_og/d/c_Ocean.takumi,title_P-Video,description_~UHJlbWl1bSBBSSB2aWRlbyBnZW5lcmF0aW9uIGZyb20gdGV4dCwgaW1hZ2VzLCBhbmQgYXVkaW8,props_eyJ0aGVtZSI6eyJtb2RlIjoibGlnaHQiLCJjb2xvcnMiOnsicHJpbWFyeSI6IiM3YzNhZWQifX19,p_Ii9ndWlkZXMvbW9kZWxzL3AtdmlkZW8i,s_aBukqQeKwjw9QmjW.png" --- # P-Video Premium AI video generation from text, images, and audio by Pruna ## [Overview](#overview) P-Video is Pruna's premium video generation model supporting text-to-video, image-to-video, and audio-conditioned generation. It offers up to 1080p resolution at 24 or 48 fps, with configurable duration up to 20 seconds. Built-in prompt upsampling automatically enhances your prompts for better results. **Rate Limit:** 250 requests per minute **Category:** Video Generation **Pricing:** | Configuration | Price | | :------------------------ | :-------------------------------- | | 720p - draft mode is OFF | 0.02$ per second of output video | | 720p - draft mode is ON | 0.005$ per second of output video | | 1080p - draft mode is OFF | 0.04$ per second of output video | | 1080p - draft mode is ON | 0.01$ per second of output video | ## [Quickstart](#quickstart) ### [Text-to-Video (Asynchronous)](#text-to-video-asynchronous) ```bash curl -X POST 'https://api.pruna.ai/v1/predictions' \ -H 'Content-Type: application/json' \ -H 'apikey: YOUR_API_KEY' \ -H 'Model: p-video' \ -d '{ "input": { "prompt": "A sports car drifting through a neon-lit city at night, cinematic aerial shot", "duration": 5, "resolution": "720p", "aspect_ratio": "16:9" } }' ``` Response: ```text { "id": "1zww7deyssrme0csqwr90phzzr", "model": "p-video", "input": { ... }, "get_url": "https://api.pruna.ai/v1/predictions/status/1zww7deyssrme0csqwr90phzzr" } ``` Check status and get results: ```bash curl -X GET 'https://api.pruna.ai/v1/predictions/status/1zww7deyssrme0csqwr90phzzr' \ -H 'apikey: YOUR_API_KEY' ``` ### [Text-to-Video (Synchronous)](#text-to-video-synchronous) ```bash curl -X POST 'https://api.pruna.ai/v1/predictions' \ -H 'Content-Type: application/json' \ -H 'apikey: YOUR_API_KEY' \ -H 'Model: p-video' \ -H 'Try-Sync: true' \ -d '{ "input": { "prompt": "A sports car drifting through a neon-lit city at night, cinematic aerial shot", "duration": 5, "resolution": "720p", "aspect_ratio": "16:9" } }' ``` Response (if completed within 60 seconds): ```text { "status": "succeeded", "generation_url": "/v1/predictions/delivery/xezq/52UGYRrRfqViaKmvYsEnENTh0qLDAWHptQ8jOnEHu7XC6AtKA/output.mp4" } ``` ### [Image-to-Video](#image-to-video) #### [Start with uploading an image](#start-with-uploading-an-image) ```bash curl -X POST "https://api.pruna.ai/v1/files" \ -H "apikey: YOUR_API_KEY" \ -F "content=@/path/to/your/file.jpg" ``` Note: Use -F (form) with @ prefix to upload a file from your local filesystem. The file path should be absolute or relative to your current directory. Response: ```text { "id": "fqadqq42xq", "name": "test.jpg", "content_type": "image/jpeg", "size": 185093, "etag": "\"14e9a51deaac6bee2dd8b5c52d7d0b5f\"", "checksums": { "sha256": "aa10d5d09bcee5cb5d854bd81899308b0cf0c0c50e29d4f00c2c06e51f0e2fe6" }, "metadata": { "content_length": 185093, "width": 1344, "height": 768 }, "created_at": "2025-01-08T18:51:26.729Z", "expires_at": "2025-01-09T18:51:26.729Z", "urls": { "get": "https://api.pruna.ai/v1/files/fqadqq42xq" } } ``` #### [Then pass that image in the "image" field](#then-pass-that-image-in-the-image-field) ```bash curl -X POST 'https://api.pruna.ai/v1/predictions' \ -H 'Content-Type: application/json' \ -H 'apikey: YOUR_API_KEY' \ -H 'Model: p-video' \ -d '{ "input": { "prompt": "The camera slowly pushes in, the person turns their head and smiles, gentle wind moves their hair", "image": "https://api.pruna.ai/v1/files/fqadqq42xq", "duration": 5, "resolution": "720p" } }' ``` Note: The image parameter should be a publicly accessible URL. You can upload files using the /v1/files endpoint first. When an input image is provided, the aspect\_ratio parameter is ignored. ### [Audio-Conditioned Video](#audio-conditioned-video) #### [Upload an audio file first](#upload-an-audio-file-first) ```bash curl -X POST "https://api.pruna.ai/v1/files" \ -H "apikey: YOUR_API_KEY" \ -F "content=@/path/to/your/audio.mp3" ``` #### [Then pass the audio URL in the "audio" field](#then-pass-the-audio-url-in-the-audio-field) ```bash curl -X POST 'https://api.pruna.ai/v1/predictions' \ -H 'Content-Type: application/json' \ -H 'apikey: YOUR_API_KEY' \ -H 'Model: p-video' \ -d '{ "input": { "prompt": "A musician performing on stage with dramatic lighting", "audio": "https://api.pruna.ai/v1/files/abc123audio", "resolution": "720p", "aspect_ratio": "16:9" } }' ``` Note: When audio is provided, the duration parameter is ignored — the video duration matches the audio length. Supported audio formats: flac, mp3, wav. ### [Parameters](#parameters) #### [Required Parameters](#required-parameters) | Parameter | Type | Description | | :-------- | :----- | :------------------------------- | | prompt | string | Text prompt for video generation | #### [Optional Parameters](#optional-parameters) | Parameter | Type | Default | Description | | :-------------------- | :----------- | :------ | :------------------------------------------------------------------------------- | | image | string (URI) | - | Input image to generate video from (image-to-video). Supports jpg, jpeg, png, webp | | audio | string (URI) | - | Input audio to condition video generation. Supports flac, mp3, wav | | duration | integer | 5 | Duration of the video in seconds (1-20). Ignored when audio is provided | | resolution | string | "720p" | Video resolution: "720p" or "1080p" | | fps | integer | 24 | Frames per second: 24 or 48 | | aspect_ratio | string | "16:9" | Aspect ratio of the video. Options: "16:9", "9:16", "4:3", "3:4", "3:2", "2:3", "1:1". Ignored when an input image is provided | | seed | integer | random | Random seed. Set for reproducible generation | | draft | boolean | false | Draft mode. Generates a lower-quality preview of the video | | save_audio | boolean | true | Save the video with audio | | last_frame_image | string (URI) | - | Reference image for the last frame of the video. Supports jpg, jpeg, png, webp | | prompt_upsampling | boolean | true | Use prompt upsampling to enhance the prompt | | disable_safety_filter | boolean | true | Disable safety filter for prompts and input images | License: [https://github.com/Lightricks/LTX-2/blob/main/LICENSE](https://github.com/Lightricks/LTX-2/blob/main/LICENSE)