About

Imported from inference-sh/skills (tools/video/p-video/SKILL.md) via skills.sh. Install upstream with npx skills add inference-sh/skills --skill p-video. Copyright stays with the author.

Install the belt CLI skill: npx skills add belt-sh/cli

Pruna P-Video Generation

Name: p-video
Author: inference-sh

Generate videos with Pruna's optimized video models via inference.sh CLI.

P-Video Generation

Quick Start

Requires inference.sh CLI (belt). Install instructions

belt login

belt app run pruna/p-video --input '{"prompt": "drone shot flying over a forest at sunset"}'

Pruna Video Models

Pruna optimizes AI models for speed without sacrificing quality.

Model	App ID	Best For
P-Video	`pruna/p-video`	Text-to-video, image-to-video, with audio
WAN-T2V	`pruna/wan-t2v`	Text-to-video, 480p/720p
WAN-I2V	`pruna/wan-i2v`	Animate images, 480p/720p

Examples

Text-to-Video

belt app run pruna/p-video --input '{
  "prompt": "waves crashing on a beach at sunset",
  "duration": 5,
  "resolution": "720p"
}'

Image-to-Video

belt app run pruna/p-video --input '{
  "prompt": "gentle camera movement, clouds drifting",
  "image": "https://your-image.jpg"
}'

With Audio

P-Video supports audio input that syncs with the video:

belt app run pruna/p-video --input '{
  "prompt": "person talking in an interview setting",
  "audio": "https://your-audio.mp3"
}'

WAN Text-to-Video

Fast and economical text-to-video:

belt app run pruna/wan-t2v --input '{
  "prompt": "a cat playing with a ball of yarn",
  "resolution": "720p",
  "duration": 5
}'

WAN Image-to-Video

Animate any still image:

belt app run pruna/wan-i2v --input '{
  "prompt": "gentle movement, natural motion, subtle breathing",
  "image": "https://portrait.jpg",
  "resolution": "720p"
}'

1080p High Quality

belt app run pruna/p-video --input '{
  "prompt": "cinematic landscape with dramatic clouds",
  "resolution": "1080p",
  "duration": 5
}'

Draft Mode (Faster, Cheaper)

belt app run pruna/p-video --input '{
  "prompt": "quick concept test video",
  "draft": true
}'

Resolution Options

Model	Resolutions	Pricing
P-Video	720p, 1080p	Per second, varies by resolution/draft
WAN-T2V	480p, 720p	$0.05 (480p), $0.10 (720p) per video
WAN-I2V	480p, 720p	$0.05 (480p), $0.11 (720p) per video

Browse All Pruna Apps

belt app list --namespace pruna

Related Skills

# Full platform skill (all apps)
npx skills add inference-sh/skills@infsh-cli

# All video generation models
npx skills add inference-sh/skills@ai-video-generation

# Image-to-video guide
npx skills add inference-sh/skills@image-to-video

# Pruna image generation
npx skills add inference-sh/skills@p-image

# Text-to-speech (for video narration)
npx skills add inference-sh/skills@text-to-speech

Browse all apps: belt app list

Documentation

Running Apps - How to run apps via CLI
Streaming Results - Real-time progress updates
Content Pipeline Example - Building media workflows

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

yaml

targets:
  - https://api.opensmartroute.ai/api/v1/registry/inference-sh-skills-p-video/manifest   # or paste the manifest below

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

inference-sh-skills-p-video.ocm.jsonjson

{
  "ocm": "1",
  "id": "inference-sh-skills-p-video",
  "kind": "skill",
  "name": "p-video",
  "description": "Generate videos with Pruna P-Video and WAN models via inference.sh CLI. Models: P-Video, WAN-T2V, WAN-I2V. Capabilities: text-to-video, image-to-video, audio support, 720p/1080p, fast inference. Pruna optimizes models for speed without quality loss. Triggers: pruna video, p-video, pruna ai video, fast video generation, optimized video, wan t2v, wan i2v, economic video generation, cheap video generation, pruna text to video, pruna image to video",
  "publisher": "inference-sh",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "skill-md",
      "skills-sh"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Generate videos with Pruna P-Video and WAN models via inference.sh CLI. Models: P-Video, WAN-T2V, WAN-I2V. Capabilities: text-to-video, image-to-video, audio support, 720p/1080p, fast inference. Pruna optimizes models for speed without quality loss. Triggers: pruna video, p-video, pruna ai video, fast video generation, optimized video, wan t2v, wan i2v, economic video generation, cheap video generation, pruna text to video, pruna image to video"
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "skills.sh",
      "repository": "https://github.com/inference-sh/skills",
      "path": "tools/video/p-video/SKILL.md",
      "ref": "HEAD",
      "url": "https://www.skills.sh/inference-sh/skills/p-video",
      "key": "inference-sh/skills/tools/video/p-video/SKILL.md"
    },
    "allowed_tools": [
      "Bash(belt",
      "*)"
    ]
  },
  "instructions": "> **Install the belt CLI skill:** `npx skills add belt-sh/cli`\n\n# Pruna P-Video Generation\n\nGenerate videos with Pruna's optimized video models via [inference.sh](https://inference.sh) CLI.\n\n![P-Video Generation](https://cloud.inference.sh/app/files/u/4mg21r6ta37mpaz6ktzwtt8krr/01kkgymcjx9g2tv51m602jssn3.jpeg)\n\n## Quick Start\n\n> Requires inference.sh CLI (`belt`). [Install instructions](https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md)\n\n```bash\nbelt login\n\nbelt app run pruna/p-video --input '{\"prompt\": \"drone shot flying over a forest at sunset\"}'\n```\n\n\n## P",
  "cost": {
    "context_tokens": 842
  }
}

Fetch it by URL: GET /api/v1/registry/inference-sh-skills-p-video/manifest?version=1.0.0

Reviews

Star ratings from people who tried it. One review per account; edit yours any time.

No reviews yet. Install it, try it, and be the first to rate it.