skills.rest
inference-sh
inference-shOFFICIAL
Explore all skills by this author →
WebsiteGitHub

p-video

Generate videos from text or images using Pruna models via inference.sh CLI.

688|95|Updated Jan 31, 2026
Search Tags:#video generation#text-to-video#image-to-video#ai video#pruna#wan models
One-click install
npx skills add https://github.com/inference-sh/skills --skill p-video
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: p-video
Source: https://github.com/inference-sh/skills/tree/main/tools/video/p-video
Command: npx skills add https://github.com/inference-sh/skills --skill p-video

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill enables users to generate high-quality videos from text or images using Pruna's optimized AI models, offering fast and cost-effective video creation.

Core Features & Use Cases

  • Text-to-Video Generation: Create videos from descriptive text prompts.
  • Image-to-Video Generation: Animate still images into dynamic video content.
  • Audio Support: Incorporate audio for synchronized video narration or effects.
  • Optimized Models: Utilizes Pruna's P-Video, WAN-T2V, and WAN-I2V for speed and efficiency.
  • Resolution Options: Supports 720p and 1080p resolutions.
  • Draft Mode: Faster and cheaper video generation for quick previews.
  • Use Case: Generate a marketing explainer video from a script, or animate a product image into a short promotional clip.

Quick Start

Generate a video from the prompt 'drone shot flying over a forest at sunset' using the pruna/p-video app.

Frequently Asked Questions about p-video

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate AI video from text prompts using WAN models?▼

Generate text-to-video by providing descriptive prompts to the WAN-T2V model via the inference CLI. This creates dynamic video content directly from text, supporting 720p and 1080p resolutions for high-quality output.

Can I animate a still image into a video clip?▼

Yes, image-to-video generation is supported using the WAN-I2V model. You can animate static images into dynamic video clips, useful for creating short promotional content or animated product demonstrations.

Does this AI video generation tool support audio synchronization?▼

Audio synchronization is supported, allowing you to incorporate audio tracks for synchronized video narration or effects. This enables creation of complete multimedia content with aligned sound.

What is the best way to speed up video generation and reduce costs?▼

Use draft mode for faster and cheaper video generation. This mode provides quick previews optimized for speed and economic efficiency, utilizing Pruna's optimized P-Video models for rapid inference.

How do I run text-to-video generation from the command line?▼

Run video generation using the inference.sh CLI tool. It interfaces with Pruna's optimized models, enabling you to execute text-to-video and image-to-video tasks directly from your command line environment.

What resolutions are supported for AI video generation?▼

The AI video generation supports both 720p and 1080p resolutions. You can select the appropriate resolution based on your quality requirements and budget constraints during the generation process.

Related Skills

Explore More Design & Creative Skills→
MohabsmarMohabsmar

wan-image-video-gen-edit

Generate and edit images and videos using Wan models via ModelStudio.

Community
Intermediate
yangyixxxxyangyixxxx
13

gptnb-image

Generate images, layered assets, and videos via the gptnb.ai middleware API.

Community
Advanced
twjarviszyra-webtwjarviszyra-web
3

optimizing-attention-flash

Optimize transformer attention with PyTorch SDPA or flash-attn to reduce memory usage.

Community
Advanced
a0972199950a0972199950
1

image-generation

Generate images and videos from text prompts using Gemini, fal.ai, and Grok Imagine.

Community
Intermediate