skills.rest
Aadi-110i
Aadi-110iCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

p-video

Generate videos from text, images, and audio using Pruna P-Video and WAN models via the inference.sh CLI.

Updated Jul 28, 2026
Search Tags:#video generation#text-to-video#image-to-video#inference.sh#ai video#pruna#wan
One-click install
npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill p-video-aadi-110i
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: p-video
Source: https://github.com/Aadi-110i/PEP-PROJECT/tree/main/skills/p-video
Command: npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill p-video-aadi-110i

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Creating AI-generated video typically requires managing complex model deployments and GPU infrastructure. This Skill lets you generate videos directly from the command line using Pruna's speed-optimized P-Video and WAN models hosted on inference.sh, with no local setup beyond the CLI. ## Core Features & Use Cases - Text-to-Video Generation: Create videos from text prompts using P-Video or the economical WAN-T2V model at 480p, 720p, or 1080p resolutions. - Image-to-Video Animation: Animate still images into moving video with WAN-I2V or P-Video by supplying an image URL and a motion prompt. - Audio-Synced Video: Attach an audio file to P-Video so the generated video syncs with speech or sound. - Draft Mode: Run faster, cheaper draft generations to test concepts before committing to full-quality renders. - Use Case: A content creator needs a short cinematic clip of a sunset beach for social media. They run one CLI command with a prompt, 720p resolution, and 5-second duration, then receive a generated video without touching any model infrastructure. ## Quick Start Ask the assistant to generate a 5-second 720p video of waves crashing on a beach at sunset using the Pruna P-Video model.

Frequently Asked Questions about p-video

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

FAQPage Schema
How do I generate a video from a text prompt with Pruna P-Video?▼

Run belt app run pruna/p-video with a JSON input containing your prompt, duration, and resolution. For example, pass a prompt describing the scene, set duration to 5 seconds, and choose 720p or 1080p output.

What is the difference between P-Video, WAN-T2V, and WAN-I2V?▼

P-Video handles text-to-video and image-to-video with audio support at 720p and 1080p. WAN-T2V is a cheaper text-to-video option at 480p or 720p, while WAN-I2V animates still images at 480p or 720p.

Can I add audio to an AI-generated video?▼

Yes, P-Video accepts an audio parameter with a URL to an audio file such as an MP3. The generated video syncs with the provided audio, which is useful for talking-person or narration scenarios.

How do I animate a still image into a video?▼

Use pruna/wan-i2v or pruna/p-video with an image parameter pointing to your image URL plus a prompt describing the desired motion, such as gentle camera movement or natural breathing.

What do I need to install before running Pruna video generation?▼

You need the inference.sh CLI called belt, installed from the official install instructions, and an authenticated session via belt login. After that, all models run remotely with no local GPU required.

How much does WAN video generation cost?▼

WAN-T2V costs $0.05 per video at 480p and $0.10 at 720p, while WAN-I2V costs $0.05 at 480p and $0.11 at 720p. P-Video pricing is per second and varies by resolution and draft mode.

Related Skills

Explore More Design & Creative Skills→
ccnuzwccnuzw
11

seedance-storyboard-skill

Convert director narration and scene notes into Seedance 2.0 formatted video prompts.

Community
Intermediate
refly-airefly-ai
199

video-creator

Generates short AI-powered videos and scripts for social media platforms.

Official
Intermediate
thangvawnthangvawn

fal-ai-media

Generate images, videos, and audio using fal.ai models.

Community
Advanced
JKhyroJKhyro

stable-diffusion-image-generation

Generate images from text prompts and source images using Stable Diffusion pipelines.

Community
Advanced