
P Video
- 4.6k installs
- 680 repo stars
- Updated August 3, 2026
- halt-catch-fire/skills
P-Video is a skill for generating videos with Pruna P-Video and WAN text-to-video or image-to-video models via the inference.sh belt CLI, including audio sync and draft mode.
About
The p-video skill documents fast video generation with Pruna optimized models through the inference sh belt CLI Install belt-sh cli run belt login then invoke pruna p-video for text-to-video or image-to-video with optional audio sync draft mode for cheaper concept tests duration control and 720p or 1080p output The guide also routes to WAN apps pruna wan-t2v for economical text prompts at 480p or 720p flat per-video pricing and pruna wan-i2v to animate still images with gentle motion prompts Examples cover drone landscapes subtle camera moves on uploaded photos interview scenes paired with external audio URLs and cinematic 1080p renders Pruna positions these models for speed without quality loss compared with heavier hosted pipelines WAN 480p runs at 0 05 per video WAN 720p around 0 10 to 0 11 while P-Video bills per second by resolution Agents discover sibling apps via belt app list namespace pruna and can chain p-image portraits text-to-speech narration or the broader ai-video-generation and infsh-cli catalogs Choose P-Video when audio-aware general video matters pick WAN
- belt app run pruna/p-video supports text-to-video, image-to-video, audio sync, draft mode, duration, and 720p or 1080p
- pruna/wan-t2v offers flat-rate text-to-video at 480p ($0.05) or 720p ($0.10) per video
- pruna/wan-i2v animates still images with motion prompts at 480p or 720p
- Audio input on P-Video can sync generated footage to an external speech or music track
- belt app list --namespace pruna surfaces related Pruna image, avatar, and platform skills
P Video by the numbers
- 4,602 all-time installs (skills.sh)
- Ranked #112 of 1,335 Generative Media skills by installs in the Skillselion catalog
- Security screen: MEDIUM risk (skills.sh audit)
- Data as of Aug 5, 2026 (Skillselion catalog sync)
p-video capabilities & compatibility
- Capabilities
- text to video and image to video via pruna/p vid · economical wan text and image animation at 480p · audio synced generation and draft mode for faste · 1080p cinematic output and duration control on p · namespace discovery with belt app list namespa
- Use cases
- video generation · marketing · orchestration
What p-video says it does
P-Video supports audio input that syncs with the video
Fast and economical text-to-video
npx skills add https://github.com/halt-catch-fire/skills --skill p-videoAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 4.6k |
|---|---|
| repo stars | ★ 680 |
| Security audit | 2 / 3 scanners passed |
| Last updated | August 3, 2026 |
| Repository | halt-catch-fire/skills ↗ |
How do I produce fast, economical AI video clips from prompts or still images without self-hosting diffusion or video models?
Generate text-to-video or image-to-video clips with Pruna P-Video and economical WAN models through the inference.sh belt CLI.
Who is it for?
Developers and agent workflows that need quick text-to-video, image-to-video, or audio-synced clips through inference.sh with minimal setup.
Skip if: Skip when you need talking-head avatar presenters from a portrait; use p-video-avatar instead, or when local-only model training is required.
When should I use this skill?
User mentions pruna video, p-video, wan t2v, wan i2v, fast video generation, optimized video, economic video generation, or pruna text to video.
What you get
Working belt CLI commands for P-Video and WAN apps with resolution, duration, draft, and audio options plus namespace discovery for related Pruna tools.
- Generated MP4 video clips
- Image-to-video outputs
- Text-to-video outputs with audio
By the numbers
- 3 models: P-Video, WAN-T2V, WAN-I2V
- 720p and 1080p output resolutions
Files
Install the belt CLI skill: npx skills add belt-sh/cliPruna P-Video Generation
Generate videos with Pruna's optimized video models via inference.sh CLI.

Quick Start
Requires inference.sh CLI (belt). Install instructionsbelt 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 prunaRelated Skills
# Full platform skill (all 250+ 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-speechBrowse all apps: belt app store
Documentation
- Running Apps - How to run apps via CLI
- Streaming Results - Real-time progress updates
- Content Pipeline Example - Building media workflows
Related skills
Forks & variants (3)
P Video has 3 known copies in the catalog totaling 4.4k installs. They canonicalize to this original listing.
- qu-skills - 3.9k installs
- inference-sh - 446 installs
- skills-shell - 7 installs
How it compares
Pick P-Video for fast Pruna WAN text-to-video; use P-Video-Avatar when you need talking-head TTS avatars from a portrait.
FAQ
How do I run a basic P-Video text-to-video clip?
After belt login, run belt app run pruna/p-video --input with a prompt plus optional duration and resolution such as 720p.
When should I use WAN models instead of P-Video?
Use pruna/wan-t2v or pruna/wan-i2v when flat per-video pricing at 480p or 720p is enough and you want fast economical drafts.
Can P-Video sync video to my own audio?
Yes. Pass an audio URL in the input JSON alongside your prompt to generate footage aligned with that track.
Is P Video safe to install?
skills.sh reports 2 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.