Wan Video Clone

Community

kevinbadi

wan-video-clone

Clone Kevin's videos as Kev's Assistant using AI face swap + voice clone + WAN 2.2 animate. Handles long videos by splitting into 5s chunks, processing each through the pipeline, and stitching back together. Trigger when asked to clone a video, create a Kev's Assistant version, or convert Kevin's content into Kev's Assistant content.

Overview

Publisher	kevinbadi
Repository	`ai-os-skills`
Skill name	`wan-video-clone`
Stars	73
Forks	29
Bundled files	2
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
2 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by kevinbadi on GitHub. Read the source before you install it.

Installation

Install the Wan Video Clone AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/kevinbadi/ai-os-skills/tree/main/wan-video-clone
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/kevinbadi/ai-os-skills.git /tmp/ai-os-skills
mkdir -p .claude/skills
cp -r /tmp/ai-os-skills/wan-video-clone .claude/skills/wan-video-clone

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Wan Video Clone in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Wan Video Clone on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Wan Video Clone is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

WAN 2.2 AI Video Clone Pipeline (Chunked)

Takes Kevin's video in, splits it into ~30s chunks, runs each through the AI pipeline, stitches them back together. Out the other side: Kev's Assistant talking in Kevin's chair with Kev's Assistant's voice.

Pipeline


Kevin's Video
    │
    ▼
┌─────────────────────┐
│  ffmpeg split (~5s)  │
└────────┬────────────┘
         │
    ┌────▼────┐
    │ chunk_0 │  chunk_1  chunk_2  ...
    └────┬────┘
         │  For each chunk:
         ├─ Extract audio (ffmpeg local)
         ├─ Voice clone → Kev's Assistant (ChatterboxHD / fal.ai)
         ├─ Merge cloned audio back (ffmpeg local)
         ├─ Upload merged chunk to fal.ai
         ├─ WAN 2.2 animate/replace (Kev's Assistant face + chunk)
         └─ Download output chunk
         │
    ┌────▼────────────────┐
    │  ffmpeg stitch all   │
    └────────┬─────────────┘
             │
             ▼
      Kev's Assistant's Video

Prerequisites

FAL_KEY env var (fal.ai API key)
ffmpeg installed
assets/kevs-reference.png — Kev's Assistant face reference image
assets/kevs-voice-sample.mp3 — Kev's Assistant voice sample for cloning
Optional: REPLICATE_API_TOKEN (not needed if using local ffmpeg for audio)

Usage

bash
# Basic — clone a video
node skills/wan-video-clone/scripts/wan-video-clone.js \
  --video "https://example.com/kevin-video.mp4"

# Local file
node skills/wan-video-clone/scripts/wan-video-clone.js \
  --video /path/to/kevin.mp4

# Custom chunk size (default 5s)
node skills/wan-video-clone/scripts/wan-video-clone.js \
  --video "URL" --chunk-duration 5

# Process 2 chunks at a time (parallel)
node skills/wan-video-clone/scripts/wan-video-clone.js \
  --video "URL" --parallel 2

# Skip voice clone (face only)
node skills/wan-video-clone/scripts/wan-video-clone.js \
  --video "URL" --skip-voice

# Skip face swap (use Kev's Assistant ref image directly with WAN)
node skills/wan-video-clone/scripts/wan-video-clone.js \
  --video "URL" --skip-face-swap

# Dry run (show plan without executing)
node skills/wan-video-clone/scripts/wan-video-clone.js \
  --video "URL" --dry-run

Flags

Flag	Default	Description
`--video`	required	Source video URL or local path
`--chunk-duration`	`30`	Seconds per chunk
`--parallel`	`1`	Max concurrent chunk processing
`--resolution`	`720p`	WAN output resolution
`--kevs-image`	auto	Kev's Assistant face image URL (uses asset if not set)
`--kevs-voice`	auto	Kev's Assistant voice sample URL (uses asset if not set)
`--prompt`	auto	Face swap prompt for Nano Banana
`--skip-voice`	false	Skip voice cloning step
`--skip-face-swap`	false	Use Kev's Assistant ref image directly
`--output`	`output/wan-clones/`	Output directory
`--dry-run`	false	Show plan without executing

Timing

Face swap: ~1 min (one-time)
Per chunk: ~15-20 min (WAN animate is the bottleneck)
A 5 min video = 10 chunks × ~20 min = ~3.5 hours sequential, ~2 hours with parallel=2
A 30s video = 1 chunk = ~20-25 min total
Stitching: seconds
IMPORTANT: Source video must be H.264 codec. AV1/VP9 causes WAN to hang. Script auto-re-encodes if needed.

Output

Final video saved to output/wan-clones/<timestamp>/kevs-assistant-clone-<timestamp>.mp4

Key APIs

fal.ai Nano Banana Pro — face swap (fal-ai/nano-banana-pro/edit)
fal.ai ChatterboxHD — voice clone (resemble-ai/chatterboxhd/speech-to-speech)
fal.ai WAN 2.2 — animate/replace (fal-ai/wan/v2.2-14b/animate/replace)
ffmpeg — split, extract audio, merge audio, stitch (all local, no API)

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

assets/kevs-voice-sample.mp31.8K KB
scripts/wan-video-clone.js20 KB

Frequently asked questions

What does the Wan Video Clone AI skill do?

Why use Wan Video Clone on TypingMind?

Because you install it once and use it with any model. Wan Video Clone is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Wan Video Clone in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kevinbadi/ai-os-skills/tree/main/wan-video-clone. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Wan Video Clone?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Wan Video Clone?

As many as you like. As long as a model supports skills, you can use Wan Video Clone with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Wan Video Clone AI skill free?

It is published on GitHub by kevinbadi. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Prompt Lookup

CommunityPopular

Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.

Banner Design

Design banners for social media, ads, website heroes, creative assets, and print. Multiple art direction options with optional generated or supplied visuals. Actions: design, create, generate banner.…

Distributed Triage

Sub-triages issues in the oncall:distributed queue by assigning distributed module labels, routing to sub-oncalls, and marking triaged. Use when an issue has been routed to oncall:distributed and…

Hyperframes

Create video compositions, animations, title cards, overlays, captions, voiceovers, audio-reactive visuals, and scene transitions in HyperFrames HTML. Use when asked to build any HTML-based video…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

WAN 2.2 AI Video Clone Pipeline (Chunked)

Pipeline

Prerequisites

Usage

Flags

Timing

Output

Key APIs

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now