This AI video tool gives you total control. Free & offline
Character swapping and video retargeting workflows in ComfyUI are rapidly improving, offering filmmakers precise local manipulation without relying on cloud-based subscriptions.
What this lesson covers
This video tutorial covers the installation and usage of Mocha, a free and open-source AI tool integrated via ComfyUI for character replacement in existing videos. It demonstrates how Mocha preserves original lighting, colors, and background details better than alternative tools like WanAnimate.
Key takeaways from the creator
AI-extracted notes, not independently verified product claims. Timestamp links let you check each point in the original video.
- 0:00 ↗
Mocha is a free, open-source tool that lets creators replace characters in an existing video using a single reference image while matching movements, gestures, and expressions.
- 1:11 ↗
Mocha maintains better color and white balance consistency compared to alternative tools like WanAnimate or Kling.
- 3:59 ↗
Mocha can be run locally offline using ComfyUI through custom nodes and specialized wrappers.
- 5:01 ↗
Installing the WanVideoWrapper requires cloning the GitHub repository into the ComfyUI custom nodes directory and running dependency updates.
Workflow outlined in the video
- Open your ComfyUI custom nodes folder in the command prompt.
- Clone the WanVideoWrapper repository using git clone.
- Update the repository and install required packages listed in the requirements file.
- Download the Mocha replacement workflow JSON file from the repository.
- Drag and drop the workflow JSON into the ComfyUI interface and load your input video and reference character.
Before you use this workflow
These notes describe the source video at its publication date. Model access, pricing, connectors and interfaces may have changed. Check the original source and the provider’s current documentation before installing an add-on, connecting an account or spending credits.
ReelStack has not independently tested this workflow. Preview one representative shot and check motion, continuity and output quality before applying it to a full production. No result, cost saving or model capability is guaranteed.
Explore the tools
How to interpret the numbers
143,453 views captured 23 October 2026. ReelStack recommendation score: 55/100. Formula: radar-v5. This is ReelStack’s calculation, not a YouTube rating or a measure of factual accuracy.
Show the calculation
- 45% performance: 1.39× views vs 15 other channel videos observed at a similar age. View-evidence factor 99% (views / (views + 1,000))
- 25% freshness: 0/100 with a 14-day half-life
- 20% momentum: 65 views/day vs 3 channel baseline (8 comparable uploads), with the same view-evidence factor
- 10% engagement: 99/100; likes + 4× comments, smoothed with a 500-view neutral prior