Genjustsu-Open-Source-Workflow

Open-source AI video replacement workflow by TEIN. Combine depth maps, SAM segmentation, face meshes, and audio processing to replace characters and objects with Seedance. Includes a local web UI to prepare inputs, review masks, preview generations, and export with original audio.

View on GitHub

Stars: 469
Forks: 138
+ today: +1
Created: 5d

Ranking data as of October 11, 2026 (UTC).

Star History

Today, hour by hour

469 stars

468469

Overview

The project is written in Python and has 138 forks. It was created 5d ago.

AI-generated summary of the repository README — may contain errors.

What it is

Genjustsu is an open-source AI video replacement workflow by TEIN, written in Python. The description says it combines depth maps, SAM segmentation, face meshes and audio processing to replace characters and objects with Seedance-generated content.

Capabilities described

- Includes a local web UI for preparing inputs, reviewing masks, previewing generations and exporting with the original audio. - The README summary says it uses the Seedance integration with human-face support, draft previews and approved 1080p generation. - Requires API keys, which the README summary says should be entered in your own .env file.

Getting started

The README summary mentions macOS and Ubuntu/WSL system packages and a .env file. The supplied evidence does not include full install commands, so see the repository README.

Installation

git clone https://github.com/sirioberati/Genjustsu-Open-Source-Workflow.git
cd Genjustsu-Open-Source-Workflow
# see README for setup

Frequently Asked Questions

Which API keys do I need?

The README summary says to fill a .env file with your own API keys. The exact key names are in the README.

Does it need external services?

Yes. The README summary says the workflow uses the Seedance integration through an external API.

What license does it use?

The supplied metadata lists MIT.