OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Image & Video AI

Talking Head Anime 2 Demo

Talking Head Anime 2 Demo is a Python repository containing a graphical manual poser for changing an anime character’s facial expression and head rotation from a single image, plus a separate program for transferring iFacialMocap facial motion to character artwork.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Talking Head Anime 2 Demo — OpenViST project profile in Image & Video AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use the manual poser for hands-on expression and head-angle adjustments; use the puppeteer when transferring iFacialMocap facial motion to character artwork.

Who it is for

  • Anime character artists and VTuber creators who want to adjust expressions or head angles from a portrait.
  • Developers exploring a Python-based graphical posing workflow.
  • Creators with an iOS TrueDepth device who want to transfer captured facial motion to anime artwork.

Documented uses

  • Manually alter a character’s facial expression and head rotation from one image.
  • Use the manual poser through a desktop GUI or Jupyter notebook.
  • Transfer facial motion captured with iFacialMocap to an anime character image.
Before you choose

Requirements & limits

The manual poser can also be tried through a linked Google Colab notebook. Local GUI use requires Python dependencies, model files, and a recent powerful Nvidia GPU. The puppeteer additionally requires an iOS 11-or-later device with a TrueDepth front camera, iFacialMocap, its paired desktop application, and a shared network connection.

  • Both programs require a recent, powerful Nvidia GPU according to the README.
  • The manual poser offers both a standard GUI application and a Jupyter notebook; notebook use requires Jupyter Notebook and IPyWidgets.
  • The puppeteer has extra device and software prerequisites: TrueDepth-capable iOS hardware, iFacialMocap, a paired desktop application, and the same network for phone and computer.
  • The repository uses an MIT license, while model files use CC BY 4.0 and require creator attribution when redistributed.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the manual poser Jupyter notebook environment

Add the documented notebook dependencies and widget support to the manual poser environment.

Before you start

  • The base Python environment and packages documented for the GUI, including PyTorch with CUDA support.
  • Anaconda.

Steps

  1. Activate the talking-head-anime-2-demo environment if it is not already active.

  2. Install the notebook dependencies with conda install -c conda-forge notebook and conda install -c conda-forge ipywidgets.

  3. Enable notebook widgets with jupyter nbextension enable --py widgetsnbextension.

Expected outcome

The environment includes the documented Jupyter Notebook and IPyWidgets requirements for the manual poser notebook.

Guide limitations

  • The README specifies Jupyter Notebook 6.2.0 or higher and IPyWidgets 7.6.3 or higher.
  • These steps document notebook environment setup, not launching or operating the notebook.
  • The programs require a recent, powerful Nvidia GPU.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
pkhungurn/talking-head-anime-2-demo · Official homepage title · retained in its source language
How we review sourcesSuggest a correction