Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Demo programs for the Talking Head Anime from a Single Image 2: More Expressive project.
| Date | Stars |
|---|---|
| 2026-07-24 | 1154 |
| 2026-07-25 | 1154 |
| 2026-07-28 | 1154 |
| 2026-07-30 | 1154 |
| 2026-08-06 | 1154 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Demo Code for "Talking Head Anime from a Single Image 2: More Expressive"
This repository contains demo programs for the [Talking Head Anime from a Single Image 2: More Expressive](http://pkhungurn.github.io/talking-head-anime-2)
project. Similar to the [previous version](http://github.com/dragonmeteor/talking-head-anime-demo), it has two programs:
* The `manual_poser` lets you manipulate the facial expression and the head rotation of an anime character, given in
a single image, through a graphical user interface. The poser is available in two forms: a standard GUI application,
and a [Jupyter notebook](https://jupyter.org/).
* The `ifacialmocap_puppeteer` lets you transfer your facial motion, captured by a commercial iOS application
called [iFacialMocap](http://www.ifacialmocap.com), to an image of an anime character.
## Try the Manual Poser on Google Colab
If you do not have the required hardware (discussed below) or do not want to download the code and set up an environment to run it, click [](https://colab.research.google.com/github/pkhungurn/talking-head-anime-2-demo/blob/master/colab.ipynb) to try running the manual poser on [Google Colab](https://research.google.com/colaboratory/faq.html).
## Hardware Requirements
Both programs require a recent and powerful Nvidia GPU to run. I could personally ran them at good speed with the
[Nvidia Titan RTX](https://www.nvidia.com/en-us/deep-learning-ai/products/titan-rtx/). However, I think recent high-end
gaming GPUs such as the [RTX 2080](https://www.nvidia.com/en-us/geforce/graphics-cards/rtx-2080/), the
[RTX 3080](https://www.nvidia.com/en-us/geforce/graphics-cards/30-series/rtx-3080/), or better would do just as well.
The `ifacialmocap_puppeteer` requires an iOS device that is capable of computing
[blend shape parameters](https://developer.apple.com/documentation/arkit/arfaceanchor/2928251-blendshapes) from a video
feed. This means that the device must be able to run iOS 11.0 or higher and must have a TrueDepth front-facing camera.
(See [this page](https://developer.apple.com/documentation/arkit/content_anchors/tracking_and_visualizing_faces) for
more info.) In other words, if you have the iPhone X or something better, you should be all set. Personally, I have
used an iPhone 12 mini.
## Software Requirements
Both programs were written in Python 3. To run the GUIs, the following software packages are required:
* Python >= 3.8
* PyTorch >= 1.7.1 with CUDA support
* SciPY >= 1.6.0
* wxPython >= 4.1.1
* Matplotlib >= 3.3.4
In particular, I created the environment to run the programs with [Anaconda](https://www.anaconda.com/), using the
following commands:
```
> conda create -n talking-head-anime-2-demo python=3.8
> conda activate talking-head-anime-2-demo
> conda install pytorch torchvision cudatoolkit=10.2 -c pytorch
> conda install scipy
> pip install wxPython
> conda install matplotlib
```
**Note:** You may find that the particular versions of Python (3.8) and CUDA Toolkit (10.2) might not work for your particular computer setup. When this happens, replace these versions with those that work with your hardware. The command would become:
```
> conda create -n talking-head-anime-2-demo python=[YOUR-PYTHON-VERSION]
> conda activate talking-head-anime-2-demo
> conda install pytorch torchvision cudatoolkit=[YOUR-CUDA-TOOLKIT-VERSION] -c pytorch
> conda install scipy
> pip install wxPython
> conda install matplotlib
```
In general, the latest version of Python and the latest version of CUDA Toolkit shown on [PyTorch's website](http://pytorch.org) would work.
To run the Jupyter notebook version of the `manual_poser`, you also need:
* Jupyter Notebook >= 6.2.0
* IPyWidgets >= 7.6.3
This means that, in addition to the commands above, you also need to run:
```
> conda install -c conda-forge noExcerpt of 10,724 characters
Read on GitHub
23
5
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:157af5754f8faf7d, topic:deep-learning, topic:pytorch
matched fp:157af5754f8faf7d, topic:computer-vision
matched fp:157af5754f8faf7d, name:talking head, desc:talking head, readme:talking head