https://github.com/mdsrqbl/omnihuman

AI model that understands text & humanoids.
https://github.com/mdsrqbl/omnihuman

computer-vision generative-ai nlp pose-synthesis pytorch transformers

Last synced: about 1 year ago
JSON representation

AI model that understands text & humanoids.

• Host: GitHub
• URL: https://github.com/mdsrqbl/omnihuman
• Owner: mdsrqbl
• License: apache-2.0
• Created: 2024-08-24T11:47:43.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2025-04-05T14:55:41.000Z (about 1 year ago)
• Last Synced: 2025-04-05T15:32:34.806Z (about 1 year ago)
• Topics: computer-vision, generative-ai, nlp, pose-synthesis, pytorch, transformers
• Language: Python
• Homepage:
• Size: 35.2 KB
• Stars: 92
• Watchers: 1
• Forks: 28
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • Funding: .github/FUNDING.yml
  • License: LICENSE

Awesome Lists containing this project

README

          
# OmniHuman

> [!IMPORTANT]

> 
This is the Original one
this isn't bytedance's plagiarized mock article 😒
#protect_open_source






**AI model that understands humanoids and text.**




[![PyPi](https://img.shields.io/pypi/v/omnihuman?logo=pypi)](https://pypi.org/project/omnihuman/)

[![Documentation Status](https://readthedocs.org/projects/omnihuman/badge/?version=latest)](https://omnihuman.readthedocs.io/en/latest/?badge=latest)

[![python](https://img.shields.io/pypi/pyversions/omnihuman?logo=python)](https://pypi.org/project/omnihuman/)

[![GitHub Repo stars](https://img.shields.io/github/stars/mdsrqbl/omnihuman?logo=github)](https://github.com/mdsrqbl/omnihuman/stargazers)

[![Downloads](https://img.shields.io/pepy/dt/omnihuman?color=purple&logoColor=white&logo=data:image/svg+xml;base64,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)](https://pepy.tech/projects/omnihuman/)


| **Support Us** ❤️ | [![PayPal](https://img.shields.io/badge/PayPal-00457C?logo=paypal&logoColor=white)](https://www.paypal.com/donate/?hosted_button_id=7SNGNSKUQXQW2) |

| ---------------- | -------------------------------------------------------------------------------------------------------------------------------------------------- |



---

1. [OmniHuman](#omnihuman)

   1. [Installation](#installation)

   2. [Usage](#usage)

   3. [Citation \& License](#citation--license)

## Installation

```bash

pip install omnihuman

```

or install editable from source

```bash

git clone https://github.com/mdsrqbl/omnihuman.git

cd omnihuman

pip install -e .

```

## Usage

```python

import omnihuman

import PIL.Image

text = "Raise both hands and clap overhead."

frames = omnihuman.read_frames("path/to/image.jpg")  # (1, channels, height, width)

# frames = omnihuman.read_frames("path/to/video.mp4")  # (n_frames, channels, height, width)

# model = omnihuman.OmniHuman()

# frames = model.generate_video(text, frames)

PIL.Image.fromarray(frames[-1].permute(1,2,0).numpy()).show()

```

Full documentation is available at [omnihuman.readTheDocs.io](https://omnihuman.readthedocs.io/en/latest/).

## Citation & License

```bibtex

@misc{mdsr2024omnihuman,

  author = {Mudassar Iqbal},

  title = {OmniHuman: AI model that understands text and humanoids.},

  year = {2024},

  publisher = {GitHub},

  howpublished = {\url{https://github.com/mdsrqbl/omnihuman}}

}

```

This project is licensed under Apache License 2.0 - see the [LICENSE](https://github.com/mdsrqbl/omnihuman/blob/main/LICENSE) file for details.

You are permitted to use the library & models, create modified versions, or incorporate pieces of the code into your own work. Your product or research, whether commercial or non-commercial, must provide appropriate credit to the original author(s) by citing this repository & research papers. And although it follows common sense, you can not steal namespace and must put in the effort to give your work an original name. 

Stay tuned for research papers!