Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/thesofakillers/gigachadify
🗿 gigachadify any face
https://github.com/thesofakillers/gigachadify
deepfakes faceswap machine-learning meme-generator
Last synced: about 5 hours ago
JSON representation
🗿 gigachadify any face
- Host: GitHub
- URL: https://github.com/thesofakillers/gigachadify
- Owner: thesofakillers
- License: mit
- Created: 2024-02-11T14:53:44.000Z (9 months ago)
- Default Branch: main
- Last Pushed: 2024-07-07T15:47:28.000Z (4 months ago)
- Last Synced: 2024-07-07T17:10:28.293Z (4 months ago)
- Topics: deepfakes, faceswap, machine-learning, meme-generator
- Language: Python
- Homepage: https://knowyourmeme.com/memes/gigachad
- Size: 784 KB
- Stars: 9
- Watchers: 1
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# gigachadify
🗿 gigachadify any face: Put any face onto the Gigachad meme with this script.
This tool automatically detects a face in your image and swaps it into the
legendary Gigachad."Giulio did you really make a script that swaps your face into Gigachad?"
![gigagiuliochad](outputs/gigagiuliochad.png)
"Yes."
## Setup
1. Clone this repo
2. Install the requirements outlined in [pyproject.toml](pyproject.toml)
3. Download the faceswap model from
[huggingface](https://huggingface.co/datasets/Gourieff/ReActor/resolve/main/models/inswapper_128.onnx)
and put it in [models/insightface](models/insightface)## Usage
```stdout
usage: python gigachadify.py [-h] --input-image INPUT_IMAGE
[--output-image OUTPUT_IMAGE]Gigachadify any face
options:
-h, --help show this help message and exit
--input-image INPUT_IMAGE
Path or URL to the input image
--output-image OUTPUT_IMAGE
Path to the output image (default: outputs/gigachad.png)
```## License
This project relies on
[insightface](https://github.com/deepinsight/insightface). Please refer to their
license.This project also relies on
[Gourieff's ReActor](https://huggingface.co/datasets/Gourieff/ReActor) models.
Please refer to their license.Otherwise, this project is licensed under the MIT License. See
[LICENSE](LICENSE)## Project state
MVP. Quick and dirty, will polish in coming weeks.
TODO:
- [ ] handle multiple faces in the input image.
- [ ] face restoration.
- [ ] better setup.## See also:
- [ComfyUI](https://github.com/comfyanonymous/ComfyUI)
- [Gourieff's ReActor ComfyUI Node](https://github.com/Gourieff/comfyui-reactor-node)
- [Insightface](https://github.com/deepinsight/insightface)