Downloads · 30 days
0
zeroscratches
leonelhs/zeroscratches
zeroscratches is a machine learning model from leonelhs. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
This is a lightweight implementation of Microsoft Bringing Old Photos Back to Life
Access
Public
Updated Jun 14, 2023
Repo size
754 MB
Likes
6
Public
Repo makeup
Click a slice to open those files.
.pt452 MB · 60%
At a glance
- License
- mit
- Access
- Public
- Created
- Jun 7, 2023
- Updated
- Jun 14, 2023
- SHA
- 07aa447a
Model card
From the Hugging Face model README
Zero Scratches
Old Photo Restoration
This is a lightweight implementation of Microsoft Bringing Old Photos Back to Life
Test the Hugging Face App
For developers
pip install zeroscatches
Basic usage
import PIL.Image
from zeroscratches import EraseScratches
image_path = "/path/to/image-scratched.jpg"
eraser = EraseScratches()
image = PIL.Image.open(image_path)
new_img = eraser.erase(image)
new_img = PIL.Image.fromarray(new_img)
new_img.show()
Get the pretrained models at Hugging Face Zero Scratches
Some Apps using the library:
Face Shine
Face Shine Is a backend server for photo enhancement and restoration.
Super Face
Super Face is a Python QT frontend for Face Shine server.
<img src="https://drive.google.com/uc?export=view&id=1D7hpjQSlUkzfTba-E5Ul4Rb1c8lYkFj5"/> <img src="https://drive.google.com/uc?export=view&id=1oKpJe-Ff3SeEekhGVRP1Ap3eIFqt0c8u"/>- License
- mit
- Created
- Jun 7, 2023
- Updated
- Jun 14, 2023