Waifu2x Python
Python wrapper for waifu2x-ncnn-vulkan with a simple and powerful interface for image and video frame upscaling.
Features
- High-performance image upscaling using waifu2x-ncnn-vulkan
- Support for multiple image formats (PNG, JPG, WEBP, etc.)
- Multiple models including anime and photo styles
- GPU acceleration with fallback to CPU
- Batch processing of multiple images
- Progress tracking and error handling
Installation
pip install waifu2x-python
Dependencies
- waifu2x-ncnn-vulkan
- Python 3.8+
- OpenCV
- NumPy
- Pillow
Usage
Basic Example
from waifu2x_python import Waifu2x, ProcessingConfig
# Initialize with default settings
waifu2x = Waifu2x()
# Process a single image
result = waifu2x.process("input.jpg", "output_2x.jpg")
print(f"Processed image saved to: {result.output_path}")
Advanced Configuration
from waifu2x_python import Waifu2x, ProcessingConfig, ModelType
# Custom configuration
config = ProcessingConfig(
model=ModelType.UPCONV_7_ANIME, # or ModelType.CUNET, ModelType.UP_PHOTO, etc.
scale=2, # 1, 2, 4, 8, 16, 32
noise=1, # -1 to 3 (-1 = no effect, 0 = no noise reduction, 1-3 = noise reduction level)
gpu_id=0, # -1 for CPU-only, 0 for first GPU, 1 for second GPU, etc.
tile_size=0, # 0 for auto
num_threads=4 # Number of CPU threads to use
)
waifu2x = Waifu2x(config=config)
# Process all images in a folder
results = waifu2x.process_folder("input_folder", "output_folder")
print(f"Processed {len([r for r in results if r.success])}/{len(results)} images successfully")
Command Line Interface
# Basic usage
waifu2x -i input.jpg -o output.png
# Process folder recursively
waifu2x -i input_folder -o output_folder -r
# Custom settings
waifu2x -i input.jpg -o output.png -m models-upconv_7_anime_style_art_rgb -s 2 -n 1 -g 0 -t 200
# CPU-only mode
waifu2x -i input.jpg -o output.png -g -1
Available Models
models-cunet- High quality denoising and upscaling (default)models-upconv_7_anime_style_art_rgb- For anime-style artmodels-upconv_7_photo- For photos
License
This project is licensed under the MIT License - see the LICENSE file for details.
Acknowledgements
- waifu2x-ncnn-vulkan - The underlying engine
- ncnn - High-performance neural network inference framework
- Vulkan - Cross-platform 3D graphics and compute API
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
waifu2x_python-2.0.4.tar.gz
(22.1 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file waifu2x_python-2.0.4.tar.gz.
File metadata
- Download URL: waifu2x_python-2.0.4.tar.gz
- Upload date:
- Size: 22.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/6.1.0 CPython/3.13.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
0309f1e342c834fdec71ff47272af657ccefd5d30ff3ce444ded6772f706f25f
|
|
| MD5 |
007cc7cc3b64dcde8bdbfcf5d802044a
|
|
| BLAKE2b-256 |
6116cc1fce0e724449418a27b2c95a438024e1a6d7c2effaea469bc6f17bdf4c
|
File details
Details for the file waifu2x_python-2.0.4-py3-none-any.whl.
File metadata
- Download URL: waifu2x_python-2.0.4-py3-none-any.whl
- Upload date:
- Size: 21.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/6.1.0 CPython/3.13.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
90ae6db8dd190ce0dfe3fe9147f9eb24d6862d5a13969d6e98c53ba3ed55b4d0
|
|
| MD5 |
f37930acbae258f58076e2cc98d40773
|
|
| BLAKE2b-256 |
da9451b06fc7223ab682ecc1579fde00f01f776fa03ccfc1fcb33f59f4a82fdf
|