๐Ÿ’– ACKNOWLEDGEMENTS

Thank You & Acknowledgements

Rice Upscaler is built on cutting-edge AI research and open-source generosity. Our gratitude to these foundational projects:

๐ŸŒ Project & Source

Official Site

Rice Upscaler Website

Official homepage, distribution and release updates.

https://riceupscaler.techomespace.com โ†—
Repository

Rice Upscaler GitHub

Source code, issue tracker, documentation and releases.

https://github.com/blackmagicc093/rice-upscaler โ†—

โšก AI & Upscaling Engines

Transformer

DAT (Dual Aggregation Transformer)

SOTA Transformer for image super-resolution (CVPR). Preserves textures and fine details.

https://github.com/zhengchen1999/DAT โ†—
GAN

Real-ESRGAN

Practical image and anime restoration. Removes compression artifacts and blur.

https://github.com/xinntao/Real-ESRGAN โ†—
Classic

Lanczos Resampling

High-quality windowed sinc resampling. Runs near-instantly without GPU.

https://en.wikipedia.org/wiki/Lanczos_resampling โ†—

๐Ÿ› ๏ธ Frameworks & Libraries

Vulkan GPU

Tencent ncnn

High-performance neural network inference optimized for cross-vendor Vulkan GPUs.

https://github.com/Tencent/ncnn โ†—
DirectX 12

Microsoft DirectML

Hardware-accelerated DirectX 12 ML library for high-performance inference on Windows.

https://github.com/microsoft/DirectML โ†—
Framework

PyTorch

Leading open-source deep learning framework for AI architectures.

https://pytorch.org โ†—
Imaging

Pillow (PIL)

Python Imaging Library โ€” cornerstone of Python image processing workflows.

https://python-pillow.org โ†—