Add files using upload-large-folder tool

62c53fc verified 6 months ago

3.52 kB

# Advanced AI Upscaling & Restoration Models
This repository contains a suite of my high-performance AI models for photorealistic upscaling and restoration. Each model, built on PyTorch architectures including [SwinIR](https://github.com/JingyunLiang/SwinIR), [ESRGAN](https://github.com/xinntao/Real-ESRGAN), [RealPLKSR](https://github.com/dslisleedh/PLKSR) and others, has been trained on my own dataset: a library of 11,500+ hand-selected and versatile real-world HD images of exceptional quality and information density. The result of this several months-long dataset curation effort is a set of models that excel at rendering authentic textures and objects (skin, fabric, grit, foliage, etc.) and intelligently handling a wide variety of image degradations. Both the dataset and models are under continuous development, with future releases targeting higher fidelity and generalization. All presented PyTorch models can be used in [Chainner](https://github.com/chaiNNer-org/chaiNNer-nightly). 

[![License: CC BY-NC-SA 4.0](https://img.shields.io/badge/License-CC%20BY--NC--SA%204.0-lightgrey.svg)](https://creativecommons.org/licenses/by-nc-sa/4.0/)

**15.02.2026 High-End Video Restoration & Upscaling Software in Development. Topaz -- I'm coming for you.**

---

**Software Development in Progress (see above)**

27.09.2025: **PureScale 1.0**

[**2x_PureScale**](https://github.com/limitlesslab/AI-upscaling-models/releases/tag/PureScale) - an upscaling model based on [RealPLKSR](https://github.com/dslisleedh/PLKSR/issues/4) (PixelShuffle) architecture designed for high-fidelity upscales of your real-world images (or videos). With regard to degradations, it only handles slight JPEG compression. The result is sharp, high-quality outputs that stay true to the original image. FP16 ONNX model is also attached for usage with NVIDIA TensorRT.

22.08.2025: **PureVision 1.0**

[**1x_PureVision**](https://github.com/daredevilstudio/AI-upscaling-models/releases/download/PureVision/1x_PureVision.pth) - this restoration model is based on [ESRGAN](https://github.com/xinntao/Real-ESRGAN) (PixelUnshuffle) architecture, trained to remove various types of compression artifacts: JPEG, WEBP, AVC (H.264), HEVC (H.265) and MPEG-2 and restore missing textures. The model also handles moderate noise and grain. The goal of the model is to make degraded images clear, more detailed and artifact-free. It is also suitable for restoring videos as a preparatory step before upscaling. 

[**2x_PureVision**](https://github.com/daredevilstudio/AI-upscaling-models/releases/download/PureVision/2x_PureVision.pth) - based on [ESRGAN](https://github.com/xinntao/Real-ESRGAN) (PixelUnshuffle) architecture, this model is trained similarly to 1x model, but handles heavier noise and grain and, likewise, is intelligent enough not to remove crucial detail at the same time, for example skin texture. The model has the ability to restore missing textures that were erased by heavy compression. It is designed to be a higher quality and more versatile replacement to the well-known official [RealESRGAN_x2plus](https://github.com/xinntao/Real-ESRGAN/releases/tag/v0.2.1). Additionally, the model is an excellent upscaler for videos, making the result detailed, polished, artifact and noise-free: it is recommended to use the FP16 [ONNX variant](https://github.com/daredevilstudio/AI-upscaling-models/releases/download/PureVision/2x_PureVision.onnx) of the model alongside NVIDIA TensorRT technology to speed up the upscaling process.

	# Advanced AI Upscaling & Restoration Models
	This repository contains a suite of my high-performance AI models for photorealistic upscaling and restoration. Each model, built on PyTorch architectures including [SwinIR](https://github.com/JingyunLiang/SwinIR), [ESRGAN](https://github.com/xinntao/Real-ESRGAN), [RealPLKSR](https://github.com/dslisleedh/PLKSR) and others, has been trained on my own dataset: a library of 11,500+ hand-selected and versatile real-world HD images of exceptional quality and information density. The result of this several months-long dataset curation effort is a set of models that excel at rendering authentic textures and objects (skin, fabric, grit, foliage, etc.) and intelligently handling a wide variety of image degradations. Both the dataset and models are under continuous development, with future releases targeting higher fidelity and generalization. All presented PyTorch models can be used in [Chainner](https://github.com/chaiNNer-org/chaiNNer-nightly).

	[![License: CC BY-NC-SA 4.0](https://img.shields.io/badge/License-CC%20BY--NC--SA%204.0-lightgrey.svg)](https://creativecommons.org/licenses/by-nc-sa/4.0/)

	15.02.2026 High-End Video Restoration & Upscaling Software in Development. Topaz -- I'm coming for you.

	---

	Software Development in Progress (see above)

	27.09.2025: PureScale 1.0

	[2x_PureScale](https://github.com/limitlesslab/AI-upscaling-models/releases/tag/PureScale) - an upscaling model based on [RealPLKSR](https://github.com/dslisleedh/PLKSR/issues/4) (PixelShuffle) architecture designed for high-fidelity upscales of your real-world images (or videos). With regard to degradations, it only handles slight JPEG compression. The result is sharp, high-quality outputs that stay true to the original image. FP16 ONNX model is also attached for usage with NVIDIA TensorRT.

	22.08.2025: PureVision 1.0

	[1x_PureVision](https://github.com/daredevilstudio/AI-upscaling-models/releases/download/PureVision/1x_PureVision.pth) - this restoration model is based on [ESRGAN](https://github.com/xinntao/Real-ESRGAN) (PixelUnshuffle) architecture, trained to remove various types of compression artifacts: JPEG, WEBP, AVC (H.264), HEVC (H.265) and MPEG-2 and restore missing textures. The model also handles moderate noise and grain. The goal of the model is to make degraded images clear, more detailed and artifact-free. It is also suitable for restoring videos as a preparatory step before upscaling.

	[2x_PureVision](https://github.com/daredevilstudio/AI-upscaling-models/releases/download/PureVision/2x_PureVision.pth) - based on [ESRGAN](https://github.com/xinntao/Real-ESRGAN) (PixelUnshuffle) architecture, this model is trained similarly to 1x model, but handles heavier noise and grain and, likewise, is intelligent enough not to remove crucial detail at the same time, for example skin texture. The model has the ability to restore missing textures that were erased by heavy compression. It is designed to be a higher quality and more versatile replacement to the well-known official [RealESRGAN_x2plus](https://github.com/xinntao/Real-ESRGAN/releases/tag/v0.2.1). Additionally, the model is an excellent upscaler for videos, making the result detailed, polished, artifact and noise-free: it is recommended to use the FP16 [ONNX variant](https://github.com/daredevilstudio/AI-upscaling-models/releases/download/PureVision/2x_PureVision.onnx) of the model alongside NVIDIA TensorRT technology to speed up the upscaling process.