---
license: cc-by-4.0
pipeline_tag: image-to-image
tags:
- pytorch
- super-resolution
---

[Link to Github Release](https://github.com/Phhofm/models/releases/tag/2xHFA2kAVCSRFormer_light)  

# 2xHFA2kAVCSRFormer_light

Name: 2xHFA2kAVCSRFormer_light  
Author: Philip Hofmann  
Release Date: 11.07.2023  
License: CC BY 4.0  
Network: SRFormer_light  
Scale: 2  
Purpose: 2x anime upscaling model that handles AVC (h264) compression  
Iterations: 140000  
batch_size: 2-4  
HR_size: 128-192  
Dataset: HFA2k_h264  
Number of train images: 2568  
OTF Training: No  
Pretrained_Model_G: SRFormerLight_SRx2_DIV2K.pth  

Description: 2x SRFormer_light anime upscale model that handles AVC (h264) compression since h264 crf 20-28 degradation together with bicubic, bilinear, box and lanczos downsampling has been applied on musl's HFA2k dataset with Kim's dataset destroyer for training.
  
If you want to run this model with chaiNNer (or another application) you need to use the onnx files with an onnx upscale node. All onnx conversions can be found in the [onnx folder](https://github.com/Phhofm/models/tree/main/2xHFA2kAVCSRFormer_light/onnx) on my repo.
  
Example 1: https://imgsli.com/MTkxMTQz  
Example 2: https://imgsli.com/MTkxMTQ0  

![Example1](https://github.com/Phhofm/models/assets/14755670/d790378e-3a06-4b3c-8d74-39378e82c19a)  
![Example2](https://github.com/Phhofm/models/assets/14755670/105b16c4-5041-48d5-a981-b2317bf79d4a)