---
license: cc-by-4.0
---

[Link to Github Release](https://github.com/Phhofm/models/releases/tag/2xHFA2kAVCCompact)

Name: 2xHFA2kAVCCompact  
Author: Philip Hofmann  
Release Date: 18.06.2023  
License: CC BY 4.0  
Network: SRVGGNet  
Scale: 2  
Purpose: Fast 2x anime upscaling model that handles AVC (h264) degradation  
Iterations: 111,000  
batch_size: 4  
HR_size: 256  
Dataset: HFA2k_h264  
Number of train images: 2568  
OTF Training: No  
Pretrained_Model_G: None  

Description: A 2x Compact anime upscale model that handles AVC (h264) degradation. Applied h264 crf 20-28 degradation together with bicubic, bilinear, box and lanczos downsampling on the HFA2k dataset with Kim's dataset destroyer. 

![image](https://github.com/Phhofm/models/assets/14755670/7cd72469-4631-4f20-b5af-227692b1879a)
![324388155-7cd72469-4631-4f20-b5af-227692b1879a](https://github.com/Phhofm/models/assets/14755670/d641c8b4-6061-4131-9aeb-7bac0f49e1d1)