---
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/4xFFHQDAT)

# 4xFFHQDAT

Name: 4xFFHQDAT  
Author: Philip Hofmann  
Release Date: 25.08.2023  
License: CC BY 4.0  
Network: DAT  
Scale: 4  
Purpose: 4x upscaling model for faces  
Iterations: 122000  
epoch: 2  
batch_size: 4  
HR_size: 128  
Dataset: FFHQ - full dataset till 50k, then first 10k img multiscaled (resulted in ~260k imgs, 126GB)  
Number of train images: 259990  
OTF Training: Yes  
Pretrained_Model_G: DAT_x4.pth  

Description: 4x photo upscaler for faces with otf jpg compression, blur and resize, trained on FFHQ dataset. This has been trained on and for faces, but i guess can also be used for other photos, might be able to retain skin detail. This is not face restoration, but simply a 4x upscaler trained on faces, therefore input images need to be of good quality if good output quality is desired.

Examples 4xFFHQDAT:  
[Imgsli1](https://imgsli.com/MjAwNjUz)  
[Imgsli2](https://imgsli.com/MjAwNjU0)  
[Imgsli3](https://imgsli.com/MjAwNjU2)  
[Imgsli4](https://imgsli.com/MjAwNjU3)  
[Imgsli5](https://imgsli.com/MjAwNjU4)  
[Imgsli6](https://imgsli.com/MjAwNjU5)  
[Imgsli7](https://imgsli.com/MjAwNzk0)  

![Example1](https://github.com/Phhofm/models/assets/14755670/3b69c1cb-3c94-4f26-8547-d8745a7165af)
![Example2](https://github.com/Phhofm/models/assets/14755670/57d92f97-0b62-44bc-ae6a-a15891d0d8a8)
![Example3](https://github.com/Phhofm/models/assets/14755670/968460e4-f94d-4c67-a657-4c634e1b03ff)
![Example4](https://github.com/Phhofm/models/assets/14755670/25261c31-a13c-43b3-96be-1116b4b12319)
![Example5](https://github.com/Phhofm/models/assets/14755670/b87b3226-24a5-4d17-a550-2c6894037e95)


---


Since the above 4xFFHQDAT model is not able to handle the noise present in low quality input images, i made a small variant/finetune of this, the 4xFFHQLDAT model. This model might come in handy if your input image is of bad quality/not suited for above model. I basically made this model in a response to an input image posted in upscaling-results channel as a request to this upscale model (since 4xFFHQDAT would not be able to handle noise), see Imgsli1 example below for result.

Name: 4xFFHQLDAT  
Author: Philip Hofmann  
Release Date: 25.08.2023  
License: CC BY 4.0  
Network: DAT  
Scale: 4  
Purpose: 4x upscaling model for low quality input photos of faces  
Iterations: 44000  
epoch: 0  
batch_size: 4  
HR_size: 128  
Dataset: FFHQ - full dataset till 50k, then first 10k img multiscaled (resulted in ~260k imgs, 126GB)  
Number of train images: 259990  
OTF Training: Yes  
Pretrained_Model_G: 4xFFHQDAT  

Examples 4xFFHQLDAT:  
[Imgsli1](https://imgsli.com/MjAwNjYx)  
[Imgsli2](https://imgsli.com/MjAwNjYy)  
[Imgsli3](https://imgsli.com/MjAwNjYz)  


![Example6](https://github.com/Phhofm/models/assets/14755670/61b3cff7-117b-4510-bdcf-cd49a1494227)
![Example7](https://github.com/Phhofm/models/assets/14755670/de8e63a4-3b7b-4583-b638-720bb6423b2d)