|
--- |
|
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/4xBHI_dat2_otf) |
|
|
|
|
|
# 4xBHI_dat2_otf |
|
|
|
Scale: 4x |
|
Network type: DAT2 |
|
Author: Philip Hofmann |
|
License: CC-BY-4.0 |
|
Purpose: 4x upscaling images, handles noise and jpg compression |
|
Pretrained Model: 4xNomos2_hq_dat2 |
|
Training iterations: 270000 |
|
Description: 4x dat2 upscaling model, trained with the real-esrgan otf pipeline on my bhi dataset. Handles noise and compression. |
|
|
|
![Example1](https://github.com/user-attachments/assets/8708dd98-3ae8-4139-b5e4-85946739ed04) |
|
![Example2](https://github.com/user-attachments/assets/cfc3f750-609b-4286-a45d-61a8f301fc8e) |
|
![Example3](https://github.com/user-attachments/assets/7c3d10c7-434c-472a-8ba5-1f3cdb9a5923) |
|
![Example4](https://github.com/user-attachments/assets/30579c0a-84f8-4a14-aa9a-2c0e565d74c0) |
|
|