Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,48 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: cc-by-4.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-4.0
|
| 3 |
+
pipeline_tag: image-to-image
|
| 4 |
+
tags:
|
| 5 |
+
- pytorch
|
| 6 |
+
- super-resolution
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
[Link to Github Release](https://github.com/Phhofm/models/releases/tag/2xLexicaRRDBNet)
|
| 10 |
+
|
| 11 |
+
# 2xLexicaRRDBNet
|
| 12 |
+
|
| 13 |
+
Name: 2xLexicaRRDBNet
|
| 14 |
+
Author: Philip Hofmann
|
| 15 |
+
Release Date: 01.06.2023
|
| 16 |
+
License: CC BY 4.0
|
| 17 |
+
Network: RRDBNet
|
| 18 |
+
Scale: 2
|
| 19 |
+
Purpose: Upscaling AI generated images
|
| 20 |
+
Iterations: 185'000
|
| 21 |
+
batch_size: 4
|
| 22 |
+
HR_size: 128
|
| 23 |
+
Epoch: 17 (require iter number per epoch: 10964)
|
| 24 |
+
Dataset: lexica-aperture-v3-small
|
| 25 |
+
Number of train images: 43856
|
| 26 |
+
OTF Training: No
|
| 27 |
+
Pretrained_Model_G: None
|
| 28 |
+
|
| 29 |
+
Description: 2x upscaler for the AI generated image output. Trained on 43856 images from lexica.art, so its trained specifically on that model but should work in general on ai generated images.
|
| 30 |
+
|
| 31 |
+
16 Examples with Input, Upscaled (Normal and Sharp) and GT Files, plus example data: https://drive.google.com/drive/folders/1LT20d5u1m8CryCrXOJ7pWJd0mlN7X5yA
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
|
| 35 |
+
|
| 36 |
+
|
| 37 |
+
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
|
| 41 |
+
|
| 42 |
+
|
| 43 |
+
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
|
| 48 |
+
|