Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,52 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: cc-by-4.0
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-4.0
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
[Link to Github Release](https://github.com/Phhofm/models/releases/tag/4xHFA2k_ludvae_realplksr_dysample)
|
| 6 |
+
|
| 7 |
+
# 4xHFA2k_ludvae_realplksr_dysample
|
| 8 |
+
Scale: 4
|
| 9 |
+
Architecture: [RealPLKSR with Dysample](https://github.com/muslll/neosr/?tab=readme-ov-file#supported-archs)
|
| 10 |
+
Architecture Option: [realplksr](https://github.com/muslll/neosr/blob/master/neosr/archs/realplksr_arch.py)
|
| 11 |
+
|
| 12 |
+
Author: Philip Hofmann
|
| 13 |
+
License: CC-BY-0.4
|
| 14 |
+
Purpose: Restoration
|
| 15 |
+
Subject: Anime
|
| 16 |
+
Input Type: Images
|
| 17 |
+
Release Date: 13.07.2024
|
| 18 |
+
|
| 19 |
+
Dataset: HFA2k_LUDVAE
|
| 20 |
+
Dataset Size: 10'272
|
| 21 |
+
OTF (on the fly augmentations): No
|
| 22 |
+
Pretrained Model: [4xNomos2_realplksr_dysample](https://github.com/Phhofm/models/releases/tag/4xNomos2_realplksr_dysample)
|
| 23 |
+
Iterations: 165'000
|
| 24 |
+
Batch Size: 12
|
| 25 |
+
GT Size: 256
|
| 26 |
+
|
| 27 |
+
Description:
|
| 28 |
+
A Dysample RealPLKSR 4x upscaling model for anime single-image resolution.
|
| 29 |
+
The dataset has been degraded using DM600_LUDVAE, for more realistic noise/compression. Downscaling algorithms used were imagemagick box, triangle, catrom, lanczos and mitchell. Blurs applied were gaussian, box and lens blur (using chaiNNer). Some images were further compressed using -quality 75-92. Down-up was applied to roughly 10% of the dataset (5 to 15% variation in size). Degradations orders were shuffled, to give as many variations as possible.
|
| 30 |
+
|
| 31 |
+
Examples are inferenced with [neosr](https://github.com/muslll/neosr) testscript and the released pth file. I include the test images also as a zip file in this release together with the model outputs, so others can test their models against these test images aswell to compare.
|
| 32 |
+
|
| 33 |
+
onnx conversions are static since dysample doesnt allow dynamic conversion, I tested the conversions with [chaiNNer](https://github.com/chaiNNer-org/chaiNNer).
|
| 34 |
+
|
| 35 |
+
Showcase:
|
| 36 |
+
[Slowpics](https://slow.pics/c/FKDZAcyI)
|
| 37 |
+
|
| 38 |
+
(Click Image to enlarge)
|
| 39 |
+
|
| 40 |
+
|
| 41 |
+
|
| 42 |
+
|
| 43 |
+
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
|