Upload model files
Browse files- .gitattributes +1 -0
- 4xRealWebPhoto_v2.pdf +3 -0
- 4xRealWebPhoto_v2_rgt_s.txt +26 -0
- 4xRealWebPhoto_v2_rgt_s_fp32.onnx +3 -0
- 4xRealWebPhoto_v2_rtg_s.pth +3 -0
- 4xRealWebPhoto_v2_rtg_s.safetensors +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
4xRealWebPhoto_v2.pdf filter=lfs diff=lfs merge=lfs -text
|
4xRealWebPhoto_v2.pdf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b523a57625ffb90fc635c70ebdfd4d7b0444561630e8d925a90303f8e864518
|
3 |
+
size 4348366
|
4xRealWebPhoto_v2_rgt_s.txt
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Name: 4xRealWebPhoto_v2_rgt_s
|
2 |
+
License: CC BY 4.0
|
3 |
+
Author: Philip Hofmann
|
4 |
+
Network: RGT
|
5 |
+
Scale: 4
|
6 |
+
Release Date: 10.03.2024
|
7 |
+
Purpose: 4x real web photo upscaler, meant for upscaling photos downloaded from the web
|
8 |
+
Iterations: 220'000
|
9 |
+
epoch: 5
|
10 |
+
batch_size: 16
|
11 |
+
HR_size: 128
|
12 |
+
Dataset: 4xRealWebPhoto_v2 (see details in attached pdf file)
|
13 |
+
Number of train images: 1'086'976 (or 543'488 pairs)
|
14 |
+
OTF Training: No
|
15 |
+
Pretrained_Model_G: RGT_S_x4
|
16 |
+
|
17 |
+
Description:
|
18 |
+
4x real web photo upscaler, meant for upscaling photos downloaded from the web. Trained on my v2 of my 4xRealWebPhoto dataset, it should be able to handle realistic noise, jpg and webp compression and re-compression, scaling and rescaling with multiple downscampling algos, and handle a little bit of lens blur.
|
19 |
+
|
20 |
+
Thought featuring degraded images in the examples, this model should also be able to handle good quality input.
|
21 |
+
|
22 |
+
Details about the approach/dataset I made to train this model (and therefore also what this model would be capable of handling) is in the attached pdf.
|
23 |
+
|
24 |
+
My previous tries of this dataset, meaning v0 and v1, will get a separate entry, though this version would be recommended over them.
|
25 |
+
|
26 |
+
12 Examples on [Slowpics](https://slow.pics/s/HxXtE1eZ)
|
4xRealWebPhoto_v2_rgt_s_fp32.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c014ca191c9e3c41c47e26a6fe859a6847dd00d9d49073386e7104ac438450e
|
3 |
+
size 48824340
|
4xRealWebPhoto_v2_rtg_s.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdfacefe9e6d98df0423703ba373439fc257ab2f74035b3972ff3863eb207165
|
3 |
+
size 135976722
|
4xRealWebPhoto_v2_rtg_s.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a165ec6fafc3cb3bd62838f0a412f344618f1df8d7198283815eec41332b8f2e
|
3 |
+
size 135601676
|