Phips commited on
Commit
ffa709e
·
verified ·
1 Parent(s): a88a0c6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +53 -3
README.md CHANGED
@@ -1,3 +1,53 @@
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/4xNomos2_hq_mosr)
10
+
11
+
12
+ # 4xNomos2_hq_mosr
13
+ Scale: 4
14
+ Architecture: [MoSR](https://github.com/umzi2/MoSR)
15
+ Architecture Option: [mosr](https://github.com/umzi2/MoSR/blob/95c5bf73cca014493fe952c2fbc0bdbe593da08f/neosr/archs/mosr_arch.py#L117)
16
+
17
+ Author: Philip Hofmann
18
+ License: CC-BY-0.4
19
+ Purpose: Upscaler
20
+ Subject: Photography
21
+ Input Type: Images
22
+ Release Date: 25.08.2024
23
+
24
+ Dataset: [nomosv2](https://github.com/muslll/neosr/?tab=readme-ov-file#-datasets)
25
+ Dataset Size: 6000
26
+ OTF (on the fly augmentations): No
27
+ Pretrained Model: [4xmssim_mosr_pretrain](https://github.com/Phhofm/models/releases/tag/4xmssim_mosr_pretrain)
28
+ Iterations: 190'000
29
+ Batch Size: 6
30
+ Patch Size: 64
31
+
32
+ Description:
33
+ A 4x [MoSR](https://github.com/umzi2/MoSR) upscaling model, meant for non-degraded input, since this model was trained on non-degraded input to give good quality output.
34
+
35
+ If your input is degraded, use a 1x degrade model first. So for example if your input is a .jpg file, you could use a 1x dejpg model first.
36
+
37
+ PS I also provide an onnx conversion in the Attachements, I verified correct output with chainner:
38
+
39
+ <img src="https://github.com/user-attachments/assets/7f2be678-9d63-43e3-bfb6-59c94827a828" width=25% height=25%>
40
+
41
+ ## Model Showcase:
42
+ [Slowpics](https://slow.pics/c/cqGJb0gT)
43
+
44
+ (Click on image for better view)
45
+ ![Example1](https://github.com/user-attachments/assets/f7af4d9c-c40f-45bf-a2b5-7d11fea31ee8)
46
+ ![Example2](https://github.com/user-attachments/assets/4796cd41-fa12-493b-abb0-c4a62c6baa0c)
47
+ ![Example3](https://github.com/user-attachments/assets/d069d258-3151-4b28-9328-caace08a3390)
48
+ ![Example4](https://github.com/user-attachments/assets/8826faa6-d52c-468a-ab6a-7c60d30410f8)
49
+ ![Example5](https://github.com/user-attachments/assets/350d9810-715e-424e-911e-2d4818ddaa31)
50
+ ![Example6](https://github.com/user-attachments/assets/803997bc-c640-4bac-ab0f-76fc8e1d594b)
51
+ ![Example7](https://github.com/user-attachments/assets/dd81d313-b07a-426c-ad4d-376f48631f05)
52
+ ![Example8](https://github.com/user-attachments/assets/932617fc-a5c4-46b6-95a5-553bc302d027)
53
+ ![Example9](https://github.com/user-attachments/assets/2e205c4d-5da2-47ca-b9f4-c5218be7d74d)