Upload Model Files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+4xRealWebPhoto.pdf filter=lfs diff=lfs merge=lfs -text

4xRealWebPhoto.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb956d5550d947ddaaf7c816ca646991e68d7c9ae70876943fe6762a4e9a80ac
+size 10133975

4xRealWebPhoto_RGT.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0a726e389a51010e0a2aaa79cf57ceb6f067c27e3a811c8309aa1801b9971e5
+size 180369878

4xRealWebPhoto_RGT.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2ca41ef2eed87ae46fdfb225b4c30257f8927c1ff7ba3fe1d912795637464d8
+size 179871484

4xRealWebPhoto_RGT.txt

@@ -0,0 +1,24 @@
+Name: 4xRealWebPhoto_RGT
+License: CC BY 4.0
+[Google Drive Folder](https://drive.google.com/drive/folders/1stOfI5a2W8KTI-FAbhFhmkYo2JEtjoGi?usp=drive_link)
+Author: Philip Hofmann
+Network: RGT
+Scale: 4
+Release Date: 10.03.2024
+Purpose: 4x real web photo upscaler, meant for upscaling photos downloaded from the web
+Iterations: 260'000
+epoch: 71
+batch_size: 12
+HR_size: 128
+Dataset: 4xRealWebPhoto
+Number of train images: 6118
+OTF Training: No
+Pretrained_Model_G: RGT_x4
+
+Description:
+4x real web photo upscaler, meant for upscaling photos downloaded from the web. Trained on my v1 of my 4xRealWebPhoto dataset, it should be able to handle noise, jpg and webp (re)compression, (re)scaling, and a bit of lens blur. I tried to simulate the use case of someone uploading a photo (maybe noisy, maybe blurry, maybe noisy&blurry) to the web (for example social media) where the provider would downscale&compress the image, and then another user downloading and re-uploading it on the web (recompression & rescale).
+
+Workflow for dataset degradation can be found [in this pdf](https://drive.google.com/file/d/1JmB4yxGtZQAtFwKn3DmKAPzfjC2SZNQ1/view?usp=drive_link) and models can be found [in this google drive folder](https://drive.google.com/drive/folders/1stOfI5a2W8KTI-FAbhFhmkYo2JEtjoGi?usp=drive_link). v0 was basically trained on a degraded RSBlur dataset with strong motion blur, v1 (this one) was on nomos8k_sfw, and v2 was on nomos8k with multiscale and variants, also different degradation values.  
+
+12 Examples:   
+[Slowpics](https://slow.pics/s/HxXtE1eZ) 

4xRealWebPhoto_RGT_fp32.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:480142fdf4851e25ef8726601fca7e593e37898854d1899a346826aef0b16a33
+size 63807295

4xRealWebPhoto_v0_rgt_s.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:238a0a458b22e1daedca83d50ecd733d302bd45dd866083e5dbced8212ce6d33
+size 135972144

4xRealWebPhoto_v0_rgt_s.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07ce83090893840edf80a01ce6811d5febea804b0c7055641c2bdc6f9c103fe6
+size 135601676

4xRealWebPhoto_v0_rgt_s_fp32.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aca3ce1333b5025aa6ee96681ec6750298aab1ea77377f4b0a06c81e3e114c9d
+size 48824340