[MODEL ADD REQUEST] 4x_Alchemy

[renarchi]

{
"name": "4x_Alchemy",
"author": "renarchi",
"license": "CC-BY-SA-4.0",
"tags": [
"general-upscaler",
"compression-removal"

],
"description": "This is the second model I trained with GAN and the first model I trained for this purpose.
I am still trying to understand training with GAN and improve my results.
The worst thing about the model is that it is quite good in some details but quite bad in others.
If I train the V2, I will try to fix this problem.",
"date": "2025-08-14",
"architecture": "realplksr_dysample",
"scale": 4,
"resources": [
{
"urls": [
"https://mega.nz/file/elxCgDwB#Tdr7RKfaKx993_zFIX3WLBqr1ms4NHD-u3ATYkUhJtc"
],
"platform": "pytorch",
"type": "pth"
}
],
"images": [
{
"type": "paired",
"LR": "https://imgsli.com/i/b05e0fdc-7861-48dc-bf0e-a8af14023ac2.jpg",
"SR": "https://imgsli.com/i/2d6439ae-3aaf-4e8f-b7dd-8f11fd369f3d.jpg",
"caption": "Lovelive"
},
{
"type": "paired",
"LR": "https://imgsli.com/i/2d6439ae-3aaf-4e8f-b7dd-8f11fd369f3d.jpg",
"SR": "https://imgsli.com/i/59082a81-6e30-4f07-87a0-619ae72a50f5.jpg",
"caption": "Kaoruhana"
}
],
"dataset": "Handpicked fanart",
"datasetSize": 3500,
"trainingIterations": 90000,
"trainingBatchSize": 8,
"trainingOTF": true
}