{
"name": "Text2HD v.1",
"author": "asterixcool",
"license": "CC-BY-SA-4.0",
"tags": [
"compression-removal",
"denoise",
"general-upscaler",
"jpeg",
"restoration",
"text"
],
"description": "Purpose: Upscale text in very low quality to normal quality.\n\nThe upscale model is specifically designed to enhance lower-quality text images, improving their clarity and readability by upscaling them by 2x. It excels at processing moderately sized text, effectively transforming it into high-quality, legible scans. However, the model may encounter challenges when dealing with very small text, as its performance is optimized for text of a certain minimum size. For best results, input images should contain text that is not excessively small.",
"date": "2024-08-27",
"architecture": "realplksr",
"size": null,
"scale": 2,
"inputChannels": 3,
"outputChannels": 3,
"resources": [
{
"urls": [
"https://github.com/starinspace/StarinspaceUpscale/releases/download/Models/2x_Text2HD_v.1-RealPLKSR.pth"
],
"sha256": "1aeb4f5816fa2fd302a2c8aef49c3252cc14a5e22c4d9359f5c266a823ceb269",
"size": 29580290,
"platform": "pytorch",
"type": "pth"
}
],
"images": [
{
"type": "paired",
"LR": "https://imgsli.com/i/46f1c843-958d-4310-80d4-9d7767fa42d4.jpg",
"SR": "https://imgsli.com/i/0527a29d-d889-4422-adde-5316a29c4b2e.jpg"
}
],
"dataset": "Scanned books and text",
"datasetSize": 8000,
"trainingIterations": 168000,
"trainingBatchSize": 8
}