Document Conversion with POINTS Reader 📖
Using tencent/POINTS-Reader Multimodal for Image Content Extraction
Model in Use ⚡
tencent/POINTS-Reader
Query Input
Perform OCR on the image precisely.
Upload Image
Drop Image Here
- or -
Click to Upload
Advanced Settings
▼
Max New Tokens
↺
512
8192
Temperature
↺
0.1
1
Top-p (nucleus sampling)
↺
0.05
1
Top-k
↺
1
100
Repetition penalty
↺
1
2
PDF Export Settings
Font Size
Line Spacing
Text Alignment
Image Size in PDF
🚀 Process Image
🗑️ Clear All
📝 Extracted Content
📰 README.md
📋 PDF Preview
📝 Extracted Content
📰 README.md
📋 PDF Preview
Raw Model Output (max T ≤ 120s)
Examples
Report-Bug💻
|
prithivMLmods🤗