PaddleOCR-VL-For-Manga Demo
Model
:
jzhang533/PaddleOCR-VL-For-Manga
Features:
Fine-tuned from
PaddleOCR-VL
Trained on Manga109-s dataset + 1.5M synthetic samples
Achieves 70% full-sentence accuracy on manga crops
Upload Manga Image
Drop Image Here
- or -
Click to Upload
Recognize Text 📖
Example Images
Recognized Text