PaddleOCR-VL-For-Manga

jzhang533/PaddleOCR-VL-For-Manga

Image Text to Text959M parametersPaddleOCRLicense: apache-2.0
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
853
Total downloads
20.7K
Gained 7D
Gained 30D
Likes
134
Rank · tracked models
#26,091
224(down 224 places)this week
Parameters
959M
Last source update
Nov 12, 2025
  • It moved from #2623 to #2660 among tracked Image Text to Text models this week.

Downloads over time

Rolling recent-window downloads as reported

Likes over time

Rank among tracked models

Lower is better

Overview

PaddleOCR-VL-For-Manga is a image text to text model published by jzhang533. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it 1h ago.

Published
Nov 5, 2025
Last updated
Nov 12, 2025
Library
PaddleOCR
License
apache-2.0
Task
Image Text to Text
Parameters
958,588,736
Spaces
Derivative models
Velocity 7D/day
PaddleOCRsafetensorspaddleocr_vlOCRMangaimage-text-to-textconversationalcustom_codejamultilingualdataset:hal-utokyo/Manga109-sbase_model:PaddlePaddle/PaddleOCR-VL

Publisher

jzhang533View publisher statistics →

Derived from PaddlePaddle/PaddleOCR-VL (reported by the source; parent not yet tracked).

Similar models

Models similar to PaddleOCR-VL-For-Manga
ModelDL 30D
PaddleOCR-VL-1.6PaddlePaddle40.5K
PaddleOCR-VL-1.5PaddlePaddle14.7K
PaddleOCR-VLPaddlePaddle8,609
PaddleOCR-VL-0.9Blvyufeng2,554
NVIDIA-Nemotron-Parse-v1.1nvidia178.2K
NVIDIA-Nemotron-Parse-v1.1-TCnvidia215