Model Details
Full Model IDPaddlePaddle/PaddleOCR-VL-1.5
Pipeline / Taskimage-text-to-text
LibraryPaddleOCR
Downloads (all-time)375.3K
Likes574
Last Modified3/17/2026
Author / OrgPaddlePaddle
PrivateNo — public
⚡ Quick Usage (Python)
Using the 🤗 Transformers library. Install with pip install transformers
from transformers import pipeline
# Load the model
pipe = pipeline("image-text-to-text", model="PaddlePaddle/PaddleOCR-VL-1.5")
# Run inference
result = pipe("Your input here")
print(result)🏷️ Tags
PaddleOCRsafetensorspaddleocr_vlERNIE4.5PaddlePaddleimage-to-textocrdocument-parselayouttableformulachartsealspottingimage-text-to-textconversationalcustom_codeenzhmultilingualarxiv:2601.21957base_model:baidu/ERNIE-4.5-0.3B-Paddlebase_model:finetune:baidu/ERNIE-4.5-0.3B-Paddlelicense:apache-2.0eval-resultsregion:us
More image-text-to-text Models
See all →🚀 Use This Model
Access model files, inference API, and full documentation on Hugging Face.
Open on Hugging Face →Browse Model Files ↗← Browse All Models🤖 Task: image-text-to-text
This model is designed for the image-text-to-text task. Explore more models for this use case.
All image-text-to-text Models →📊 Popularity
⬇ Downloads375.3K
❤️ Community Likes574
🛠️ Requirements
- →Install: pip install PaddleOCR
- →Python 3.8+ recommended for Transformers.
- →GPU (CUDA) speeds up inference significantly.
- →Use model.half() for fp16 on limited VRAM.