Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

google
/
pix2struct-base

Image-to-Text
Transformers
PyTorch
Safetensors
pix2struct
image-text-to-text
Model card Files Files and versions
xet
Community
10

Instructions to use google/pix2struct-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use google/pix2struct-base with Transformers:

    # Use a pipeline as a high-level helper
    # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5.
    # You must load the model directly (see below) or downgrade to v4.x with:
    # 'pip install "transformers<5.0.0'
    from transformers import pipeline
    
    pipe = pipeline("image-to-text", model="google/pix2struct-base")
    # Load model directly
    from transformers import AutoProcessor, AutoModelForImageTextToText
    
    processor = AutoProcessor.from_pretrained("google/pix2struct-base")
    model = AutoModelForImageTextToText.from_pretrained("google/pix2struct-base")
  • Notebooks
  • Google Colab
  • Kaggle
New discussion
Resources
  • PR & discussions documentation
  • Code of Conduct
  • Hub documentation

Use the model offline

#10 opened over 1 year ago by
mariaclaraXXXXX

Text Banner

#9 opened about 2 years ago by
samxaverian

What's the maximum supported decoder length?

#8 opened over 2 years ago by
jiang719

How to use this model to extract html structure from image?

8
#7 opened over 2 years ago by
Alexziyu

Pix2struct Sagemaker deployment Failing because of task Incompatibility

#5 opened almost 3 years ago by
lalaser1899

Configuration fix to allow fine-tuning

#3 opened about 3 years ago by
gbarello

cannot import name 'Pix2StructForConditionalGeneration' and AttributeError in 'AutoProcessor'

2
#2 opened about 3 years ago by
pathikg
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs