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
Use the model offline
#10 opened almost 2 years 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