Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
google
/
pix2struct-textcaps-base
like
28
Follow
Google
7.2k
Image-to-Text
Transformers
PyTorch
Safetensors
5 languages
pix2struct
image-text-to-text
arxiv:
2210.03347
License:
apache-2.0
Model card
Files
Files and versions
Community
5
Train
Deploy
Use this model
5ed5581
pix2struct-textcaps-base
/
preprocessor_config.json
ybelkada
Upload processor
06e4e67
almost 2 years ago
raw
Copy download link
history
blame
Safe
189 Bytes
{
"do_convert_rgb"
:
true
,
"do_normalize"
:
true
,
"image_processor_type"
:
"Pix2StructImageProcessor"
,
"patch_size"
:
[
16
,
16
]
,
"processor_class"
:
"Pix2StructProcessor"
}