Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
ziffir
/
PASDV1
like
4
Image-to-Text
sbu_captions
visual_genome
HuggingFaceM4/VQAv2
ChristophSchuhmann/MS_COCO_2017_URL_TEXT
English
image-captioning
visual-question-answering
arxiv:
2308.14469
License:
apache-2.0
Model card
Files
Files and versions
Community
Edit model card
arxiv.org/abs/2308.14469
Downloads last month
0
Inference API
Image-to-Text
Drag image file here or click to browse from your device
Browse for image
Unable to determine this model's library. Check the
docs
.
JSON Output
Maximize
Datasets used to train
ziffir/PASDV1
HuggingFaceM4/VQAv2
Updated
Jun 30, 2022
•
4.7k
•
11
visual_genome
Preview
•
Updated
Jun 29, 2023
•
2.99k
•
58
ChristophSchuhmann/MS_COCO_2017_URL_TEXT
Viewer
•
Updated
Nov 27, 2021
•
273
•
16