Promote Sign in Sign up

Multimodal model

vit-gpt2-image-captioning

Listed for image to text. Explore the model card for usage and requirements.

nlpconnect Multimodal Open weights apache-2.0
Open model card ↗
Type
Multimodal
Weights
Open
Downloads
83k
Likes
935
Pipeline
image to text
License
apache-2.0

Model hub

nlpconnect/vit-gpt2-image-captioning

Repo
nlpconnect/vit-gpt2-image-captioning
Library
transformers
Access
Public
Technical tags and languages
transformers pytorch vision-encoder-decoder image-text-to-text image-to-text image-captioning doi:10.57967/hf/0222 endpoints_compatible
Open on Hugging Face