Hugging Face's logo

AterMors
/
Swin2-GTP2_art-caption

Image-to-Text
Transformers
Safetensors
English
vision-encoder-decoder
image-text-to-text
captioning
paintings
art
wikiart
Model card Files
xet
 Community

Image Captioning Model created with VisionEncoderDecoderModel architecture using "microsoft/swinv2-base-patch4-window12to16-192to256-22kto1k-ft" as image_encoder and "openai/gpt2" as text_decoder. It has been trained on a variant of the WikiArt dataset that can be found at "AterMors/wikiart_recaption".

Downloads last month
12
Safetensors
Model size
0.2B params
Tensor type
F32
·
Inference Providers NEW
Image-to-Text
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for AterMors/Swin2-GTP2_art-caption

Base model

microsoft/swinv2-base-patch4-window12to16-192to256-22kto1k-ft
Finetuned
(12)
this model

Dataset used to train AterMors/Swin2-GTP2_art-caption